Skip to content

PointSav Documentation

The engineering library for the PointSav platform — operating systems and services for regulated businesses that own their data, their AI, and their record-keeping outright. Where the monorepo holds the code, this wiki holds the reasoning: architecture, services, security, and the governance commitments that bind future development.

PointSav Digital Systems

Last updated · 498c83f7 · Español

Knowledge-graph-grounded apprenticeship

Knowledge-graph grounding is the pattern by which the Doorman (AI inference service) consults the per-tenant knowledge graph in service-content — entity extraction and knowledge-graph host before dispatching a request to a compute tier. Matching entities are prepended to the model's system prompt as factual context, isolated per tenant by module identifier — the Woodfine adapter never sees PointSav graph context or vice versa.

This pattern extends the Apprenticeship substrate with a graph-grounding layer.

Pre-inference grounding

Before dispatching a request, the Doorman extracts words of four or more characters from the user's most recent message and queries service-content — entity extraction and knowledge-graph host for entities whose names substring-match those words, preferring longer and more specific candidates first. A matching entity carries its classification (Person, Company, Project, Account, or Location) and, where known, role, location, and contact detail — the query defaults to one hop out from the matched entities, not a wider traversal. Results are prepended as a system message the model sees alongside the user's query.

The lookup is non-fatal: if service-content is unavailable or no entity matches, the request proceeds unmodified. A generic system-administration question with no relevant entities in its text simply gets no grounding — that is the expected, common case, not a failure.

No automatic graph-writeback from inference

Nothing in the Doorman's routing or verdict-handling path writes back to the graph. The mutation endpoint service-content — entity extraction and knowledge-graph host exposes (POST /v1/graph/mutate) exists, but its only real caller is a human-operated tool — project-editorial's graph-committer.py, which requires an operator to review a staged proposal and pass --confirm before anything is written. A separate, unrelated path writes graph entities without a per-item human review: a nightly extraction job that (when enabled) captures automatically-extracted entities for later batch approval rather than writing them immediately — see Nightly DataGraph rebuild for that mechanism's own real behavior and its currently-open governance gap. Neither path is triggered by an inference request's verdict.

Graph-coherence quality metrics

A model response can still be evaluated against the knowledge graph on three dimensions, independent of whether the graph itself changes:

Citation rate — the fraction of named entities in the response that exist in the graph. A high citation rate indicates the model is staying within known facts.

Relationship accuracy — the fraction of stated relationships that match the graph's own recorded edges. Inaccurate relationships signal model drift from the grounded record.

Hallucination rate — the fraction of named entities in the response that are not present in the graph. Hallucination rate is the primary failure mode; responses above a threshold are candidates for refinement or rejection. 1

These metrics feed the verdict process. A response with high hallucination rate is rejected; one with low citation rate is a candidate for refinement before acceptance.

Dependency on single-boundary discipline

Grounding depends on the Single-boundary compute discipline. If inference can bypass the Doorman, it bypasses graph grounding entirely — a request routed around the Doorman gets no entity context and no citation-rate measurement. Without single-boundary enforcement, grounded apprenticeship cannot be guaranteed for every request.

See also

  1. Edge, D. et al. 'From Local to Global: A Graph RAG Approach to Query-Focused Summarization.' arXiv:2404.16130, 2024. https://arxiv.org/abs/2404.16130 ↩

Cite this record: /wiki/knowledge-graph-grounded-apprenticeship — revision 498c83f7, last updated 22 August 2026.

Important Information

Corporate structure. PointSav Digital Systems ("PointSav") is currently a trade name of Woodfine Capital Projects Inc. ("Woodfine"), planned to become a wholly-owned Woodfine subsidiary upon incorporation. PointSav does not itself offer, sell, or solicit any security. Any securities offering associated with Woodfine's real-property direct-hold solutions is made exclusively by Woodfine, and only by means of the applicable Private Placement Memorandum.

No investment advice. This wiki's content is provided for engineering, operational, research, and development purposes. Nothing on this wiki constitutes investment advice or a solicitation to invest in any Woodfine partnership or direct-hold solution.

Intellectual property. The PointSav name, trade name, wordmark, and marks, together with all current and future PointSav- and Totebox-branded products, services, and offerings — and the software, source code, documentation, design system, and all related materials — are proprietary to Woodfine and its affiliates, except for components identified as open source. No rights are granted except as expressly set out in a written license or agreement. The full trademark notice appears in the footer of every page on this site.

Open source components. Portions of the platform are made available under permissive open-source licenses identified in the accompanying repository. Use of those components is governed by their respective license terms.

No warranty; informational use. Content on this wiki is provided for general informational purposes only and does not constitute a representation, warranty, or commitment with respect to product functionality, availability, pricing, or roadmap. Some articles describe planned or intended features, capabilities, and milestones — language such as "planned," "intended," "targeted," "may," and "expected" marks this forward-looking content, which is subject to change and does not constitute a commitment regarding future performance.

Confidentiality. Where an article describes an operational or deployment detail that is not intended for public disclosure, that article is not published on this wiki. Content here is general-purpose engineering documentation, not customer-specific configuration.

Jurisdiction. Woodfine Capital Projects Inc. is organized in British Columbia, Canada. References to the Sovereign Data Foundation on this wiki describe a planned or intended initiative only, not a current equity holder or active governance body.

Changes to this notice. PointSav may update this notice from time to time; the version posted on this page governs.

Not a filing system. This wiki is not a securities filing system, an electronic disclosure repository, or a substitute for SEDAR+ or any other regulatory filing system. Formal securities filings are made through the applicable regulatory filing system, not through this wiki.

Full disclaimer. This notice supplements, and does not replace, the full Disclaimers article. In the event of any conflict, the full Disclaimers article governs.

Read the full disclaimer →