Cite as: Real Problem AI problem “Why are library docs still written for humans when the first reader is now an agent?”. Opportunity score 8.3 out of 10 (severity 8, AI feasibility 9, market signal 8, competition gap 8). Category Others. Trend LLM. Source signal: Andrej Karpathy, Sequoia Ascent 2026 summary. Canonical URL: https://www.realproblem.ai/idea/why-are-library-docs-still-written-for-humans-when-the-first-reader-is-now-an-agent.
Why are library docs still written for humans when the first reader is now an agent?
Cursor / Claude Code / Devin are now the primary reader of any new SDK; doc sites front-load tutorials, marketing, navigation chrome and screenshots that waste agent context window and degrade tool-call accuracy.
Who has it: AI-native developers using agentic coding (Cursor, Claude Code, Devin, Copilot) on libraries and APIs that haven't shipped agent-grade docs.
Evidence
“Why are people still telling me what to do? I don't want to do anything. What is the thing I should copy-paste to my agent?”
Quoted word for word from the public post linked below. Nobody submitted it to Real Problem AI.
Andrej Karpathy, Sequoia Ascent 2026 summaryScoring breakdown
Existing players
- Mintlify / ReadMe / GitBook · Beautiful human docs; AI-ready is a chatbot bolt-on, not structured agent contract.
- Context7 · Aggregates llms.txt at consumer side; doesn't fix source library docs.
- llms.txt standard · Convention with no opinionated tooling, validation, or coverage SLA.
- Anthropic docs MCP / OpenAI cookbook · First-party only.
What they are missing
Stripe Atlas for agent-grade docs: ingest a repo + OpenAPI spec, output a versioned, tested, agent-shaped doc bundle the maintainer can host. Per-library SaaS to maintainers ($99-499/mo).
Founders working in this area (not affiliated with Real Problem AI)
- Han Wang, Co-founder, Mintlify
Stack hint
#T14 · Canonical URL: https://www.realproblem.ai/idea/why-are-library-docs-still-written-for-humans-when-the-first-reader-is-now-an-agent