@ayush115

I Evaluated My AI Agent. Three Decisions Were Wrong.

Apr 17 · 9 min read · In my last post, I built a customer support agent with conditional routing, RAG-grounded responses, and human-in-the-loop approval for billing actions. I ended that post by listing evaluations as the

Building AI Agents That Know When Not to Answer

Apr 14 · 7 min read · Most AI support agents fail in the same way. They answer questions they should not. A wrong feature explanation is annoying.A wrong refund is expensive.An insensitive reply to a frustrated customer ca

Building AI Agents That Know When NOt

Apr 14 · 7 min read · Most AI support agents fail in the same way. They answer questions they should not. A wrong feature explanation is annoying.A wrong refund is expensive.An insensitive reply to a frustrated customer ca

Your Agent Should Decide When to Use RAG

Apr 10 · 6 min read · Most RAG tutorials assume every query needs retrieval. That's a bad default. In a real agentic system, retrieval is just one tool — and often the wrong one. So instead of building another RAG pipeline

What Actually Happens When You Add Tools to a LangGraph Agent

Apr 8 · 7 min read · Most LangGraph tutorials stop at "it works." This post is about what breaks right after that. There's a big difference between understanding tool calling in theory and wiring it into a production-grad