Four sources.
One governed platform.
Canon Engine ingests knowledge from four source types, enriches non-vault sources with LLM processing, and serves everything through a unified query interface with source-type filtering.
Dual-layer storage model.
Every knowledge source is stored in two layers: a structured record with full metadata and enrichment output, and chunks in a shared pgvector table for semantic search. This allows both “get transcript by ID” and “find knowledge about X across all sources” through a single system.
Knowledge matures.
It doesn't just accumulate.
Canon vault documents follow a formal lifecycle. Only accepted documents are authoritative. Draft and in-review documents are provisional. Superseded documents point to their replacements. Non-vault knowledge sources are factual records — they don't need governance because they describe events, not positions.
Stewardship rule: Humans steward Canon. No automated system may promote a document to accepted status without human approval.
Three ways to ask.
Direct file reads at known vault paths. Zero latency, zero API cost. The primary interface for agent session protocols and governance checks.
Supabase pgvector with source-type filtering. Semantic search across all knowledge sources through a single function call.
Direct Supabase queries by ID, account, date range. Full metadata on every record.
Enrich what's raw.
Preserve what's governed.
Transcripts, emails, and documents receive automatic LLM enrichment on ingest — summaries, key decisions, action items, and topics. Canon vault documents receive no enrichment. They are human-authored governed content, preserved exactly as written. This distinction is a governance invariant, not a feature toggle.
Built to be replaced.
The Knowledge Platform Contract defines every interface. Read how substitutability is designed in from day one.