For leadership ยท How our AI engineering team works
One Captain. Specialist bots.The owner approves every gate.
The Captain takes every request and hands it to specialist bots, who work in parallel where safe. Work stops at owner approval gates, no bot ever commits code, and all bots share one cache instead of re-reading documents. Click any bot in the map to see what it does.
โจ Feature path
๐ Bug path
All bots
โถ Walk through the path
Feature flow Bug flow Human gate Fix loop Shared cache
The flow Handoff chain
Captain reads the request and picks the path (a question gets an answer only)
Intake bots read the tracker ticket, the requirements doc, the design and the code once
The owner approves the brief
Gap Finder lists gaps and questions
The owner answers, and the answers go to the planner
Dev Planner writes the plan, test cases and must-haves
The owner approves the plan and confirms the repo
Devs build and write tests, QA writes test cases
Analyzer gate: fail goes back to devs
Review bots check in parallel, comments go back to devs
QA tests on devices: fail means rework, pass means the report
The owner accepts the QA report, then the tracker is updated and Done
Key rules What every bot follows
โ
Quality first Must-haves before coding, self-check before handoff.
๐งช Light TDD Test cases planned, tests written for every new function.
๐ Code gate Grade B or above, 80%+ coverage on changed code.
๐ฏ Pixel QA Checked against the design on several device sizes.
๐ฐ Token saving Short summary files, related files only, failures only.
๐ง Right model Heavy model only for gaps and planning.
๐ One rulebook Cache Keeper syncs rules across every bot and AI tool.
๐งฉ Project first The project's own rules win, except safety rules.
Trust How it stays safe and reliable
๐ Metrics (to be measured) Hours saved per ticket TBD Rework loops TBD Token cost per feature TBD
๐๏ธ Concurrency Each task has its own tasks/<TASK-KEY>/ folder. Shared files are edited by one dev at a time.
โ Stuck gates Gates never auto-approve. Work waits for the owner. Captain B only prepares work.
๐ Loop metrics Analyzer fails, PR comments and QA fails are logged in tasks/<KEY>/loops.md.
โก Small fix route A typo or one-line fix skips Gap and Plan: dev, analyze, quick review, 1 to 2 gates.
๐งพ Audit trail tasks/<KEY>/approvals.md records stage, decision, by whom and when.
๐พ Checkpointing Every stage writes its .md, so any bot can resume from the last finished stage.
FAQ Quick answers
What if bots disagree? Captain decides, and the owner has the final say.
Faster, but better? Yes: the code gate, pixel QA and loop metrics keep quality up.
What if a bot is wrong? Every stage has an owner gate plus review.
Is data safe? Test data stays local, no secrets are read, and only the owner does git.
A general explainer of how the bot team works. Metrics will be added once measured.