What makes Compound Interest notable?

1.2K downloads. Trust evidence available

How should Compound Interest 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

Compound Interest

Activate when: user asks about starting early vs. later for savings/investing, wonders if small consistent gains add up, wants to know how long to double mon... Skill: Compound Interest Owner: deciqai Summary: Activate when: user asks about starting early vs. later for savings/investing, wonders if small consistent gains add up, wants to know how long to double mon... Tags: latest:1.0.5 Version history: v1.0.5 | 2026-07-16T17:54:59.743Z | user Description tail link + agents machine-readable metadata line (deciqai.com/s/compound-interest.json) v1.0.4 | 2026-07-09T11:16:31.916

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

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. 1.2K 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: 1.2K 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:compound-interest

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-compound-interest/snapshot"

Documentation

CLAWHUB

143,771 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: compound-interest
description: "Activate when: user asks about starting early vs. later for savings/investing, wonders if small consistent gains add up, wants to know how long to double money, is evaluating long-term wealth or skill-building decisions, mentions 'Rule of 72' or 'exponential growth.' Do NOT activate when: the time horizon is short (under 3 years) and compounding is negligible; the underlying process is genuinely linear with no reinvestment or accumulation. More: deciqai.com/c/compound-interest"
---

# Compound Interest

## Overview

Compound interest: a quantity grows at a rate proportional to its current size — growth itself grows — producing exponential accumulation. Formula: A = P × (1 + r)^t. Humans underestimate long-horizon outcomes because cognition extrapolates linearly. Two consequences: **Rule of 72** (doubles in ≈ 72/r periods); **late-period dominance** (most final value comes from the last few periods).

Composes with `lindy-effect`, `hyperbolic-discounting`, `expected-value-and-kelly`, `network-effects`, `deep-work`.

## When to Use

- Evaluating any long-horizon investment, savings, or wealth decision
- Deciding between starting earlier vs. starting later; intensity vs. duration paths
- Evaluating compound advantages in business (data, brand, switching cost)
- Weighing AI capex, AI adoption timing, or defending against AI-native competition — where data flywheels, ecosystem lock-in, and eval/technical debt compound over years
- Skill-development planning; recognizing compound decay (fees, atrophy, trust erosion)

**Not when:** horizon is short; rate is so low linear approximation is fine; process is genuinely linear; situation requires immediate one-shot intensity.

## Coaching Novices (Adaptive Front Door)

- **Engine mode:** user has a concrete long-horizon 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-line: duration of compounding dominates rate — starting earlier with small consistency beats starting later with large intensity.
2. Check fit. Short horizon or very low rate? Compound effects are small — save it for genuinely long horizons.
3. Elicit the specific decision, time horizon, and rate.
> **[WAIT — do not advance until user responds]**
4. Walk through Rule of 72, precise compound outcome, late-period dominance, and other life domains one question at a time.
> **[WAIT — do not advance until user responds]**
5. Close: decision informed by compound math + compound dynamics identified + commitment to early consistent action.
> **[WAIT — do not advance until user responds]**

## The Process

**Step 1 — Specify the situation**
`Starting value / Rate (per period) / Time horizon / Decision / Alternative options`

**Step 2 — Rule of 72 intuition**
`Doubling time = 72/r | Doublings in horizon | Approximate multiplier = 2^doublings`

**St

_meta.json

{
  "ownerId": "kn754b8sk22s8c6gjxt02bftbn88q7ye",
  "slug": "compound-interest",
  "version": "1.0.5",
  "publishedAt": 1784224499743
}

references/sources.md

# Sources — compound-interest

> *Primary sources for the [compound-interest](../SKILL.md) skill.*

- Bernoulli, J. (1683). "Quaestiones nonnullae de usuris, cum solutione problematis de sorte alearum." *Acta Eruditorum*. The original discovery of e via compound interest.
- Franklin, B. (1789). Codicil to the Last Will and Testament of Benjamin Franklin. Reprinted in Smyth, A. H. (Ed.) (1907). *The Writings of Benjamin Franklin*, Vol. 10. Macmillan. The 200-year compounding trusts for Boston and Philadelphia.
- Graham, B., & Dodd, D. L. (1934). *Security Analysis.* Whittlesey House. ISBN 978-0071592536 (2008 reprint). The investment-philosophy foundation.
- Graham, B. (1949). *The Intelligent Investor.* Harper. ISBN 978-0060555665. The popular companion volume.
- Buffett, W. E. (1956-present). Berkshire Hathaway Chairman's Letters. Available at berkshirehathaway.com. The longest-running practical demonstration.
- Bogle, J. C. (2007). *The Little Book of Common Sense Investing.* Wiley. ISBN 978-1118521205. The index-investing operationalization.
- Munger, C. T. (2005). *Poor Charlie's Almanack.* Donning Company. ISBN 978-1578645015. Compound advantage in mental models and business.
- Clear, J. (2018). *Atomic Habits.* Avery. ISBN 978-0735211292. Compound interest applied to habits and skill.
- Ericsson, K. A., Krampe, R. T., & Tesch-Römer, C. (1993). "The role of deliberate practice in the acquisition of expert performance." *Psychological Review*, 100(3), 363-406.
- Dweck, C. S. (2006). *Mindset: The New Psychology of Success.* Random House. ISBN 978-0345472328.
- Thaler, R. H., & Benartzi, S. (2004). "Save More Tomorrow: Using behavioral economics to increase employee saving." *Journal of Political Economy*, 112(S1), S164-S187.
- Sculley, D., et al. (2015). "Hidden Technical Debt in Machine Learning Systems." *Advances in Neural Information Processing Systems (NeurIPS) 28.* The compounding cost of neglected ML/eval debt — the 2023–2026 AI-era decay case.
- Hoffman, R., & Yeh, C. (2018). *Blitzscaling: The Lightning-Fast Path to Building Massively Valuable Companies.* Currency. ISBN 978-1524761417. Data flywheels, network effects, and ecosystem lock-in as compounding business moats — the framing behind AI-era data-advantage strategy.

