{"id":"d2a17242-f55b-4d28-9d8d-dcfa48f8ed4e","entityType":"agent","slug":"clawhub-deciqai-latticework","name":"Latticework","canonicalUrl":"https://www.xpersona.co/agent/clawhub-deciqai-latticework","canonicalPath":"/agent/clawhub-deciqai-latticework","generatedAt":"2026-10-11T20:57:33.597Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":null},"description":"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s... Skill: Latticework Owner: deciqai Summary: Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s... Tags: latest:1.0.5 Version history: v1.0.5 | 2026-07-16T18:04:38.150Z | user Description tail link + agents machine-readable metadata line (deciqai.com/s/latticework.json) v1.0.4 | 2026-07-10T10:26:34.695Z | user Add","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17a4mqcnk515kvaca5ze55d0x88pfpx:latticework","sourceUrl":"https://clawhub.ai/deciqai/latticework","homepage":"https://clawhub.ai/deciqai/skills/latticework","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/deciqai/latticework","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/deciqai/skills/latticework","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":null},"stars":null,"forks":null,"downloads":1033,"packageName":null,"latestVersion":"1.0.5","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:57:58.397Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T15:57:58.410Z","lastCrawledAt":"2026-10-11T15:57:58.397Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T15:57:58.397Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.5","createdAt":"2026-07-16T18:04:38.150Z","changelog":"Description tail link + agents machine-readable metadata line (deciqai.com/s/latticework.json)","fileCount":6,"zipByteSize":12236},{"version":"1.0.4","createdAt":"2026-07-10T10:26:34.695Z","changelog":"Add 2024-2026 AI-era worked example + updated sources","fileCount":6,"zipByteSize":12195},{"version":"1.0.3","createdAt":"2026-07-08T11:07:28.566Z","changelog":"Footer now uses /c/<slug> short link (fixes UTM truncation when SKILL.md is read in a terminal)","fileCount":5,"zipByteSize":7794},{"version":"1.0.2","createdAt":"2026-07-08T00:52:15.508Z","changelog":"Refreshed content + GitHub star link in footer","fileCount":5,"zipByteSize":7897},{"version":"1.0.1","createdAt":"2026-07-07T22:28:00.331Z","changelog":"Add catalog categories and topics","fileCount":5,"zipByteSize":7682},{"version":"1.0.0","createdAt":"2026-06-29T09:18:02.398Z","changelog":"Initial publish","fileCount":5,"zipByteSize":7730}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17a4mqcnk515kvaca5ze55d0x88pfpx:latticework","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:57:33.594Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":null},"readme":"Skill: Latticework\n\nOwner: deciqai\n\nSummary: Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s...\n\nTags: latest:1.0.5\n\nVersion history:\n\nv1.0.5 | 2026-07-16T18:04:38.150Z | user\n\nDescription tail link + agents machine-readable metadata line (deciqai.com/s/latticework.json)\n\nv1.0.4 | 2026-07-10T10:26:34.695Z | user\n\nAdd 2024-2026 AI-era worked example + updated sources\n\nv1.0.3 | 2026-07-08T11:07:28.566Z | user\n\nFooter now uses /c/<slug> short link (fixes UTM truncation when SKILL.md is read in a terminal)\n\nv1.0.2 | 2026-07-08T00:52:15.508Z | user\n\nRefreshed content + GitHub star link in footer\n\nv1.0.1 | 2026-07-07T22:28:00.331Z | user\n\nAdd catalog categories and topics\n\nv1.0.0 | 2026-06-29T09:18:02.398Z | user\n\nInitial publish\n\nArchive index:\n\nArchive v1.0.5: 6 files, 12236 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), examples/reasoning-about-the-ai-boom-2024-2026.md (7710b), references/sources.md (1627b), skill-card.md (2317b), SKILL.md (6552b), _meta.json (130b)\n\nFile v1.0.5:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage). More: deciqai.com/c/latticework\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with `first-principles`, `second-order-thinking`, `probabilistic-thinking`, and `map-is-not-the-territory`.\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n- Judging an AI-boom / AI-adoption / AI-hype bet where \"is it a bubble?\" and \"is it real?\" are being argued through one lens each\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n*→ 2026 lens: [Reasoning About the AI Boom (2024–2026)](examples/reasoning-about-the-ai-boom-2024-2026.md) — economics × psychology × systems × game theory on one situation*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — 227 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/c/latticework** · ⭐ Star the repo → https://github.com/deciqAI/knowledge-skills · Contributions welcome.*\n\n*Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/latticework.json*\n\nFile v1.0.5:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.5\",\n  \"publishedAt\": 1784225078150\n}\n\nFile v1.0.5:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644285. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n- Stanford Institute for Human-Centered AI (HAI). *AI Index Report* (2024 and 2025 editions). https://aiindex.stanford.edu — annual data on model training costs, enterprise AI adoption, and investment; the empirical backdrop for the 2024–2026 AI-boom latticework example.\n- Brown, T., et al. (2020). \"Language Models are Few-Shot Learners.\" arXiv:2005.14165. https://arxiv.org/abs/2005.14165 — foundational scaling / compute-cost paper underpinning the economics-vs-systems tension in the AI capex debate.\n\nFile v1.0.5:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.5:examples/reasoning-about-the-ai-boom-2024-2026.md\n\n# Method in Action: Reasoning About the AI Boom (2024–2026)\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\nBetween 2024 and 2026 the generative-AI build-out became the single most consequential — and most contested — allocation question in technology. Bulls saw a general-purpose technology on the scale of electricity; bears saw a capital bubble reminiscent of telecom fiber in 1999–2001. The debate stalled largely because each camp reasoned through **one lens**: an economist saw capex and margins, a psychologist saw hype and FOMO, an operator saw feedback loops, a strategist saw a game-theoretic race. Latticework's claim is that the honest answer only appears when these run *side by side* — where they converge, confidence is high; where they diverge is exactly what you don't yet know. Below the anchor case is walked through this skill's own five-step Process.\n\n# Latticework Analysis: The 2024–2026 AI capital boom\n\n## 1 — Phenomenon\n\n**Core question:** Is the 2024–2026 AI infrastructure build-out (compute capex, model labs, enterprise adoption) a durable platform shift worth its cost, a bubble, or both at once — and how should a builder or investor act under that uncertainty?