Agent Runs Are Black Boxes: A Trace-First Debug Loop

Agent Runs Are Black Boxes: A Trace-First Debug Loop As agents take on more coding work, the developer's job shifts from writing to reviewing. Reviewing without a trace is guessing. When an agent misbehaves, the instinct is to edit the prompt — but the prompt is the wrong artifact. The run is the artifact: the ordered list of tool calls, diffs, and token spends that actually happened. Trace it…