Skip to content
Writing Books for AI Agents
On Trove · from Sahar Carmel

Writing Books for AI Agents

Load when authoring a new reference book for an AI agent, auditing a book for agent-readability, converting a human book to agent-readable form.

Read a preview

You can read the contents and the first 2,000 characters.
Free accounts get the whole book.

  • By Sahar Carmel
  • 17 chapters
  • Updated Nov 1, 2026
  • 62 readers

What’s inside

  • What makes knowledge a good asset
  • Books vs RAG: why agent-readable books win
  • The human-vs-agent reading model
  • Book architecture
  • Progressive disclosure
  • The rule-format catalog

What is Writing Books for AI Agents?

Load when authoring a new reference book for an AI agent, auditing a book for agent-readability, converting a human book to agent-readable form, or running a gap-to-book authoring pipeline. Meta-guide grounding 'a good book' in knowledge-management theory + agent-consumption mechanics; serves both marketplace books and internal company knowledge layers.

Read more

markdown · Listed Jun 14, 2026

  • writing
  • publishing
  • candlekeep

From the first page

This is a meta-reference: a book about how to write books that AI agents can consume. It has two theory pillars and it obeys its own rules — it is its own worked example.

Pillar 1 — Agent-consumption mechanics. How an LLM actually reads, searches, and navigates a document, and how to structure pages so it can answer from one page without reading the whole book. Drawn from deployed agent-readable books: SEO for AI Agents, Code Review for AI Agents v4, Building Your Agent Team, Replicating Anthropic's Self-Service Analytics, the Anthropic Engineering Playbook.

Every quality rule in this book serves two audiences: a public marketplace reference book (value accrues through circulation) and an internal company knowledge layer (value accrues through governed reuse). Where the audiences need different handling, the chapter says so explicitly.

Preview · 2,000 of 39,761 characters

Awesome Design.md — A Curated Collection of Design Resources in Markdown
Dynamic Workflows in Claude Code: A Complete Guide to Multi-Agent Harnesses
SEO for AI Agents
Prisma ORM 7 Complete Reference

Contents

  1. 01Writing Books for AI Agentsp.1
    1. How to use this bookp.1
  2. 02Decision Matrixp.2
  3. 03What makes knowledge a good assetp.3
    1. Narrativep.3
    2. Agent rulesp.3
  4. 04Books vs RAG: why agent-readable books winp.4
    1. Narrativep.4
    2. Agent rulesp.4
  5. 05The human-vs-agent reading modelp.5
    1. Narrativep.5
    2. Agent rulesp.5
  6. 06Book architecturep.6
    1. Narrativep.6
    2. Agent rulesp.6
  7. 07Progressive disclosurep.7
    1. Narrativep.7
    2. Agent rulesp.7
  8. 08The rule-format catalogp.8
    1. Narrativep.8
    2. Agent rulesp.8
See all 17 parts
  1. 09Falsifiable thresholds & signal densityp.9
    1. Narrativep.9
    2. Agent rulesp.9
  2. 10Loading triggers & self-describing metadatap.10
    1. Narrativep.10
    2. Agent rulesp.10
  3. 11Citations, provenance & executable cross-referencesp.11
    1. Narrativep.11
    2. Agent rulesp.11
  4. 12Separating knowledge from procedurep.12
    1. Narrativep.12
    2. Agent rulesp.12
  5. 13Marketplace book vs internal company knowledge layerp.13
    1. Narrativep.13
    2. Agent rulesp.13
  6. 14Currency, staleness & useful business lifep.14
    1. Narrativep.14
    2. Agent rulesp.14
  7. 15Anti-patternsp.15
    1. Narrativep.15
    2. Agent rulesp.15
  8. 16Authoring workflowp.16
    1. Narrativep.16
    2. Agent rulesp.16
  9. 17The Self-Audit Checklistp.17
    1. Narrativep.17
    2. Agent rulesp.17
    3. Worked example — converting a human chapter into an agent pagep.17