\n\n**Prior single-model framing + its known blind spot:** The dominant framing was financial — \"look at the revenue vs. the capex.\" Its blind spot: a pure capex/margin model treats demand, incentives, and belief as exogenous. It cannot explain *why* rational firms keep spending faster than near-term revenue justifies, nor whether adoption compounds or plateaus. Forcing the whole phenomenon through one discipline is the failure mode latticework exists to catch.\n\n## 2 — Lenses (independent disciplines)\n\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics (capex/margins) | Frontier-model training and datacenter capex run far ahead of attributable AI revenue; depreciation on fast-obsolescing GPUs pressures returns. Capital-intensive, thin near-term margins. | − |\n| 2 | Psychology (hype/FOMO) | Narrative, availability, and social proof inflate expectations; \"can't afford to be left behind\" drives spend detached from unit economics. Overshoot likely. | − |\n| 3 | Systems (feedback loops) | Reinforcing loops (better models → more usage → more data/revenue → more compute) can compound real value; but delays between capex and payoff cause overshoot and oscillation. | + / delay |\n| 4 | Game theory (the lab race) | Multi-player race among a few well-capitalized labs and clouds: unilateral slowing risks ceding the frontier, so each rationally over-invests even knowing collective overshoot is possible. | + spend / − discipline |\n\nEach lens is genuinely independent: they make different, falsifiable predictions rather than re-labeling one story.\n\n## 3 — Convergence Map\n\n**≥2 lenses agree (higher-confidence):**\n- Economics **and** Psychology **and** Game theory all predict *spending outruns near-term justification*. Three independent disciplines converging on \"capex overshoot is likely\" makes that a high-confidence read — regardless of whether the underlying technology is real.\n- Systems **and** Game theory agree the *build-out itself is somewhat self-sustaining in the short run*: the race guarantees continued spend, and reinforcing loops mean early capacity can find demand.\n\n**Lenses disagree (live unknown — investigate):**\n- Economics says \"returns may not clear the cost of capital\"; Systems says \"reinforcing adoption loops could eventually make them clear.\" The divergence *is the question*: does enterprise adoption compound (loop dominates) or plateau (capex model dominates)? This is where investigation should concentrate — measure real retention and revenue durability, not announced capex.\n\n**Lollapalooza: multiplicatively aligned forces?** Yes, on the *upside of spend*: FOMO (psychology) × competitive race (game theory) × reinforcing usage loops (systems) push in the same direction simultaneously — which is precisely why the boom accelerated rather than self-correcting early. The same multiplicative alignment that produces genuine platform shifts also produces bubbles; a lollapalooza signals *magnitude and speed*, not *direction of truth*. It is a reason to expect a large move, not evidence the move is justified.\n\n## 4 — Blind Spots\n\nWhat no lens above covers:\n- **Regulation / geopolitics** — export controls, energy/permitting limits, and safety rules can bind harder than any market force; not captured by economics, psychology, systems, or the lab-race framing as drawn.\n- **Physical constraints** — power availability, grid interconnection, and chip supply may cap the build-out independent of demand or belief.\n- **Discontinuous capability** — the models could improve (or stall) in step-changes that none of the four lenses forecast; a genuine black-swan channel.\n\nNaming these is the point: a latticework that cannot state its own blind spots is a single lens wearing a costume.\n\n## 5 — Calibrated Conclusion\n\n**Recommendation + Confidence:** Treat the 2024–2026 AI boom as *\"real platform shift AND capital overshoot, simultaneously\"* — the two are not mutually exclusive (fiber in 1999 was overbuilt *and* underpinned the real internet). High confidence (three independent lenses converge) that near-term spend outruns near-term returns and that a repricing of over-levered players is plausible. Moderate confidence that durable value accrues to whoever controls the compounding loops (distribution, proprietary data, retained users) rather than to raw capex. For a builder: avoid competing on capex you can't sustain; build on top of the infrastructure and own a reinforcing loop. For an investor: size for overshoot and separate \"the technology is real\" from \"this specific entity's returns clear its cost of capital.\"\n\n**Key residual uncertainty:** Whether enterprise/consumer AI usage *retains and monetizes* (loop compounds) or *plateaus after novelty* (capex model wins). This single variable flips the conclusion.\n\n**Information that would most change the picture:** Hard data on cohort retention and gross-margin trajectory of AI revenue (not gross bookings), GPU depreciation schedules actually realized, and any binding regulatory/energy constraint. A durable, improving retention curve moves weight decisively toward the systems lens; a plateau moves it toward economics.\n\n---\n\nThe discipline this case illustrates: no single 2024–2026 hot take (\"it's a bubble\" / \"it changes everything\") was *wrong* so much as *partial*. Running economics, psychology, systems, and game theory in parallel converts a shouting match into a map — with a high-confidence zone (spend overshoots), a marked live unknown (does adoption compound?), and named blind spots (regulation, power, capability jumps). That map, not a verdict, is the deliverable.\n\n*Sources: Munger, C. T. (1994/2005), \"A Lesson on Elementary, Worldly Wisdom,\" in* Poor Charlie's Almanack *(Donning Company) — the latticework method. Bevelin, P. (2003),* Seeking Wisdom: From Darwin to Munger *(Post Scriptum) — cross-disciplinary application. On the AI capex-vs-revenue debate and the fiber/telecom bubble analogy widely discussed 2024–2025: reporting and commentary in the* Financial Times*,* The Economist*, and Stanford HAI's* AI Index Report *2024/2025 (documenting rising training costs and enterprise adoption); the \"GPT-3\" scaling and compute-cost literature (Brown et al., 2020, \"Language Models are Few-Shot Learners,\" arXiv:2005.14165). Specific figures are omitted here in favor of durable, widely-reported directional facts as of early 2026.*\n\nFile v1.0.5:skill-card.md\n\n## Description:\n\nLatticework guides agents through multi-model decision analysis by comparing independent disciplinary lenses, mapping convergence and divergence, and naming blind spots.