sgit newsroom v0.1.29 · snapshot 2026-09-24

Reading room · riskmandate.ai

On this page

Reading room / riskmandate.ai · raw text · live ↗

From riskmandate.ai, the page as fetched on 2026-09-25 · open the live page ↗Everything on this sheet is the source site's own text; the newsroom's chrome is outside it.

T10 — The two Voice Debrief use-case vaults, and a use-case axis on the library

Rendered from .claude/briefs/T10-use-case-vaults.md in the repository. The text below is that file. Source: https://riskmandate.ai/admin/work/T10/↗ · noindex · written by scripts/site/build-admin.mjs

From: docs/briefs/direction__use-case-driven-policies-and-the-prompt-workflow.md §4–5. Size: a day, after the agent that knows the Voice Debrief workflows has run the prompt. Touches: site/vaults/voice-debrief-web/, site/vaults/voice-debrief-whatsapp-n8n/ (new), site/vaults/index.json (a Use cases group), scripts/site/build-abp-pages.mjs (the group), vault.json (kind: use-case).

The task

Two vaults for two workflows of our own product, documented from the workflows as built: the web flow (upload, transcribe, infographic; audio and text sent through a model-routing service to several providers) and the WhatsApp flow through n8n (the measured n8n grant plus the messaging platform's bot scope). The lead's instruction is that the agent that knows the workflows runs MAP-A-GRANT.md and sends the two JSON files here; this brief packages them. This is the £500 workflow run on ourselves before it is run for a customer.

Constraints

Done means