rai-story-review

To run a story retrospective after implementation and passing tests, execute the review process to aggregate design and plan artifacts, compute acceptance metrics, and generate a retrospective document.

Extracting reusable patterns involves querying the project knowledge graph for context, computing gap metrics from story phases, and persisting new technical or process patterns into the memory store.

Yes, tests must pass using manifest-configured commands or language defaults before capturing learnings, ensuring the story review only processes validated implementations to compute metrics and reinforce patterns.

A knowledge graph improves story retrospectives by providing contextual historical data during the review, enabling the system to accurately compute metrics and reinforce existing behavioral patterns through explicit voting.

Yes, you can persist process improvements automatically by running the post-implementation review, which adds newly identified patterns to the memory store and reinforces behavioral patterns for long-term calibration.

Computing acceptance and gap metrics requires aggregating learning records from the story-design, plan, and implement phases, combining them with knowledge graph context to produce the final retrospective document.