Field notes on reliable AI agents.
Richard Luo · PhD @ HKU. Writing about reliable AI agents, LLM engineering, and research practice. Concrete examples, clear limits.
Your Agent Finished. What Exactly Did It Finish?
An agent says it has finished updating a document. The output looks sensible. It even includes a tidy summary of the changes. Then someone opens the document and finds the old version. There are several possible explanations. The agent might have edited a different copy. A tool might have accepted a request without completing it. A background process might still be running. Or the summary might simply be wrong. From the reader’s perspective, these failures look similar: the promised result is missing. ...