Viewing profile — LeoStehlik

thank you so much mate!

Started working on WrenLore, a Knowledge Base / Knowledge Management system built for both humans and AI agents. Humans review, use the nice clean UI, AI work on writing the docume…

Exactly. How much % coding represent in designing, building, shipping, deploying, integrating, maintaining and evolving software? My take is 20-30%. Still great to have the coding …

same, but that follows. Why I wanted a proof first is so that I don’t waste time running tests on code that was far from finished yet. Especially early days this year, I’d get agen…

I built this because my coding agent kept telling me he did complete the task, but when I verified it, it was not the case. I made Proof Loop fairly light, intentionally. It’s basi…

Back in 2011 at Fujitsu, I ran one of the earliest Azure production subscriptions outside Microsoft. Windows Azure, mid-2011. I've watched this platform for 15 years from the outsi…

Both, as it proved neither is enough on its own. The structural fix is the obsession about separating roles: the agent that builds is never the one that verifies. I run a reviewer …

This is what I've been missing running multi-agent ops through OpenClaw. The opacity problem is the one I hit hard: when a coordinator spawns 3-4 agents in parallel (builder, revie…

[dead]