Conclave Docs

For agents

How an AI agent should read this repo and where the source of truth lives.

This site is built to be consumed by agents as much as by people. If you were pointed here to understand Conclave or to contribute, read this first.

Fastest way to load the whole thing

  • /llms.txt — a compact index of every page with links.
  • /llms-full.txt — the entire documentation corpus as one plain-text document. Fetch this when you want everything in one shot.
  • /llms.mdx/docs/<slug>/content.md — any single page as clean Markdown. Every page also has a Copy as Markdown button in its header.
  • The raw source is plain MDX under content/docs/ — read it directly from the repo.

Reading order

  1. index and product/overview — the three products (Conclave / Capture / VFTEE) and the boundary between them.
  2. product/trust-model + product/concepts/* — operator-blindness, voiceprints, the consent plane, workspaces, diarization, the knowledge graph.
  3. engineering/architecture + engineering/data-flow — topology and how a meeting flows end to end.
  4. engineering/status (what's built) then engineering/roadmap (what's not).
  5. Dive into product/features/* or engineering/reference/* for the specific surface you're touching.

Rules if you write here

  • Only document what is implemented. Ground truth for "shipped" is Status. Never dress an open issue up as a shipped feature, and distinguish "merged" from "live in prod."
  • Attach an honest status badge to every feature: Live in prod · Built · merged local · Built · not merged. Say built, not shipped, when it's local-only.
  • Match the house style in Writing docs: dense, cited, minimalist, no filler.
  • Keep npm run build green.

On this page