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[deciqai](https://clawhub.ai/user/deciqai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and employees use this skill to structure strategic, product, operational, and investment questions through 3-5 independent lenses. The skill helps identify convergence, disagreement, blind spots, and residual uncertainty before making consequential decisions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can produce persuasive strategic, financial, or operational recommendations from incomplete facts.\n\nMitigation: Users should independently verify facts and retain human judgment for material decisions.\n\nRisk: The skill is a reasoning aid and can overstate confidence if users treat convergence across lenses as proof.\n\nMitigation: Use the verification checklist to require independent lenses, falsifiable predictions, named divergence, blind spots, and residual uncertainty.\n\n## Reference(s):\n\n- [Primary Sources](references/sources.md)\n- [Method in Action: Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)\n- [Method in Action: Reasoning About the AI Boom (2024-2026)](examples/reasoning-about-the-ai-boom-2024-2026.md)\n- [ClawHub Skill Page](https://clawhub.ai/deciqai/skills/latticework)\n- [Stanford HAI AI Index](https://aiindex.stanford.edu)\n- [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown analysis with tables and concise prose]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May pause for user input in coach mode before completing the full analysis.]\n\n## Skill Version(s):\n\n1.0.5 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.4: 6 files, 12195 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), examples/reasoning-about-the-ai-boom-2024-2026.md (7710b), references/sources.md (1627b), skill-card.md (2408b), SKILL.md (6419b), _meta.json (130b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage).\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with `first-principles`, `second-order-thinking`, `probabilistic-thinking`, and `map-is-not-the-territory`.\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n- Judging an AI-boom / AI-adoption / AI-hype bet where \"is it a bubble?\" and \"is it real?\" are being argued through one lens each\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n*→ 2026 lens: [Reasoning About the AI Boom (2024–2026)](examples/reasoning-about-the-ai-boom-2024-2026.md) — economics × psychology × systems × game theory on one situation*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — 223 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/c/latticework** · ⭐ Star the repo → https://github.com/deciqAI/knowledge-skills · Contributions welcome.*\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1783679194695\n}\n\nFile v1.0.4:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644285. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n- Stanford Institute for Human-Centered AI (HAI). *AI Index Report* (2024 and 2025 editions). https://aiindex.stanford.edu — annual data on model training costs, enterprise AI adoption, and investment; the empirical backdrop for the 2024–2026 AI-boom latticework example.\n- Brown, T., et al. (2020). \"Language Models are Few-Shot Learners.\" arXiv:2005.14165. https://arxiv.org/abs/2005.14165 — foundational scaling / compute-cost paper underpinning the economics-vs-systems tension in the AI capex debate.\n\nFile v1.0.4:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.4:examples/reasoning-about-the-ai-boom-2024-2026.md\n\n# Method in Action: Reasoning About the AI Boom (2024–2026)\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\nBetween 2024 and 2026 the generative-AI build-out became the single most consequential — and most contested — allocation question in technology. Bulls saw a general-purpose technology on the scale of electricity; bears saw a capital bubble reminiscent of telecom fiber in 1999–2001. The debate stalled largely because each camp reasoned through **one lens**: an economist saw capex and margins, a psychologist saw hype and FOMO, an operator saw feedback loops, a strategist saw a game-theoretic race. Latticework's claim is that the honest answer only appears when these run *side by side* — where they converge, confidence is high; where they diverge is exactly what you don't yet know. Below the anchor case is walked through this skill's own five-step Process.\n\n# Latticework Analysis: The 2024–2026 AI capital boom\n\n## 1 — Phenomenon\n\n**Core question:** Is the 2024–2026 AI infrastructure build-out (compute capex, model labs, enterprise adoption) a durable platform shift worth its cost, a bubble, or both at once — and how should a builder or investor act under that uncertainty?\n\n**Prior single-model framing + its known blind spot:** The dominant framing was financial — \"look at the revenue vs. the capex.\" Its blind spot: a pure capex/margin model treats demand, incentives, and belief as exogenous. It cannot explain *why* rational firms keep spending faster than near-term revenue justifies, nor whether adoption compounds or plateaus. Forcing the whole phenomenon through one discipline is the failure mode latticework exists to catch.\n\n## 2 — Lenses (independent disciplines)\n\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics (capex/margins) | Frontier-model training and datacenter capex run far ahead of attributable AI revenue; depreciation on fast-obsolescing GPUs pressures returns. Capital-intensive, thin near-term margins. | − |\n| 2 | Psychology (hype/FOMO) | Narrative, availability, and social proof inflate expectations; \"can't afford to be left behind\" drives spend detached from unit economics. Overshoot likely. | − |\n| 3 | Systems (feedback loops) | Reinforcing loops (better models → more usage → more data/revenue → more compute) can compound real value; but delays between capex and payoff cause overshoot and oscillation. | + / delay |\n| 4 | Game theory (the lab race) | Multi-player race among a few well-capitalized labs and clouds: unilateral slowing risks ceding the frontier, so each rationally over-invests even knowing collective overshoot is possible. | + spend / − discipline |\n\nEach lens is genuinely independent: they make different, falsifiable predictions rather than re-labeling one story.\n\n## 3 — Convergence Map\n\n**≥2 lenses agree (higher-confidence):**\n- Economics **and** Psychology **and** Game theory all predict *spending outruns near-term justification*. Three independent disciplines converging on \"capex overshoot is likely\" makes that a high-confidence read — regardless of whether the underlying technology is real.