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.

Historical revision — this record as it stood on 4 September 2026, not the current version. View the current record →

How AI Is Used and ContainedIndex

The ai category collects where AI sits in the platform and where it is not allowed. It covers the boundary that keeps AI away from the authoritative record, the routing between models, and the small, customer-side models designed to learn a customer's own environment. The deterministic core runs fully without AI.

This is the front door for the platform's most distinctive architectural claim — AI is used, and it is contained — and for engineers looking up a specific piece of the AI stack: the inference boundary, sovereign routing, the vendor-tier model programme, and the training pipelines that produce it.

"The core runs fully without it" is this category's own headline claim, and the article that argues it — Substrate without inference — The base case — lives in Building Blocks, not here. Read it first if you're evaluating the containment claim itself; everything below assumes it.

The Doorman boundary

The single gateway every inference call routes through — no service holds its own AI credentials or makes a direct outbound call.

  • Doorman protocol — The Doorman is the sole AI request boundary through which every inference call routes, holding every external-model credential and logging every call to an immutable audit ledger.
  • AI routing and the linguistic air-lock — AI routing holds every external-model credential and audit-logs every request at a single boundary. It does not scrub PII from prompts, and Tier C external routing is not live yet.
  • Decode-time constraints — The constrained-decoding technique, and a clear line between it and what PointSav has built today: an advisory post-generation linter, with the grammar-based mechanism itself planned, not shipped.
  • SLM Rust stack architecture — The full Rust dependency graph and binary architecture for service-slm, the Doorman service that mediates every inference call in the PointSav platform.

Compute tiers

Where inference actually runs, and the vendor-tier model this routes toward at the top.

  • Zero-container inference — Tier B GPU deployment pattern using native Linux binaries under systemd on an L4 GPU, with idle detection run from the Doorman server process rather than a timer on the GPU VM itself.
  • PointSav-LLM — The planned vendor-tier specialist AI model for substrate-sovereign SMBs — Tier 3 of the Four-Tier SLM Substrate Ladder, built by continued pretraining of the OLMo 3 32B base model.

Entity extraction and the training loop

How the platform turns use into training signal — the mechanism behind "the platform learns from how it gets used."

  • Tiered entity extraction architecture — The entity extraction pipeline runs three tiers per document: Tier 0 fast extractive detection via GLiNER, Tier A generative fallback via OLMo, Tier B GPU enrichment.
  • Elastic Compute #1 nightly LoRA training pipeline — Nightly two-phase pipeline on Elastic Compute #1 that rebuilds the deployment DataGraph and trains LoRA adapter weights for the workspace language model.
  • Learning DataGraph — Training loop turning operator interactions into training signal — trajectory capture, an apprenticeship queue, and a GLiNER→OLMo distillation pipeline that generates entity-extraction DPO pairs.
  • Knowledge flow: training loop and ontological DataGraph — Quality framework for the Totebox knowledge flow, asking whether LoRA adapters measurably improve the model and whether the DataGraph is an accurate ontology.

See also

  • How It's Built — the three-ring build that makes this boundary structural
  • Building Blocks — AI-adjacent mechanism concepts, including the AI-optionality article above
  • Platform Services — the per-service pages, including the AI service itself
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 →