Reviewer Agent: Separate Builder from Marker
The agent that wrote the code cannot grade it. A reviewer is a second loop with a different system prompt, a different goal, and read-only access to everything the builder produced. The gap between builder and reviewer is where most reliability lives. State why the same agent cannot reliably review its own work. Build a reviewer agent loop that consumes builder artifacts and emits a structured review report. Author a reviewer rubric that grades specific dimensions, not vibes. Wire the reviewer into the workbench so the human review step starts from a real artifact. You ask the agent to fix a bug. It edits four files, runs the tests, and reports done. The verification gate (Phase 14 · 38) confirms acceptance ran and scope held. The gate says passed: true. You merge. Two days later you find that the fix solved the wrong half of the bug. Acceptance is necessary, not sufficient. The reviewer asks the questions acceptance cannot ask: did this solve the right problem? Did it expand scope without flagging it? Did it document assumptions that should have been questioned? Did it leave the workbench in a state the next session can pick up? Five dimensions, each scored 0 to 2. Total out of 10. A run below 7 is a soft fail; a run below 5 is…
Reviewer Agent: Separate Builder from Marker: The agent that wrote the code cannot grade it. A reviewer is a second loop with a different system prompt, a…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.