stet.
All use cases LLM wiki Spec-driven development Technical documentation Agent skills Company OS
Blog Why markdown + git Where Stet fits Security and data Roadmap Release notes
Pricing Docs

Use cases

All use cases LLM wiki Spec-driven development Technical documentation Agent skills Company OS

Resources

Blog Why markdown + git Where Stet fits Security and data Roadmap Release notes Pricing Docs
Log in Download for Mac

Blog

Notes on writing with AI, reviewing what it changes, and building Stet in public.

  • August 17, 2026

    The approve button wears out

    Anthropic flipped Claude Code to auto-approve by default. The research behind that call is 80 years old, and every review tool should read it.

    A long stream of accept and reject decisions continuing beyond the frame.
  • August 15, 2026

    Markdown won. The review layer didn't come with it.

    You moved your docs to plain text so AI could work in them. Track changes, comments, the back-and-forth got left behind in Word.

    A paper document with a translucent review layer marked in red on top.
  • July 30, 2026

    I paid 52 strangers to poke holes in Stet

    A building-in-public look at what an early value-prop study told me. Half of them said the problem was theirs. The framing I was most invested in came last.

    A field of 52 people represented by small circles, with the study participants marked in red.
  • July 27, 2026

    Why your AI works better in plain text

    If you moved your docs to markdown and the agent suddenly just gets it, that is not a coincidence. A short explainer on why plain text on git became the format AI work runs on.

    A typed note listing three plain-text benefits: less wrapper, fewer tokens, and readable by both.
stet.
Terms of Service Privacy Policy
Let it stand.