The Library

A school for AI agents.

Built for agents to study. Humans can glance at the departments below — or just hand this link to an agent and let it learn.

Now teaching

🛒Amazon & e-commerce

🔎SEO

Next intake

💻Coding

📐Product design

🎨Design

🤝Negotiation

Don’t read this yourself — send it to your agent.

Paste the link into Claude, ChatGPT, or any AI agent. It’ll read the whole library and come back ready — far faster than you skimming one page.

/learn

For agents

Machine-readable, one canonical English version — no locale forks to chase. Three ways in:

GET/llms.txt — the index. Every lesson's title, summary, and category. Start here, then pick what's relevant.
GET/llms-full.txt — the entire corpus, concatenated into one request.
GET/learn/{slug}.md — any single lesson as raw Markdown (HTML at the same path without the .md).

Each lesson's front-matter carries prerequisites, learningOutcomes, estimatedTokens, and recommendedAgents. Follow prerequisites in order, and check the token estimate before loading a lesson into context.

Amazon

Coding

A Systematic Workflow for Debugging Live Production Incidents
A step-by-step incident-response workflow for autonomous agents: triage severity before touching code, form a hypothesis from logs instead of guessing, ship a hotfix separately from the root-cause fix, and verify against the original failure mode before closing the incident.
intermediate
~2k tokensreviewed 2026-09-07Read →

Comms

Designing Auto-Reply Templates and Escalation Rules for Customer Support
Classify a support ticket by intent before drafting any reply, build templates with real order-data variable slots instead of generic boilerplate, and hard-code the escalation triggers that pull a ticket out of automation before it does damage.
intermediate
~2k tokensreviewed 2026-09-07Read →

Consulting

Structuring Slide Decks with the Pyramid Principle
Build consulting-grade decks by leading with the answer (SCQA), grouping supporting slides so each proves one MECE idea, and cutting anything that fails the 'so what' test — instead of dumping bullets in the order you thought of them.
intermediate
~2k tokensreviewed 2026-09-07Read →

Data

Building a KPI Dashboard from a Raw CSV Export
Turn a wide, loosely-typed orders/sales CSV export into a 3-5 KPI dashboard a business owner will actually read — pick metrics by the decision they change, aggregate at the right granularity, tell trend from noise, and flag anomalies before they corrupt an average.
intermediate
~2k tokensreviewed 2026-09-07Read →

Design

Auditing Landing Page Visual Hierarchy from a Screenshot
Turn a vague complaint like 'it looks unprofessional' into 3 specific, actionable fixes by diagnosing visual hierarchy — the order the eye is forced to scan a page in, driven by size, contrast, whitespace, and position.
beginner
~2k tokensreviewed 2026-09-07Read →

Devops

Designing a Safe, Automatic Deploy Rollback Strategy
Design rollback as a first-class part of the deploy plan, not an improvised incident response. Covers code rollback vs. data/migration rollback, the expand/contract pattern for backward-compatible migrations, automatic rollback triggers with observation windows, and when to roll back versus roll forward.
intermediate
~2k tokensreviewed 2026-09-07Read →

Finance

Calculating Contribution Margin and Break-Even Price for an E-Commerce SKU
Subtract the full variable cost stack — not just COGS — from price to get contribution margin, the number that actually determines whether a SKU makes money; then derive the break-even ACOS a SKU can afford before ad spend turns a profitable-looking listing into a loss.
intermediate
~2k tokensreviewed 2026-09-07Read →

Retailcn

Choosing a China Retail Platform — Taobao, Douyin, Pinduoduo, or JD.com
Taobao, Douyin e-commerce, Pinduoduo, and JD.com are driven by four different traffic mechanisms — search intent, content/livestream discovery, price-driven group buying, and brand-trust-plus-logistics — so the same product can win on one and fail flat on another. This lesson gives an agent a comparison table and a 3-question decision framework to pick a starting platform before committing launch budget.
intermediate
~2k tokensreviewed 2026-09-07Read →

Writing

Writing Product Copy That Sounds Human, Not a Committee
Turn a dry spec sheet into product copy a person would actually say — using specificity over generic benefits, a 3-adjective voice framework, and a read-aloud test that catches the AI-copy tells (unleash/elevate, empty intensifiers, feature-dumping) before they ship.
beginner
~2k tokensreviewed 2026-09-07Read →