\n- Systems **and** Game theory agree the *build-out itself is somewhat self-sustaining in the short run*: the race guarantees continued spend, and reinforcing loops mean early capacity can find demand.\n\n**Lenses disagree (live unknown — investigate):**\n- Economics says \"returns may not clear the cost of capital\"; Systems says \"reinforcing adoption loops could eventually make them clear.\" The divergence *is the question*: does enterprise adoption compound (loop dominates) or plateau (capex model dominates)? This is where investigation should concentrate — measure real retention and revenue durability, not announced capex.\n\n**Lollapalooza: multiplicatively aligned forces?** Yes, on the *upside of spend*: FOMO (psychology) × competitive race (game theory) × reinforcing usage loops (systems) push in the same direction simultaneously — which is precisely why the boom accelerated rather than self-correcting early. The same multiplicative alignment that produces genuine platform shifts also produces bubbles; a lollapalooza signals *magnitude and speed*, not *direction of truth*. It is a reason to expect a large move, not evidence the move is justified.\n\n## 4 — Blind Spots\n\nWhat no lens above covers:\n- **Regulation / geopolitics** — export controls, energy/permitting limits, and safety rules can bind harder than any market force; not captured by economics, psychology, systems, or the lab-race framing as drawn.\n- **Physical constraints** — power availability, grid interconnection, and chip supply may cap the build-out independent of demand or belief.\n- **Discontinuous capability** — the models could improve (or stall) in step-changes that none of the four lenses forecast; a genuine black-swan channel.\n\nNaming these is the point: a latticework that cannot state its own blind spots is a single lens wearing a costume.\n\n## 5 — Calibrated Conclusion\n\n**Recommendation + Confidence:** Treat the 2024–2026 AI boom as *\"real platform shift AND capital overshoot, simultaneously\"* — the two are not mutually exclusive (fiber in 1999 was overbuilt *and* underpinned the real internet). High confidence (three independent lenses converge) that near-term spend outruns near-term returns and that a repricing of over-levered players is plausible. Moderate confidence that durable value accrues to whoever controls the compounding loops (distribution, proprietary data, retained users) rather than to raw capex. For a builder: avoid competing on capex you can't sustain; build on top of the infrastructure and own a reinforcing loop. For an investor: size for overshoot and separate \"the technology is real\" from \"this specific entity's returns clear its cost of capital.\"\n\n**Key residual uncertainty:** Whether enterprise/consumer AI usage *retains and monetizes* (loop compounds) or *plateaus after novelty* (capex model wins). This single variable flips the conclusion.\n\n**Information that would most change the picture:** Hard data on cohort retention and gross-margin trajectory of AI revenue (not gross bookings), GPU depreciation schedules actually realized, and any binding regulatory/energy constraint. A durable, improving retention curve moves weight decisively toward the systems lens; a plateau moves it toward economics.\n\n---\n\nThe discipline this case illustrates: no single 2024–2026 hot take (\"it's a bubble\" / \"it changes everything\") was *wrong* so much as *partial*. Running economics, psychology, systems, and game theory in parallel converts a shouting match into a map — with a high-confidence zone (spend overshoots), a marked live unknown (does adoption compound?), and named blind spots (regulation, power, capability jumps). That map, not a verdict, is the deliverable.\n\n*Sources: Munger, C. T. (1994/2005), \"A Lesson on Elementary, Worldly Wisdom,\" in* Poor Charlie's Almanack *(Donning Company) — the latticework method. Bevelin, P. (2003),* Seeking Wisdom: From Darwin to Munger *(Post Scriptum) — cross-disciplinary application. On the AI capex-vs-revenue debate and the fiber/telecom bubble analogy widely discussed 2024–2025: reporting and commentary in the* Financial Times*,* The Economist*, and Stanford HAI's* AI Index Report *2024/2025 (documenting rising training costs and enterprise adoption); the \"GPT-3\" scaling and compute-cost literature (Brown et al., 2020, \"Language Models are Few-Shot Learners,\" arXiv:2005.14165). Specific figures are omitted here in favor of durable, widely-reported directional facts as of early 2026.*\n\nFile v1.0.4:skill-card.md\n\n## Description: <br>\nGuides agents through cross-disciplinary mental-model analysis to stress-test decisions, map convergence and divergence across lenses, and surface blind spots. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[deciqai](https://clawhub.ai/user/deciqai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nEmployees, external users, and developers use this skill when strategy, product, investment, or AI-adoption decisions need cross-domain stress testing rather than a single-framework analysis. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Users may treat advisory business, investment, or strategy analysis as automatic approval to act. <br>\nMitigation: Treat outputs as advisory analysis and require human review before acting, especially for business or investment decisions. <br>\nRisk: Weak or non-independent lenses can create false confidence in a multi-model conclusion. <br>\nMitigation: Require genuinely independent lenses, explicit predictions, named blind spots, and investigation of lens disagreements before relying on the conclusion. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/deciqai/skills/latticework) <br>\n- [Sources - latticework](artifact/references/sources.md) <br>\n- [Charlie Munger 1994 USC Business School Address example](artifact/examples/charlie-munger-1994-usc-business-school-address.md) <br>\n- [Reasoning About the AI Boom (2024-2026) example](artifact/examples/reasoning-about-the-ai-boom-2024-2026.md) <br>\n- [Stanford HAI AI Index](https://aiindex.stanford.edu) <br>\n- [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance, Analysis] <br>\n**Output Format:** [Markdown analysis with tables and short coaching questions when needed] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Advisory output; may pause for user input in coach mode.] <br>\n\n## Skill Version(s): <br>\n1.0.4 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.3: 5 files, 7794 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), references/sources.md (1115b), skill-card.md (2354b), SKILL.md (6105b), _meta.json (130b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage).