#debugging
Every post tagged "debugging".
34 posts · showing 1–10
-
The Agent Said It Booked the Meeting. Learn to Read One Turn: Text, Tool Call, Tool Result, and Which One Counts
An agent's reply can describe an action it never took. Once you can tell the three kinds of message in a transcript apart, you will know in ten seconds whether the calendar invite exists.
-
Can You See the Raw Messages? The Question That Sorts Agent Frameworks
Every agent framework demos well. The one that survives your first 2am incident is the one that will hand you the exact bytes it sent to the model — and let you change them before they go.
-
Your Agent Called the Same Tool Three Times in a Row. Here's What the Loop Is Telling You.
A repeating agent isn't being stubborn — it's being consistent. Identical tool calls mean the context barely changed between turns, and there are only four reasons that happens.
-
Framework or Raw SDK? The Test Is Whether You Can Print the Exact Prompt
The framework debate is usually argued on taste. There's a faster test: build a two-tool agent and try to dump the exact request it sends on turn four. How hard that is predicts your next six months of debugging.
-
Your Retriever Returned 12 Chunks. The Agent Only Really Read 3 of Them.
The correct passage was in the prompt and the agent wrote around it anyway. That's not a retrieval bug — it's a placement bug, and there's a one-minute test that tells the two apart before you touch your embeddings.
-
Four Tool Calls to One Answer: A Research Run, Annotated
A research agent answers one question in four steps. Reading what changed in the transcript between each step explains more about how agents work than any diagram of the loop.
-
The First Hour of an Agent Incident
Nothing crashed, no alert fired, and a customer just forwarded a policy answer your support agent invented. The hardest question in the first hour isn't what broke — it's when it started.
-
Was It Retrieval or Reasoning? Diagnosing a Wrong Answer
A day spent rewriting the prompt for a wrong policy answer, when the policy document was never retrieved. Three checks in the right order, and one log field that separates "ignored it" from "never saw it."
-
Test the Tool or Test the Agent? What Each Layer Catches
Sort a month of eval failures by root cause and most turn out to be tool contract bugs — findable in milliseconds by a unit test, currently being caught by the slowest instrument you own.
-
The Timeout That Looked Like an Empty Result
The health check timed out, the handler returned an empty list, and the agent reported all clear while two services were down. An empty result and a failed check must not share a shape.