learnings-researcher

To search past solutions, filter the docs/solutions knowledge base by parsing frontmatter fields like module, problem_type, and tags. This surfaces relevant institutional learnings to guide architecture planning and prevent repeated engineering mistakes.

Finding relevant learnings before fixing a bug requires matching frontmatter metadata such as component and problem_type against your current task. This contextual filtering prioritizes applicable past solutions to align with engineering guidelines and accelerate knowledge reuse.

Yes, you can filter a knowledge base by module and component by parsing specific frontmatter fields. Locating and distilling relevant institutional learnings relies on matching these metadata tags to your current feature work or bug fixes.

Matching frontmatter metadata helps avoid repeated mistakes by pinpointing applicable past solutions within the docs/solutions knowledge base. Distilling these learnings provides immediate architectural context and prevents teams from recreating previously resolved patterns.

You need frontmatter fields like module, problem_type, component, and tags in your docs to use a learnings search effectively. Parsing these structured metadata fields is required to accurately surface and distill relevant institutional learnings for your tasks.