\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with `first-principles`, `second-order-thinking`, `probabilistic-thinking`, and `map-is-not-the-territory`.\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — 164 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/c/latticework** · ⭐ Star the repo → https://github.com/deciqAI/knowledge-skills · Contributions welcome.*\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1783508848566\n}\n\nFile v1.0.3:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644287. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n\nFile v1.0.3:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.3:skill-card.md\n\n## Description: <br>\nLatticework helps an agent analyze complex decisions by applying independent mental models from multiple disciplines, mapping where they converge or diverge, and identifying blind spots. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[deciqai](https://clawhub.ai/user/deciqai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, analysts, and decision-support agents use this skill when a single framework is missing important cross-domain interactions. It guides the agent through a structured latticework analysis that compares 3-5 independent lenses, names convergence and disagreement, and produces a calibrated conclusion. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can influence complex decisions and may produce guidance that users over-weight in legal, financial, medical, or other high-stakes contexts. <br>\nMitigation: Treat outputs as decision-support analysis, require human review, and validate conclusions against domain expertise before acting. <br>\nRisk: A latticework analysis may still miss important blind spots if the selected lenses are too similar or poorly grounded. <br>\nMitigation: Use genuinely independent disciplinary lenses, explicitly record disagreements and residual uncertainty, and seek more evidence where lenses diverge. <br>\n\n\n## Reference(s): <br>\n- [Primary sources](references/sources.md) <br>\n- [Charlie Munger 1994 USC Business School Address example](examples/charlie-munger-1994-usc-business-school-address.md) <br>\n- [ClawHub skill page](https://clawhub.ai/deciqai/skills/latticework) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown analysis with headings, tables, and concise recommendations] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May pause for user input in coach mode before completing the analysis.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.2: 5 files, 7897 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), references/sources.md (1115b), skill-card.md (2526b), SKILL.md (6206b), _meta.json (130b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage).\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with `first-principles`, `second-order-thinking`, `probabilistic-thinking`, and `map-is-not-the-territory`.\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — 163 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/skills/latticework?utm_source=clawhub&utm_medium=marketplace&utm_campaign=knowledge-skills&utm_content=latticework** · ⭐ Star the repo → https://github.com/deciqAI/knowledge-skills · Contributions welcome.*\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1783471935508\n}\n\nFile v1.0.2:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644287. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n\nFile v1.0.2:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.2:skill-card.md\n\n## Description: <br>\nLatticework helps agents analyze complex decisions by applying independent disciplinary lenses, mapping convergence and disagreement, and surfacing blind spots and reinforcing effects. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[deciqai](https://clawhub.ai/user/deciqai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, analysts, and decision makers use this skill when a single framework is not enough to evaluate a complex strategy, product, investment, or operational decision. It guides an agent to compare 3-5 independent lenses, identify agreement and disagreement, and produce a calibrated conclusion. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can influence how an agent frames complex decisions, which may lead to over-weighting the selected lenses or presenting an incomplete analysis as decisive. <br>\nMitigation: Review the final analysis, check that at least three genuinely independent lenses were used, and treat named disagreements and residual uncertainty as decision inputs rather than conclusions. <br>\nRisk: External footer links may lead outside the skill package. <br>\nMitigation: Review external links before use and do not send private or sensitive user content to external sites unless separately authorized. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/deciqai/skills/latticework) <br>\n- [Sources - latticework](references/sources.md) <br>\n- [Method in Action: Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md) <br>\n- [deciqAI Latticework Skill](https://www.deciqai.com/skills/latticework?utm_source=clawhub&utm_medium=marketplace&utm_campaign=knowledge-skills&utm_content=latticework) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Produces a structured analysis template with lenses, convergence map, blind spots, confidence, and residual uncertainty.] <br>\n\n## Skill Version(s): <br>\n1.0.2 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.1: 5 files, 7682 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), references/sources.md (1115b), skill-card.md (2127b), SKILL.md (6103b), _meta.json (130b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage).\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with [`first-principles`](../first-principles/SKILL.md), [`second-order-thinking`](../second-order-thinking/SKILL.md), [`probabilistic-thinking`](../probabilistic-thinking/SKILL.md), and [`map-is-not-the-territory`](../map-is-not-the-territory/SKILL.md).\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — open-source thinking skills that make rigor executable for AI agents. Built by deciqAI · https://deciqai.com · Contributions welcome — see the template at the repo root.*\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1783463280331\n}\n\nFile v1.0.1:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644287. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n\nFile v1.0.1:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nLatticework guides agents through multi-model decision analysis by combining independent disciplinary lenses to identify convergence, divergence, blind spots, and lollapalooza effects. