Flow of Autonomous Brain and its Engine

posted Originally published at github.com 1 min read

On the last post, I mentioned usuage of multiple github models, but made some more modifications, and now 2 new providers are also added to the boardroom.

STAGE 1 ARCHITECT CONFERENCE

     Architect A (Mixtral/Groq) + Architect B (Llama/Groq) propose plans in parallel
     Judge (GPT-4o) synthesises or proposes a more unpredictable plan

STAGE 2 IMPLEMENT

     Engineer (GPT-4o) writes each file with full sibling context

STAGE 3 QUALITY LOOP (up to 8 rounds)

     Reviewer A (Mixtral/Groq) + Reviewer B (Gemini) in parallel
     Fixer applies merged feedback + Playwright interaction test

STAGE 4 QA REVIEW

     Playwright clicks every button, tests every slider
     QA Tester (GPT-4o) issues verdict: shippable / partially_usable / non_functional

STAGE 5 PUBLISH

     New public GitHub repo created via API
     GitHub Pages enabled -> live URL in under 60 minutes from cold start

STAGE 6 SELF-IMPROVE

     CTO (Gemini) reads last 30 failure logs, proposes a surgical source patch
     Validates Python syntax, commits - next build runs improved code

More Posts

TypeScript Complexity Has Finally Reached the Point of Total Absurdity

Karol Modelskiverified - Apr 23

I’m a Senior Dev and I’ve Forgotten How to Think Without a Prompt

Karol Modelskiverified - Mar 19

I Wrote a Script to Fix Audible's Unreadable PDF Filenames

snapsynapseverified - Apr 20

Your App Feels Smart, So Why Do Users Still Leave?

kajolshah - Feb 2

Why Prompt Engineering Is Just an Expensive Way to Be Incompetent

Karol Modelskiverified - May 21
chevron_left

Related Jobs

View all jobs →

Commenters (This Week)

1 comment
1 comment
1 comment

Contribute meaningful comments to climb the leaderboard and earn badges!