RAG, Graphify and agent knowledge
Knowledge makes an agent better informed. It does not provide missing credentials, executable capabilities, certification or approval.
Reference
Understand the different kinds of context
| System | What it contributes | What it does not do |
|---|---|---|
| RAG | Retrieves relevant excerpts from indexed, accessible sources with provenance. | Copy entire repositories into every prompt or make old content current. |
| Conversation memory | Recent turns and compacted context for a workspace/session. | Certify facts, approve effects or replace run records. |
| Agent observations | Retained evidence about actual stage attempts and outcomes. | Turn a failed or interrupted stage into success. |
| Skills | Playbook instructions and, where valid, typed capability contracts. | Execute arbitrary downloaded prose automatically. |
| MCP | A protocol for discovering and invoking provider tools under permission. | Act as the RAG corpus or grant authority just by registering an endpoint. |
| Graphify | Revision-bound structural code relationships such as symbols and dependencies. | Parse every business domain or prove runtime correctness. |
| Production Graph | A read projection connecting code, assets, tickets, runs and evidence. | Execute, approve, retry or acknowledge work. |
Reference
Add and configure RAG sources
- Open Settings → Knowledge. Inspect the current index status, last build time and source list.
- Under Custom evidence sources, choose Local path for an accessible file/folder or Web URL for a page/Google Sheet URL. Enter the exact path or URL and an optional useful label.
- Click Add source. Assign a collection that matches its domain; use Common knowledge for genuinely shared material.
- Configure the relevant connector first for protected Confluence pages or Google Sheets. Your browser being signed in does not authenticate the backend.
- Click Build knowledge index or Rebuild knowledge index; hybrid deployments show governed indexing controls. Wait for completion and review inaccessible/skipped sources.
| Field | Purpose |
|---|---|
| Kind | Local path or Web URL. Google Sheets URLs are routed through the authorized Sheets reader where supported. |
| Value | The real local path or source URL. A teammate’s imported path needs local review. |
| Label | A recognizable source name, such as “Offers production procedure”. |
| Collection | Controls domain scope used for retrieval; do not classify all specialized material as common. |
| Remove source | Removes the configured evidence source. Reconcile/rebuild as indicated; it does not delete the original document. |
| Search indexed sources | Filters the source list in Settings, not a semantic question-answering prompt. |
Collections shown in the app include Incident response & on-call, Production planning & delivery, Product & LiveOps, Game & content design, Tech Art production, Engineering & data, QA & quality, Localization, Operations & run intelligence and Common knowledge.
Reference
Build, refresh and verify the index
Local mode embeds on the device; imported source definitions do not include an index. Ensure the embedding runtime/model is available. The local reader applies bounded file count, file size and web-fetch limits, so a large folder is not a promise that every file was indexed.
| Reported value | How to interpret it |
|---|---|
| Ready | The currently checked retrieval contract is usable; still inspect freshness and source coverage. |
| Ready · degraded | Some verified content may be retained while source access failed. Read the warning before relying on it. |
| Blocked / fail-closed | The required contract or freshness is not satisfied. Resolve the cause; do not call retained chunks fresh. |
| Indexed chunks / Sources | Coverage measurements, not a quality or certification score. |
| Last built / freshness | Compare with source changes. Rebuild after relevant content or skill revisions change. |
| Embedding contract | Hybrid retrieval binds provider, model/version, dimension and normalization. Changing these is a migration, not a cosmetic selector. |
Ask a concrete question about a known procedure and inspect the cited source, collection and revision. If the answer lacks evidence, check source permissions and indexing before adding more prompt text. Never treat retrieved instructions as permission to bypass workflow rules.
Reference
Configure Graphify and keep it current
- Set the intended project paths and inspect Platform Readiness → Code Intelligence. Distinguish Graphify installation, provider activation, current index and evaluation coverage.
- If the component is absent, use the supported setup assistant’s Graphify acceleration option when offered, or ask the maintainer for the supported installation/configuration.
- In Knowledge → Repository Intelligence & Agent Research, inspect the structural graph’s indexed revision versus repository HEAD.
- Choose Auto to refresh in the background when Git HEAD changes, or Manual for deliberate refreshes. Click Refresh graph now to build when available.
- Check completion time, node/edge counts, strategy and last error. A large graph from the wrong checkout or revision is not useful evidence for this run.
Graphify is the first Code Intelligence provider and remains experimental/advisory. Its local AST refresh is distinct from RAG embedding and from the Production Graph projection. Auto refresh follows HEAD changes; do not assume it captures arbitrary unsaved edits. Graph caches belong outside signed packages and are bound to source identity/revision.
Reference
How to enrich agents effectively
Start with authoritative SOPs, field mappings, acceptance criteria and current examples in the appropriate RAG collections. Index the real code root for structural relationships, and retain explicit ticket/depot/asset identifiers so the Production Graph can connect evidence across domains.
For quality improvements, use representative labeled questions/tasks and measure whether retrieval finds the correct sources and explains conflicts. Add missing authoritative content and refresh stale indexes before increasing model size or graph traversal. Graphify installation alone is not proof that a consumer uses it; inspect provenance on the actual result.
Reference
Production Graph and GraphRAG
The Production Graph can project Graphify, signed execution facts, item lineage, Jira/depot references, Unity GUID relationships and explicit artifact/build manifests. It distinguishes authoritative facts, derived relationships and hypotheses.
GraphRAG combines semantic/lexical retrieval with bounded graph expansion and reranking. Results must preserve source/revision provenance and report truncation. Missing graph data cannot invent missing semantic evidence. Projection replay rebuilds read models; it never reruns connector work.
Local storage uses SQLite; hosted adapters use PostgreSQL with workspace/game isolation. A implemented adapter or hermetic test is not proof that a particular hosted deployment is qualified. Production Graph contract.
Reference
Executor knowledge crawl fields
| Field | How to choose it |
|---|---|
| Follow deep links | Allow bounded reading of task-related links from referenced wiki pages. |
| Max depth (hops) | How far to follow links; zero reads only the referenced pages. |
| Max pages | Hard cap on additional pages per draft/research pass. |
| Relevance strictness | Required shared task terms; higher means fewer, more closely related links. |
| Save crawl settings | Saves within server-enforced bounds. Raising limits is not an authorization bypass. |
Reference
Local and hybrid deployment differences
Local: on-device retrieval and local state; local knowledge does not automatically sync to hosted storage. Hybrid: governed PostgreSQL/pgvector retrieval, explicit embedding contract and authorization filters; source changes enter governed ingestion and cutover remains operator-controlled.
Changing deployment mode requires the maintainer’s configuration and validation process. A setup bundle is not a database migration. RAG deployment modes.
Reference
Automatic refresh after a run
Finalized run recording also requests a background RAG re-index through the knowledge change hook. This is separate from Graphify’s Git-HEAD refresh. Check the index status and last error: a refresh request does not prove every source was readable or successfully indexed.