Use This Two-Step Dictation Strategy to Write Better Docs (typeless Tutorial)

This guide teaches a two-step voice dictation system for writing better docs with AI. You will create a repeatable workflow where AI drafts the first structure, Typeless captures your spoken edits, and an agent rewrites the working draft in your voice. The system also improves over time by saving a before-and-after trail of your drafts.

• Founders and operators who write a lot of memos, updates, and internal docs but do not want them to sound like generic AI
• Creators and marketers who use AI for first drafts but still need the final version to sound like their actual voice
• Anyone using Codex, Claude Code, Claude, or ChatGPT who wants a repeatable writing system instead of starting from scratch every time

You will build a reusable writing workflow where AI creates the first structure, Typeless captures your spoken edits, and an agent rewrites the working draft in your voice.

• An untouched initial draft
• A working draft you can edit freely
• A before-and-after trail that helps an agent extract the editorial rules you keep applying

• Typeless installed for dictation; the free plan works
• Codex, Claude Code, Claude, ChatGPT, or another AI tool that can draft and revise documents
• A document you want to write, like a memo, project update, guide, proposal, or email
• A simple place to save markdown files, docs, or drafts

• Once you have an initial draft and a final working draft, you can ask an agent to compare them and extract editorial rules. You can also turn the process into a weekly automation that looks for new initial and final drafts, compares them, and updates your editorial rules file so future writing sessions have more context.

• Look at the initial version and the final working draft. Pull out the editorial rules for future writing. Add them to an editorial-rules.md file. Keep the rules concise and de-duplicate anything repetitive.