Building Trustworthy and Reliable AI Agents: Practical Challenges in Production and Observability
Hi all. I'm Anson, excited to be here. I鈥檓 an engineering leader working on AI products and have gotten increasingly interested in the practical side of making agents reliable in production: evals, observability, failure handling, durable workflows, and all the messy stuff that shows up after the demo works. I joined because I鈥檓 looking for people who care about the same thing: how to build agentic systems that are actually trustworthy, inspectable, and operable in the real world. Would love to hear what folks here are working on, especially if you鈥檝e been deep in agent reliability, tracing, or evals.
