---
title: "Enrich"
type: "glossary-term"
category: "Corpus & data pipeline"
canonical_url: "https://www.graphcanon.com/glossary/corpus-and-data/enrich"
updated: "2026-07-09"
---

# 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

- [How trust signals work](/trust-methodology)

## Related terms

- [Ingest](/glossary/corpus-and-data/ingest.md)
- [Backfill](/glossary/corpus-and-data/backfill.md)
- [Large language model (LLM)](/glossary/ai-and-llms/large-language-model.md)

[Corpus & data pipeline](/glossary/corpus-and-data.md) · [All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_