Search posts, tags, users, and pages
Vamsi Krishna
Building production-ready AI systems and sharing practical field notes on LLMs, RAG, agents, evaluation, and governance.
An agent run once produced a perfectly reasonable plan, executed it cleanly, and wrote the output into the wrong workspace. No exception. No alert. The model behaved exactly as intended. The runtime h
Nahid Mahmud
Building open-source tools for developers
This hit home! The practical insights here are genuinely helpful. How do you measure the success metrics for a setup like this?
Nahid Mahmud
Building open-source tools for developers
This hit home! The practical insights here are genuinely helpful. How do you measure the success metrics for a setup like this?