What problem does it solve?
Parses raw customer feedback (app reviews, support tickets, interview transcripts) into categorized severity-ranked themes, scans the codebase to identify affected files and components, and proposes 3 structural edit options per theme (minimal/refactor/architectural) with rationale tied directly to the original feedback. Trigger when: user provides raw customer feedback and wants to know what to change in the code; or an agent holds user complaints needing file-level engineering proposals. Do NOT trigger for: internal PR/code review comments (use receiving-code-review instead), stack-trace bug reports (use systematic-debugging instead), or PRD drafting.
Core Features & Use Cases
- Ingest feedback and extract concrete behaviours to drive structured themes
- Classify themes by category, severity, and pattern count, then map to relevant code areas
- Propose exactly 3 edit options per theme with rationale tied to the original feedback
- Gate via human confirmation and codebase-scanning rules to ensure safe, scoped changes
Quick Start
Paste raw customer feedback to generate themes and three edit options per theme.