# 03 — The workflows, and why this is the sgit showcase

The commission's third note: *"this is also a good example of the kind of companies and business models that can be built on top of sgit and encrypted vaults + Vault Apps."* This document is that argument, made concretely — and the workflows page is what makes the site *"more than a law summary."*

---

## 1. The pipeline exists — March 2026, the founder's own statements

The 29 March debrief records the exact workflow, already run: credit card statements shared into a vault by short token, an agent cloning it, **working inside the vault**, committing and pushing back, the human pulling and seeing exactly what changed — *"a genuine shared workspace, persistent and versioned across sessions."*

| The March workflow | This service |
|---|---|
| Statements as raw input | The same |
| Parse into a ledger | Parse into a **subscription inventory** |
| Agent works inside the vault, versioned | Unchanged |
| Shared by a short token | Unchanged |
| Output: an accountant-ready pack | **Output: a claim file per subscription** |

*"Only the destination changes… the novel work is the legal mapping and the claim file, not the plumbing."* And the April positioning brief already named the audience — people who send document bundles to accountants and brokers, *"folders that remember everything"* — and the economics: *"a serverless, low-cost business."*

## 2. The vault architecture — three stores, three rules

| Store | Holds | Rule |
|---|---|---|
| **The person's own vault** | Statements, the claim file, full responses, anything identifying them | *"A completed claim file is a concentrated dossier of one person's financial life"* — it belongs to them; the operator holds *"only what a live claim requires"* |
| **The public register vault** | Company rows, dates, verbatim replies (details removed), exit measurements, templates, parsers | **"The unit of the register is a company's behaviour, never a person's case"** — CC BY, re-pointable to a neutral domain at the split |
| **Per-provider parser workspaces** | The template for that provider, the known reply shape, the extraction workflow | *"One person works out how to parse one provider's export, and everybody after them gets it for nothing"* — **the crowdsourced asset is the parsers and the templates, not the data** |

## 3. The honest vault claim — publish the last row

| Property | True? |
|---|---|
| The client holds their own evidence pack and can take it elsewhere | **Yes** |
| Sharing with a specific party is a key rather than an account | **Yes** |
| The store cannot read it | **Yes** |
| Every change versioned — what was submitted when is answerable **in a dispute** | **Yes** |
| The agent reading the statements cannot see the contents | **No — it reads plaintext** |

*"Vaults buy portability and controlled sharing, not zero knowledge… the privacy claim for the processing step is operational (we do not retain it) rather than architectural (we cannot see it)."* Publishing that row is the estate's standing discipline — *"a page that names where its own approach loses is what makes the rest of it credible."*

**Which is why bring-your-own-model is the default**, inverted from the usual ordering: *"being the meter puts you in the request path"*, and the content here is bank statements. BYOM keeps the claim architectural; hosted-metered is the convenience option, priced per extraction, retention stated structurally. The consumption ledger already exists, generic on unit type by design.

## 4. The SAR workflow, with its constitution

The access request is the discovery engine — representative requests must be honoured, high refusal threshold, one month — with the ask-list ordered by claim value: **usage and access logs first** (converts a feeling into a record), then the sign-up record, consent records, billing history, correspondence, and **the terms in force at the time** (not today's website).

The one rule that keeps the mechanism alive, verbatim: *"Every access request is a genuine request for the person's own data, sent because they want it. It is never sent as leverage, never bundled with a demand, and never sent in a volume calculated to burden."* Merit is tested **before** the request; the decline rate is published. Authority to act is captured as evidence, not assumed. And the portability right is noted for volume: where it works it yields machine-readable output.

## 5. The showcase summary — for `sgit.ai` and the memory network

One paragraph the estate can reuse: a consumer service where **the client's file lives in the client's vault**, the operator is thin and serverless, the **shared asset is workflows in vaults** (parsers, templates), the register is **published data in a re-pointable vault**, metering is a generic ledger, the model is **BYOM-first because the meter costs the privacy claim** — and the whole thing was assembled from primitives that already existed: the March pipeline, the token gateway finding, the comparison-page discipline, the store-the-choices rule. **No new infrastructure was invented for this business.** That is the sgit business-model argument in one worked example.

---

This document is released under the Creative Commons Attribution 4.0 International licence (CC BY 4.0).