Tom Johnson's AI-Assisted Technical Writing Workflow
Table of content

Tom Johnson is a technical writer at Google based in Seattle. He runs I’d Rather Be Writing, one of the longest-running technical writing blogs, and hosts a popular API documentation course. His writing on AI workflows has become required reading for technical communicators adapting to LLM tools.
Johnson reports roughly doubling his productivity since incorporating AI into his documentation workflow. His approach treats AI as a power tool requiring skilled direction rather than an autonomous writer.
Background
- Education: English degree from Brigham Young University, MFA in literary nonfiction from Columbia University
- Career path: Teacher in Cairo, copywriter in Florida, eight years at Amazon, now at Google
- Blog: Publishes regularly since 2006 at idratherbewriting.com
- Course: Free API documentation course used by thousands of tech writers
- Community: Hosts the AI Book Club discussing books about AI and human-in-the-loop perspectives
The Iterative Workflow
Johnson’s methodology rejects the “magic button” approach to AI writing. Instead, he breaks documentation tasks into discrete steps:
Gather source material. Record engineer interviews, collect internal docs, pull code samples. The quality of inputs determines output quality.
Distill with AI. Feed 100+ pages into large-context models (700K+ tokens). Ask for summaries, extract key concepts, identify gaps.
Generate section by section. Don’t ask for complete documents. Work through outlines one topic at a time.
Apply chain of thought. Separate evaluation from action. First ask AI to identify issues, then fix them in a second pass.
Review and iterate. Multiple cycles for factual accuracy, technical correctness, and editorial quality.
From his April 2024 blog post: “The more you can decompose complex processes into discrete steps, the outcome will be better.”
Use Cases for Documentation
Johnson identifies ten areas where AI adds genuine value for technical writers:
| Use Case | Application |
|---|---|
| Code comprehension | Explain what unfamiliar code does |
| Bug thread distillation | Extract actionable updates from long discussions |
| Content summarization | Condense lengthy source material |
| Grammar and style | Get second opinions on unclear sentences |
| Information typing | Restructure content into standard patterns |
| API comparison | Find discrepancies between specs and responses |
| Glossary drafting | Generate initial definitions for technical terms |
| Build scripts | Write automation for publishing workflows |
| Data synthesis | Find patterns across granular feedback |
His AI-powered documentation section covers each in depth with practical prompts.
Human-in-the-Loop Philosophy
Johnson positions AI as collaborative rather than autonomous. Documentation requires context that AI lacks: organizational priorities, audience needs, what’s been tried before, political sensitivities.
Key principles from his writing:
AI excels at voiceless, explanatory content. Documentation written in neutral third person suits AI well. Experience-driven or opinion pieces don’t.
Raw output is insufficient. First drafts need substantial editing. The time savings come from faster iteration, not skipped steps.
Prompt engineering isn’t obvious. Many writers struggle despite AI’s clear potential. Success requires learning to guide the tool.
From December 2023: “My central argument is that AI use cases are so ubiquitous they apply to all facets of life.”
Tools and Setup
Johnson primarily uses:
- Gemini for large-context documentation work (700K+ token windows)
- Claude for creative content and blog writing
- ChatGPT for comparative analysis and grammar checking
He emphasizes matching tools to tasks. Large context windows matter for digesting engineering docs. Creativity matters for blog posts. Grammar checking needs different strengths.
The AI Book Club
Johnson co-hosts monthly discussions on AI-related books at idratherbewriting.com. Recent reads include Ethan Mollick’s Co-Intelligence, Karen Hao’s Empire of AI, and Yuval Noah Harari’s Nexus.
The club reflects his broader approach: treat AI as a subject worth studying, not just a tool to use.
Key Takeaways
| Principle | Implementation |
|---|---|
| Task decomposition | Break docs into sections, process individually |
| Chain of thought | Evaluate first, then fix |
| Source quality | Better inputs yield better outputs |
| Human review | Multiple passes for accuracy |
| Tool matching | Different AI tools for different tasks |
Links
- I’d Rather Be Writing
- API Documentation Course
- AI-Powered Documentation
- AI is accelerating my technical writing output
- 30+ ways I’m using AI tools
- GitHub: @tomjoht
Next: Simon Willison’s Workflow
Get updates
New guides, workflows, and AI patterns. No spam.
Thank you! You're on the list.