https://korchasa.dev/tags/flowai-workflow/Recent content in Flowai-Workflow on korchasa@*opsHugoenFri, 08 May 2026 00:00:00 +0000https://korchasa.dev/posts/2026_05_08_lumatale_autonomous_agents/Fri, 08 May 2026 00:00:00 +0000https://korchasa.dev/posts/2026_05_08_lumatale_autonomous_agents/<p>I wanted to test <a href="https://github.com/korchasa/flowai-workflow" rel="nofollow noopener noreferrer external">flowai-workflow</a> on something more or less complex and real, since the usual &ldquo;home&rdquo; tasks are too simple, and work tasks are mostly built around ci/cd pipelines.</p> <p>In the end I decided to make a fully autonomous and cheap process for building services. The service is developed by a group of agents based on flowai-workflow. It plays all the roles itself, including product manager. I sometimes act as hitl, but not too often. Product and architect — sonnet 4.6 from the claude code subscription. Developer and QA — glm 4.6 from the annual z.ai subscription. Right now development speed is bottlenecked by glm limits, bugs, and my own meddling in the sdlc.</p>https://korchasa.dev/posts/2026_04_28_symphony_orchestrator/Tue, 28 Apr 2026 00:00:00 +0000https://korchasa.dev/posts/2026_04_28_symphony_orchestrator/<p>No worries, no worries. Soon they&rsquo;ll add multi-agents and decouple from linear, just like in <a href="https://github.com/korchasa/flowai-workflow" rel="nofollow noopener noreferrer external">flowai-workflow</a> :) Although running different agents and ides for different stages still won&rsquo;t work for them.</p> <p>Even isolated agents with self-checks can already close a fairly large percentage of tasks. Especially boring stuff like refactoring, documentation, tech-debt cleanup, and so on. The downside is the accumulation of unknowns in your own code, but that&rsquo;s covered by:</p>