Learning from the person's own AI history

The idea

A person imports their own transcripts, files, commits and messages. Traits they accept steer briefs, checks and voice. History they bind to one repository becomes facts, decisions and documents that they confirm.

The problem
Workers do not work the way the person does, and decisions in past AI chats are lost.
Why it matters
Work follows the person's accepted habits and the repository's own facts, each with its source.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • Team pipeline profile and layered preferences

    Onboarding proposes how the team works (design first, test first, trunk, approvals, strict paths, stage shares), with a backtest over 30 merged PRs. Accepted settings resolve in layers, with the person's own layer on top.

  • Gate on all outgoing text

    Commits, PR text, comments, messages and reports go through rule-based checks (length, structure, banned phrases, attribution, secrets) and a style check against examples a person approved. Failing text gets a limited number of rewrites.

  • Correct once

    When you correct an AI worker once, Crewshal turns the correction into a lesson, and the worker gets that lesson again when later work touches the same part of the code.

    Recorded walkthrough

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.