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[deciqai](https://clawhub.ai/user/deciqai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nEmployees, external users, and agents use this skill to stress-test strategy, product, operations, investment, or other cross-domain decisions when one framework is insufficient. It helps produce a calibrated analysis that names independent lenses, agreement, disagreement, blind spots, and residual uncertainty. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Decision-analysis output may be incorrect, incomplete, or overconfident for consequential business, financial, or personal decisions. <br>\nMitigation: Use the skill as analytical support and have a human reviewer validate assumptions, evidence, confidence, and residual uncertainty before acting. <br>\n\n\n## Reference(s): <br>\n- [Sources - latticework](references/sources.md) <br>\n- [Method in Action: Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md) <br>\n- [ClawHub skill page](https://clawhub.ai/deciqai/skills/latticework) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown analysis template with tables, checkpoints, and concise recommendations] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Coach mode may pause at explicit WAIT prompts; the skill does not request tool, system, or network access.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: ClawHub release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 5 files, 7730 bytes\n\nFiles: examples/charlie-munger-1994-usc-business-school-address.md (4269b), references/sources.md (1115b), skill-card.md (2337b), SKILL.md (6103b), _meta.json (130b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage).\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with [`first-principles`](../first-principles/SKILL.md), [`second-order-thinking`](../second-order-thinking/SKILL.md), [`probabilistic-thinking`](../probabilistic-thinking/SKILL.md), and [`map-is-not-the-territory`](../map-is-not-the-territory/SKILL.md).\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:\n```\n\n*→ Method in Action: [Charlie Munger 1994 USC Business School Address](examples/charlie-munger-1994-usc-business-school-address.md)*\n\n## Pack: Latticework Across Domains\n| Domain | Typical single lens | Key missing lens |\n|---|---|---|\n| Startup PMF | Customer interviews | Systems (adoption loops) + History |\n| Pricing | Demand curve | Game theory (competitive response) |\n| M&A | Financial synergies | Psychology (culture) + History (base rates) |\n\n## Applying It Well\n\n- Independence matters: 3 re-labeled versions of the same model is not a latticework\n- Divergence = information; stop adding lenses when marginal new predictions cease (3–5)\n\n*→ Primary sources: [references/sources.md](references/sources.md)*\n\n## Common Rationalizations\n\n**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**\n\n| Fake move | Reality |\n|---|---|\n| [D] \"We already did a full analysis\" | One framework applied thoroughly is a single-lens deep dive — not a latticework. |\n| [D] \"Adding more models adds confusion\" | Confusion from diverging models is *information* — it shows where understanding is incomplete. |\n| [D] \"We consulted multiple advisors\" | If all advisors share the same disciplinary lens, that is triangulation within one model. |\n| [D] \"The model has worked before\" | A model that predicted correctly in past contexts may be in a regime where its assumptions no longer hold. |\n| [D] \"Convergence is confirmation bias with extra steps\" | Confirmation bias seeks evidence for a pre-held view. Latticework compares independent predictions — divergence check is the anti-bias mechanism. |\n| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |\n\n## Red Flags\n\n- Only one discipline's vocabulary used throughout\n- Stakeholder objections dismissed without checking if they represent another model's prediction\n- Decision called \"rigorous\" because the single model was applied thoroughly\n- Diverging data forced into the primary model instead of triggering a model-check\n- The analysis cannot name its own blind spots\n\n## Verification\n\n- [ ] ≥3 genuinely independent disciplinary lenses applied\n- [ ] Each lens produced an explicit, falsifiable prediction (not just \"we considered X\")\n- [ ] Convergence zones marked higher-confidence; divergence zones named as live unknowns\n- [ ] At least one blind spot named (phenomenon no lens covers)\n- [ ] Lollapalooza check: any convergent forces multiplicatively aligned?\n\n---\n*Part of **deciqAI Knowledge Skills** — open-source thinking skills that make rigor executable for AI agents. Built by deciqAI · https://deciqai.com · Contributions welcome — see the template at the repo root.*\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1782724682398\n}\n\nFile v1.0.0:references/sources.md\n\n# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644287. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n\nFile v1.0.0:examples/charlie-munger-1994-usc-business-school-address.md\n\n# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psychology of the customer relationship is fragile — that is the investigation priority.\n\nThe same methodology applies to diagnoses in operations and strategy. A company losing market share might be analyzed through:\n- **Porter's Five Forces** (competitive structure)\n- **Psychology** (customer switching behavior, loss aversion, brand association)\n- **Systems** (feedback loops in pricing and quality)\n- **Second-order effects** (what does each competitor's response to your response look like?)\n\nWhere three of the four lenses say \"this is a structurally losing position,\" confidence in that diagnosis is high. Where they disagree, you have found the strategic opening — the anomaly in the model that might be the lever.\n\n**The deciqAI Knowledge Skills collection itself** is the operational implementation of Munger's program. The 90–100 skills across this collection represent models drawn from multiple disciplines: cognitive science, economics, evolutionary biology, game theory, systems dynamics, statistics, narrative theory, and more. This skill — #93, latticework — is the meta-layer: the instruction for how to operate the collection as an integrated system, not a reference menu. You are, as you read this, using a latticework.\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nLatticework helps agents apply independent mental models from multiple disciplines to stress-test decisions, map convergence and divergence, and identify blind spots. