Corpus & data pipeline

Enrich

Enrichment runs a language model over already-stored data to add or improve derived fields - summaries, tags, decision facts - without fetching from GitHub.

Enrich is the LLM pass over the existing corpus. It reads stored repository data and produces derived content: neutral taglines and summaries, category and tag suggestions, decision facts, and comparison narratives.

Because it works on stored data (no GitHub fetch), enrichment can be re-run to backfill or improve fields as the pipeline evolves.

In GraphCanon

Enrichment fills the parts of the graph that are not raw GitHub facts. Runs are logged and can be scoped to a ticket so the work is auditable.

See also

Related terms

Last reviewed 2026-07-09

Command menu

Search tools or jump to a page