examples/ai-era-data-and-eval-debt-compounding-2023-2026.md

# Method in Action: Compounding in the AI Era — Data Flywheels, Ecosystem Lock-In, and Eval Debt (2023–2026)

> *Example for the [compound-interest](../SKILL.md) skill.*

The 2023–2026 generative-AI boom is a live demonstration that compounding is not only a financial phenomenon. The durable advantages accruing to leading AI companies — proprietary usage data, developer-ecosystem lock-in, and model-improvement loops — are compound assets. So is the liability side: neglected technical and evaluation ("eval") debt compounds against you at the same relentless rate. This example runs one AI-native product decision through the skill's process, then generalizes to the wider landscape.

**Step 1 — Specify the situation.** A founding team is choosing between two paths for an AI product. Path A: ship a thin wrapper on a third-party model, optimize for a fast launch, and defer investment in proprietary data capture and evaluation harnesses. Path B: ship a narrower first version but instrument every interaction to build a proprietary usage-data flywheel, invest early in an eval suite, and cultivate a developer ecosystem around an API. Starting value: a small early user base and one deployed model. Rate: the per-period rate at which retained data and ecosystem depth improve the product. Time horizon: 5–10 years. Decision: optimize for near-term launch speed, or for compounding assets that widen a moat over time. Alternative options: buy data later; switch models later; add evals later.

**Step 2 — Rule of 72 intuition.** Suppose the compounding assets (data quality, eval coverage, ecosystem integrations) improve the product's effective value by roughly 15% per year — a plausible figure when a data flywheel is genuinely turning. At 15%, the doubling time is 72/15 ≈ 4.8 years. Over a 10-year horizon that is roughly two doublings, an advantage multiplier on the order of 4×. The point of the Rule-of-72 pass is not the exact number; it is to convert "we'll add data and evals eventually" into a visible exponent. A competitor who starts the flywheel two doublings earlier is not a little ahead — they are multiples ahead on the compounding dimension.

**Step 3 — Precise compound result.** Using A = P × (1+r)^t with r = 0.15 and t = 10: the compound multiplier is 1.15^10 ≈ 4.05×. Linear extrapolation — "we improve by 15% of the original value each year" — would predict 1 + 0.15 × 10 = 2.5×. The gap between the compound path (≈4.05×) and the linear intuition (2.5×) is the advantage that linear-thinking competitors systematically fail to price in. The mechanism is well documented in the practitioner literature as the "data flywheel": more usage produces more data, more data improves the model, a better model attracts more usage. Each turn of the loop reinvests the prior turn's output — the defining structure of compounding.

**Step 4 — Late-period dominance.** As with any compound curve, most of the gap opens late. At the half-time mark (year 5), 1.15^5 ≈ 2.01× — only a

examples/bernoulli-1683-graham-buffett.md

# Method in Action: Bernoulli 1683, Graham/Buffett, and the Compound-Advantage Tradition

> *Example for the [compound-interest](../SKILL.md) skill.*

The mathematical foundation is **Jacob Bernoulli's 1683 paper** in *Acta Eruditorum*. Bernoulli was studying the limit of (1 + 1/n)^n as n → infinity — the question of what happens when compound interest is computed with ever-more-frequent compounding intervals. The limit, he discovered, is the constant we now call *e* ≈ 2.71828:

> "If a sum is compounded n times per year at rate r/n per period, the year-end value is P(1 + r/n)^n. As n increases, this value increases but is bounded above. The bound, as n → ∞, exists and equals P × e^r where e is a transcendental constant approximately equal to 2.71828."
>
> — Bernoulli (1683), as later formalized by Euler (1737).

Bernoulli's discovery of *e* is one of the foundational results in mathematics, with applications far beyond finance — it appears throughout differential equations, probability theory, and physics. But its first context was compound interest, and the connection has remained central.

The principle's operationalization in **investment** is most associated with **Benjamin Graham** (1894-1976) and his student **Warren Buffett** (1930-).

**Graham's *Security Analysis* (1934)** established the value-investing framework, which is essentially the discipline of finding compounding opportunities at favorable prices. Graham's central claim:

> "The market quotation for a security on any given day reflects emotion as much as analysis. Over the long term, however, the compound growth in earnings of well-selected businesses dominates the noise. A patient investor who buys good businesses at reasonable prices and holds them through market cycles can expect, over a 20- to 30-year horizon, returns approximating the underlying business growth — typically 6-10% annually. Compounded over those decades, these returns produce wealth that exceeds intuition."
>
> — Graham, B., & Dodd, D. L. (1934). *Security Analysis.* Whittlesey House, p. 19.

**Buffett's annual letters to Berkshire Hathaway shareholders (1956-present)** are perhaps the longest-running practical demonstration of compound interest in business and investment. Buffett's writing repeatedly returns to compound math:

> "Time is the friend of the wonderful business and the enemy of the mediocre. ... Our long-term advantage comes from not paying ourselves through high turnover, transaction costs, or short-term thinking. Compound interest, like a savings account at 8% over 40 years, is dramatic. Compound interest in a business with intrinsic returns of 15% over 50 years is wealth-creating on a scale that only the very patient ever realize."
>
> — Buffett, W. E. (1989). Berkshire Hathaway Chairman's Letter, p. 14.

Buffett's career-long results are the empirical case. Berkshire Hathaway's compound book-value growth from 1965-2024 has been approximately 19.8% annually — a number that, sustained over 6

Github ReposUpdated 1d 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.