Show HN: Pullboard – An agent development workflow that builds itself Pullboard, an MIT-licensed agent development workflow that builds itself, has been released on GitHub and npm by its developer, who used it to grow a quantitative trading platform to roughly 500,000 lines of code running across more than a dozen Mac minis. The workflow follows a claim, build, verify loop in which a different agent reviews each change, and it accumulates what the developer calls Agentic Institutional Knowledge — items, shouts and doctrine stored in Pullboard history so future agents can reference prior lessons instead of losing them in old chats. The developer began using agents seriously at around 30,000 lines of code and worked full-time on the project for the last eight months. Been working on a quantitative trading platform for about 2.5 years, off and on, then full-time for the last eight months. I started using agents seriously around 30,000 lines of code and found an agentic workflow I could trust, and I turned that into Pullboard. Pullboard builds Pullboard itself. MIT : https://github.com/pullboard-dev/pullboard https://github.com/pullboard-dev/pullboard Essential Loop: claim - build - verify different agent reviews, see website. Primitive Concepts: https://pullboard.dev/tutorials/ https://pullboard.dev/tutorials/ I absolutely needed to trust my agents to write proper code and worked out an Agentic Item Lifecycle AILC that works for me, within an Agentic Development Lifecycle ADLC . My flavor of all this may not be "correct" but it does work, and it helped me build out a quant trading system. That system is now roughly 500K LOC and runs across more than a dozen Mac minis. It trades autonomously and runs dozens of strategies, and it must work at market open. That aside, what makes this workflow valuable is the "Agentic Institutional Knowledge" that gets built up over time outside the codebase in the Pullboard history; e.g., items, shouts and doctrine all get referenced, discussed and lessons remain available to future agents instead of disappearing into old chats. The best part is I hardly re-explain myself. You do have to steer agents and make decisions, but this is quite nearly autonomous development. Anyways it is early and open source. See: Pullboard.dev or try, npm install -g pullboard pullboard tour Feedback welcome. Thank you Comments URL: https://news.ycombinator.com/item?id=50025023 https://news.ycombinator.com/item?id=50025023 Points: 1 Comments: 0