Reflection

Problem

One-shot generation underuses the model in a specific way: the model has the ability to spot its own surface errors when it is asked to look at a finished draft, but in a single forward pass it commits to tokens without the opportunity to review what it has written. Without a separate critique step, obvious local mistakes ship even when the model could have caught them. A naive free-form critique pass helps a little but invents new criteria on each call, so reviews are inconsistent, and after one or two iterations the same model just starts approving its own work. The team needs structure around the critique step to make it actually catch errors instead of rubber-stamping.

Solution

After producing an output, the model is prompted (often as a critic persona) to find issues. The original output and critique go back into a revision step. Repeat until a stop condition (no new issues, max iterations).

When to use

• One-shot generation underuses the model and a critique pass would catch errors.
• A critic prompt can identify issues meaningfully on the task's outputs.
• Stop conditions (no new issues, max iterations) can be defined.