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[deciqai](https://clawhub.ai/user/deciqai) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nEmployees, external users, developers, and analysts use this skill when a decision or strategy needs multiple independent disciplinary lenses instead of a single-framework analysis. It guides the agent to compare predictions, surface live unknowns, and produce a calibrated conclusion. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill supports decision analysis and could produce incomplete or overconfident recommendations for high-impact business, financial, legal, or operational decisions. <br>\nMitigation: Use the output as structured decision support, require human review for consequential decisions, and verify assumptions, blind spots, and residual uncertainty before acting. <br>\nRisk: The skill can pause for user input in coach mode, so incomplete interaction may leave the analysis unfinished. <br>\nMitigation: Continue through the prompted steps until the convergence map, blind spots, lollapalooza effects, and calibrated conclusion are all produced. <br>\n\n\n## Reference(s): <br>\n- [Sources - latticework](references/sources.md) <br>\n- [Charlie Munger 1994 USC Business School Address example](examples/charlie-munger-1994-usc-business-school-address.md) <br>\n- [deciqAI](https://deciqai.com) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown analysis with tables, checklists, and concise recommendations] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May pause for user input in coach mode before completing the full analysis.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: Latticework Owner: deciqai Summary: Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s... Tags: latest:1.0.5 Version history: v1.0.5 | 2026-07-16T18:04:38.150Z | user Description tail link + agents machine-readable metadata line (deciqai.com/s/latticework.json) v1.0.4 | 2026-07-10T10:26:34.695Z | user Add","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"},{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"},{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"},{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"},{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"},{"language":"text","snippet":"# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n## 3 — Convergence Map\n  ≥2 lenses agree (higher-confidence):\n  Lenses disagree (live unknown — investigate):\n  Lollapalooza: multiplicatively aligned forces?\n\n## 4 — Blind Spots\n  What no lens covers:\n\n## 5 — Calibrated Conclusion\n  Recommendation + Confidence:\n  Key residual uncertainty:\n  Information that would most change the picture:"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: latticework\ndescription: \"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', or a decision keeps surfacing objections from different stakeholders that don't overlap.\n  Do NOT activate when: the problem is fully contained in one discipline with no cross-domain interactions (pure legal text, pure engineering spec); time is too short for multi-model deliberation (crisis triage). More: deciqai.com/c/latticework\"\n---\n\n# Latticework\n\n## Overview\n\n**Latticework** is the practice of cross-wiring mental models from multiple disciplines on the same situation. Power comes from *inter-connection*: independent lenses converging = high-confidence signal; lenses diverging = unknown to investigate. When multiple forces align simultaneously they amplify — the **lollapalooza effect** (Munger, 1994). Composes with `first-principles`, `second-order-thinking`, `probabilistic-thinking`, and `map-is-not-the-territory`.\n\n## When to Use\n\n- Stakeholders keep raising non-overlapping objections — each is right from their model\n- Post-mortem shows failure was \"outside the model we used\"\n- \"Our analysis is solid\" — but only one framework was applied\n- Situation looks like a classic X but has anomalous features X cannot explain\n- Designing a strategy/product where market, psychology, operations, and incentives all interact\n- Judging an AI-boom / AI-adoption / AI-hype bet where \"is it a bubble?\" and \"is it real?\" are being argued through one lens each\n\n**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.\n\n## Coaching Novices (Adaptive Front Door)\n\n- **Engine mode:** user has a concrete case → run The Process directly.\n- **Coach mode:** user is unfamiliar → guide step by step.\n\nIn Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.\n\n1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).\n2. Check fit: has one model already failed or felt incomplete? If yes, proceed.\n3. Elicit: what models applied so far? What disciplines are missing?\n\n> **[WAIT — do not advance until user responds]**\n\n4. Run The Process one step at a time with their input.\n\n> **[WAIT — do not advance until user responds]**\n\n5. Close: name the convergence map, blind spots, and any lollapalooza effects found.\n\n> **[WAIT — do not advance until user responds]**\n\n## The Process + Output Template\n\n```\n# Latticework Analysis: <situation>\n\n## 1 — Phenomenon\n  Core question:\n  Prior single-model framing + its known blind spot:\n\n## 2 — Lenses (3–5, genuinely independent disciplines)\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics | | |\n| 2 | Psychology | | |\n| 3 | Systems | | |\n\n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn754b8sk22s8c6gjxt02bftbn88q7ye\",\n  \"slug\": \"latticework\",\n  \"version\": \"1.0.5\",\n  \"publishedAt\": 1784225078150\n}"},{"path":"references/sources.md","content":"# Sources — latticework\n\n> *Primary sources for the [latticework](../SKILL.md) skill.*\n\n- Munger, C. T. (1994/2005). \"A Lesson on Elementary, Worldly Wisdom.\" USC Business School. In *Poor Charlie's Almanack*, Donning Company. ISBN 978-1578645015. The primary text.\n- Munger, C. T. (1995). \"The Psychology of Human Misjudgment.\" Harvard Law School address. Repr. in *Poor Charlie's Almanack*, 2005. Twenty-five psychological tendencies as lattice nodes.\n- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644285. Systematic exposition of the latticework program across disciplines.\n- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.\n- Epstein, D. (2019). *Range: Why Generalists Triumph in a Specialized World.* Riverhead. ISBN 978-0735214484. Empirical case for cross-domain model transfer as competitive advantage.\n- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.\n- Stanford Institute for Human-Centered AI (HAI). *AI Index Report* (2024 and 2025 editions). https://aiindex.stanford.edu — annual data on model training costs, enterprise AI adoption, and investment; the empirical backdrop for the 2024–2026 AI-boom latticework example.