Skip to main content

Docs as Tests & AI: A Strategy for Self-Healing Technical Documentation

The follow-up to Docs as Tests, written for the new reality every documentation team is navigating: AI is in the pipeline.

About the Book​

AI now shows up everywhere in the documentation pipeline. It generates content, consumes your docs through chatbots and RAG systems, and executes your procedures as agents—and every error along the way amplifies to thousands of users. Docs as Tests & AI extends the original Docs as Tests strategy to the four places AI touches your documentation and shows you how to verify each one, so the whole pipeline stays trustworthy.

The book assumes basic familiarity with documentation work but doesn't require any prior experience with Docs as Tests.

What You'll Learn​

  • The four AI integration points in your doc pipeline and what each one needs from testing
  • Probabilistic vs. deterministic verification: how to choose based on cost, risk, and product cadence
  • Workflow documentation AI can execute: project descriptions, agent definitions, plans, and skills agents can actually run
  • Self-healing systems that detect drift, diagnose the cause, fix the docs, verify the fix, and report what happened
  • Governance frameworks that balance agent autonomy with the right amount of human oversight

The book also includes lessons and case studies from teams at Anthropic, Avalara, Google, Kong, and Vercel—real numbers, real tradeoffs, and real workflows you can adapt.

Who It's For​

This book is designed for:

  • Technical Writers integrating AI into their documentation workflows
  • Documentation Engineers building and maintaining doc testing pipelines
  • Developer Advocates generating drafts with LLMs or feeding docs into chatbots and RAG systems
  • Any team letting agents act on documented procedures

With forewords by Scott Abel and Michael Iantosca.

Key Benefits​

If your docs touch AI—or AI touches your docs—this book gives you:

  • A verification layer that makes the whole AI-powered pipeline trustworthy
  • Practical decision criteria for where to apply probabilistic vs. deterministic checks
  • Patterns for self-healing docs that fix themselves and report what changed
  • Governance you can defend, balancing automation with human oversight
  • Battle-tested case studies from teams shipping AI-assisted documentation at scale

Get the Book​

  • Amazon - Kindle, paperback, and hardcover formats
  • Physical copies are available through retailers worldwide

About the Author​

Manny Silva is Head of AI Docs Practice at Promptless and creator of the Docs as Tests methodology. With experience at companies like Apple and Google, he's developed practical strategies for keeping documentation resilient at scale. His work focuses on building tools and processes that make documentation testing accessible and effective for teams of all sizes.

Questions about the book or docs-as-tests approach? Connect on LinkedIn or check out the blog.