> ## Documentation Index
> Fetch the complete documentation index at: https://docs.shamwari.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# What concurrent traffic looks like

> Six people asking six different things through one gateway, and the three different places their requests stop.

There is one code path. Every request runs the same six stages — authenticate,
scope gate, Ground retrieval, route, infer, sink — and what distinguishes one
caller from another is not which path they take but **where their path stops.**

<Note>
  **Interactive.** The [Shamwari traffic board](https://claude.ai/code/artifact/7788e014-745f-40cc-af16-b0c11c4effd6)
  runs this as a live board: six lanes, a pip per stage, and two switches — the
  AI Gateway credential and `MIND_AVAILABLE` — that change the answers. Source
  is `docs/multi-user-flow.html` in the repository.

  It is a simulation. Neither Core nor the gateway is deployed yet, and Ground
  is empty.
</Note>

## Three shapes a request can take

**Refused at the gate.** A `personal`-scope question — someone asking about
their own payslip — stops at stage two with **409
`scope_requires_local_inference`**, two stages before anything is embedded and
four before anything is generated. It is not downgraded to a general answer.
A downgrade would answer confidently while withholding the user's own data,
giving no signal that anything was missing.

**Served without a provider.** With Shamwari Mind available, the same question
takes a shorter path rather than a longer one: authenticate, scope, Ground,
stop. `/v1/ground/context` returns a system prompt and citations, and the
device generates the answer. No embedding is computed at the edge, because
embedding is inference. There is no sink row, because the gateway never sees
the answer.

That is what "routes to Mind" has to mean. Mind runs on the device, so it is a
client of the gateway, not a backend behind it.

**Answered on Cloud.** `platform` and `community` scope run all six stages. A
short question in Shona stays on the economy tier; a long question about a
statutory instrument escalates to standard. Both are open-weight models.

## Two gates on the training corpus

A conversation becomes Shamwari Mind training data only if both hold.

| Gate       | Asks                                                                                        | Fails when                                            |
| ---------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------- |
| Provenance | Does the licence of the model that **actually answered** permit training a competing model? | An unlisted or restricted model served — ❌ restricted |
| Ownership  | Was this the platform's data, or the user's own?                                            | The exchange was `personal` scope                     |

They are independent, and both are enforced at write time rather than filtered
at read time. A read-time filter is one forgotten `WHERE` clause away from
training on someone's payslip.

Provenance follows the model that answered, not the tier that was requested.
The two diverge whenever a request degrades to Workers AI, and whenever an AI
Gateway dynamic route substitutes a model — a dashboard edit, with no deploy
behind it. An unlisted model resolves to `restricted`: unlisted means nobody
has read its terms, and a lost training row is recoverable where a corpus that
has to be discarded is not.

## Breaking Cloudflare on purpose

The infer stage has three steps behind it: AI Gateway, then the provider
directly, then Workers AI. Every response reports which one answered, in
`inference_path`, so degradation is observable rather than assumed.

These fallbacks rot silently if they are never exercised. Break the Gateway
credential deliberately once a month, and watch the path move.


## Related topics

- [Two rules that must not be broken](/rules.md)
- [How we describe it](/language.md)
- [An AI companion that refuses to send your data away](/index.md)
- [Three data scopes, not three tiers](/scopes.md)
- [Architecture](/architecture.md)