What makes Latticework notable?

1K downloads. Trust evidence available

How should Latticework be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Latticework

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

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.5release · observed Jul 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17a4mqcnk515kvaca5ze55d0x88pfpx:latticework

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: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-deciqai-latticework/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

103,782 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: latticework
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 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.
  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"
---

# Latticework

## Overview

**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`.

## When to Use

- Stakeholders keep raising non-overlapping objections — each is right from their model
- Post-mortem shows failure was "outside the model we used"
- "Our analysis is solid" — but only one framework was applied
- Situation looks like a classic X but has anomalous features X cannot explain
- Designing a strategy/product where market, psychology, operations, and incentives all interact
- 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

**Not when:** problem is contained in one discipline; crisis triage (no time); decision too small for multi-model overhead.

## Coaching Novices (Adaptive Front Door)

- **Engine mode:** user has a concrete case → run The Process directly.
- **Coach mode:** user is unfamiliar → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

1. One-liner: facts don't become knowledge until they hang on a latticework of theory (Munger's rule #1).
2. Check fit: has one model already failed or felt incomplete? If yes, proceed.
3. Elicit: what models applied so far? What disciplines are missing?

> **[WAIT — do not advance until user responds]**

4. Run The Process one step at a time with their input.

> **[WAIT — do not advance until user responds]**

5. Close: name the convergence map, blind spots, and any lollapalooza effects found.

> **[WAIT — do not advance until user responds]**

## The Process + Output Template

```
# Latticework Analysis: <situation>

## 1 — Phenomenon
  Core question:
  Prior single-model framing + its known blind spot:

## 2 — Lenses (3–5, genuinely independent disciplines)
| # | Discipline | Key Prediction | Force (+/-/0) |
|---|-----------|---------------|--------------|
| 1 | Economics | | |
| 2 | Psychology | | |
| 3 | Systems | | |

_meta.json

{
  "ownerId": "kn754b8sk22s8c6gjxt02bftbn88q7ye",
  "slug": "latticework",
  "version": "1.0.5",
  "publishedAt": 1784225078150
}

references/sources.md

# Sources — latticework

> *Primary sources for the [latticework](../SKILL.md) skill.*

- 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.
- 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.
- Bevelin, P. (2003). *Seeking Wisdom: From Darwin to Munger.* Post Scriptum. ISBN 978-1578644285. Systematic exposition of the latticework program across disciplines.
- Griffin, T. (2015). *Charlie Munger: The Complete Investor.* Columbia University Press. ISBN 978-0231170277. Applied latticework in investment analysis.
- 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.
- Parrish, S., & Berryman, R. (2019). *The Great Mental Models, Volume 1.* Latticework Publishing. Operational framework derived from Munger's program.
- 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.
- 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.

examples/charlie-munger-1994-usc-business-school-address.md

# Method in Action: Charlie Munger 1994 USC Business School Address

> *Example for the [latticework](../SKILL.md) skill.*

**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.

The address opens with the key proposition:

> "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."
>
> — Munger (1994/2005), *Poor Charlie's Almanack.*

Munger 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).

His 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:

- **Economics:** scale economies in distribution, advertising leverage, franchise economics with bottlers (capital-light for Coca-Cola)
- **Psychology:** availability heuristic (ubiquitous → preferred), association bias (happiness imagery), social proof (everyone drinks it)
- **Systems:** distribution network as a self-reinforcing feedback loop — more distribution → more sales → more revenue → more distribution investment
- **History:** first-mover advantage locked in cultural association across two world wars; the military supply contracts institutionalized the product globally

No 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*.

Munger'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

examples/reasoning-about-the-ai-boom-2024-2026.md

# Method in Action: Reasoning About the AI Boom (2024–2026)

> *Example for the [latticework](../SKILL.md) skill.*

Between 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.

# Latticework Analysis: The 2024–2026 AI capital boom

## 1 — Phenomenon

**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?

**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.

## 2 — Lenses (independent disciplines)

| # | Discipline | Key Prediction | Force (+/-/0) |
|---|-----------|---------------|--------------|
| 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. | − |
| 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. | − |
| 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 |
| 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 |

Each lens is genuinely independent: they make different, falsifiable predictions rather than re-labeling one story.

## 3 — Convergence Map

**≥2 lenses agree (higher-confidence):**
- Economics **and** Psychology **and** Game theory all predict *spending outruns near-term justification*. Three

Github ReposUpdated 2d agoRank 70

AionUi

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.