\n- Brown, T., et al. (2020). \"Language Models are Few-Shot Learners.\" arXiv:2005.14165. https://arxiv.org/abs/2005.14165 — foundational scaling / compute-cost paper underpinning the economics-vs-systems tension in the AI capex debate."},{"path":"examples/charlie-munger-1994-usc-business-school-address.md","content":"# Method in Action: Charlie Munger 1994 USC Business School Address\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\n**Charlie Munger** (1924–2023), vice-chairman of Berkshire Hathaway, delivered the 1994 USC Business School commencement address titled \"A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business.\" The address was transcribed, circulated, and later published in *Poor Charlie's Almanack* (2005, Donning Company) — one of the most reproduced investor education texts of the late 20th century.\n\nThe address opens with the key proposition:\n\n> \"What is elementary, worldly wisdom? Well, the first rule is that you can't really know anything if you just remember isolated facts and try and bang 'em back. **If the facts don't hang together on a latticework of theory, you don't have them in a usable form.** You've got to have models in your head. And you've got to array your experience — both vicarious and direct — on this latticework of models.\"\n>\n> — Munger (1994/2005), *Poor Charlie's Almanack.*\n\nMunger then walked through the disciplines he drew from: mathematics (compound interest, permutations, the normal distribution, regression to the mean), physics (critical mass, tipping points), chemistry (autocatalysis), biology (Darwin's natural selection and the survival of variants), psychology (a list of 25 psychological tendencies, later expanded in the 1995 Harvard Law School address), and economics (comparative advantage, supply and demand, opportunity cost, the agency problem).\n\nHis applied example was **Coca-Cola**: why does a single beverage product dominate for 130+ years? Single-model answers (brand, distribution, taste) are each partially right and jointly incomplete. Munger's lattice:\n\n- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)\n- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)\n- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment\n- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally\n\nNo single lens predicts the durability. All four together produce a lollapalooza: multiple forces reinforcing the same outcome (dominance) simultaneously. That explains not just *that* Coca-Cola is dominant but *why the dominance has been so persistent across fundamentally different market eras*.\n\nMunger's investment methodology followed from this: before making a major investment, systematically ask what each of 4–6 disciplines would say about this business. If 4 disciplines agree it is an exceptional business, confidence is much higher than if 1 discipline says so. If the disciplines disagree — e.g., the economics are excellent but the psych"},{"path":"examples/reasoning-about-the-ai-boom-2024-2026.md","content":"# Method in Action: Reasoning About the AI Boom (2024–2026)\n\n> *Example for the [latticework](../SKILL.md) skill.*\n\nBetween 2024 and 2026 the generative-AI build-out became the single most consequential — and most contested — allocation question in technology. Bulls saw a general-purpose technology on the scale of electricity; bears saw a capital bubble reminiscent of telecom fiber in 1999–2001. The debate stalled largely because each camp reasoned through **one lens**: an economist saw capex and margins, a psychologist saw hype and FOMO, an operator saw feedback loops, a strategist saw a game-theoretic race. Latticework's claim is that the honest answer only appears when these run *side by side* — where they converge, confidence is high; where they diverge is exactly what you don't yet know. Below the anchor case is walked through this skill's own five-step Process.\n\n# Latticework Analysis: The 2024–2026 AI capital boom\n\n## 1 — Phenomenon\n\n**Core question:** Is the 2024–2026 AI infrastructure build-out (compute capex, model labs, enterprise adoption) a durable platform shift worth its cost, a bubble, or both at once — and how should a builder or investor act under that uncertainty?\n\n**Prior single-model framing + its known blind spot:** The dominant framing was financial — \"look at the revenue vs. the capex.\" Its blind spot: a pure capex/margin model treats demand, incentives, and belief as exogenous. It cannot explain *why* rational firms keep spending faster than near-term revenue justifies, nor whether adoption compounds or plateaus. Forcing the whole phenomenon through one discipline is the failure mode latticework exists to catch.\n\n## 2 — Lenses (independent disciplines)\n\n| # | Discipline | Key Prediction | Force (+/-/0) |\n|---|-----------|---------------|--------------|\n| 1 | Economics (capex/margins) | Frontier-model training and datacenter capex run far ahead of attributable AI revenue; depreciation on fast-obsolescing GPUs pressures returns. Capital-intensive, thin near-term margins. | − |\n| 2 | Psychology (hype/FOMO) | Narrative, availability, and social proof inflate expectations; \"can't afford to be left behind\" drives spend detached from unit economics. Overshoot likely. | − |\n| 3 | Systems (feedback loops) | Reinforcing loops (better models → more usage → more data/revenue → more compute) can compound real value; but delays between capex and payoff cause overshoot and oscillation. | + / delay |\n| 4 | Game theory (the lab race) | Multi-player race among a few well-capitalized labs and clouds: unilateral slowing risks ceding the frontier, so each rationally over-invests even knowing collective overshoot is possible. | + spend / − discipline |\n\nEach lens is genuinely independent: they make different, falsifiable predictions rather than re-labeling one story.\n\n## 3 — Convergence Map\n\n**≥2 lenses agree (higher-confidence):**\n- Economics **and** Psychology **and** Game theory all predict *spending outruns near-term justification*. Three "}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s... Skill: Latticework Owner: deciqai Summary: Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we s... Tags: latest:1.0.5 Version history: v1.0.5 | 2026-07-16T18:04:38.150Z | user Description tail link + agents machine-readable metadata line (deciqai.com/s/latticework.json) v1.0.4 | 2026-07-10T10:26:34.695Z | user Add","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1871,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:57:58.410Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T20:57:33.597Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}