Why I Started BuildWithAgents: A Developer's Perspective

Three years ago I was building a document processing pipeline for a client and hit a wall. I needed something that could understand context, reason over multiple documents, and route outputs to different downstream systems. Traditional rule-based automation was not going to cut it.

That project sent me deep into the world of language models, vector search, and eventually agent frameworks. What I found was powerful but scattered. Great research papers, promising tools, and almost no practical guidance on how to put it all together.

I started BuildWithAgents to be the resource I wished had existed. Every guide here comes from real implementation experience. When I write about chunking strategies or agent memory patterns, I am writing from having built and broken those systems myself.

My technical background spans Python, TypeScript, cloud infrastructure, and now the growing ecosystem of AI tooling. I am particularly obsessed with reliability, because in production, an agent that mostly works is often worse than no agent at all.

I update this site regularly as the ecosystem evolves. Subscribe to the newsletter if you want to stay current without drowning in noise.