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

# AI Studio

> Operate Tuturuuu AI Studio policies, credentials, traces, evaluations, and workspace credit metering.

AI Studio is the workspace-scoped development surface at
`https://ai.tuturuuu.com`. It is a registered satellite app and uses the same
workspace session, permissions, settings, and billing context as other Tuturuuu
apps.

## Rollout controls

AI Studio is disabled by default. Access requires all of the following:

1. the root global Studio policy is enabled;
2. the workspace policy resolves to enabled;
3. the requested model is enabled globally and granted to the workspace;
4. the caller or AI-only key has the required Studio permission and model
   scope; and
5. the workspace has enough AI credits and is within its request and budget
   limits.

Root administrators configure global defaults and workspace overrides in
Infrastructure → AI Studio. Workspace administrators manage prompts, agents,
evaluations, keys, retention, and model restrictions from AI Studio.

## AI-only keys

Studio keys use the `ttr_ai_` prefix. The plaintext key is revealed once; only
its SHA-256 digest is stored. A key is a workspace service credential, not a
human session, and it cannot authorize non-AI Tuturuuu APIs.

Keys can be limited by environment, model, expiry, request rate, and credit
budget. Rotate or revoke a key immediately when its value may have been
exposed. Never write plaintext keys to logs, database columns, issue trackers,
or committed configuration.

## Metering lifecycle

Every model call follows one transactionally guarded lifecycle:

1. authenticate the session or AI-only key;
2. resolve the global, workspace, plan, and key policy intersection;
3. reserve the maximum permitted credits;
4. execute the provider call;
5. persist the run and trace metadata; and
6. settle exact provider usage and release unused credits.

Provider failures and aborted streams still settle billable usage. Runs record
model, key, prompt or agent version, latency, first-token latency, token or
media units, provider cost, billed credits, status, and a stable request ID.

## Trace retention

Run metadata is retained for 365 days by default. Prompt content, model output,
tool arguments, and tool results are not captured unless the workspace
explicitly enables content capture. Captured content defaults to 30 days and
must be redacted before persistence.

Customer AI content is not used for general-purpose model training by default.
Provider-specific no-training and data-control options should be enabled when
the provider supports them.

## Curated tools

Agents can use only tools declared in the root tool catalog and explicitly
enabled for the workspace. Tools must enforce workspace scope and normal
Tuturuuu permissions. Arbitrary HTTP requests, undeclared data access, and code
execution are not supported.

## Local verification

Apply and test the private-schema migrations before running the app:

```bash theme={null}
bun sb:up
cd apps/database
node scripts/run-supabase.js test db supabase/tests/ai-studio-foundations.sql
```

Then run the focused checks:

```bash theme={null}
bun --filter @tuturuuu/ai-studio test
bun --filter @tuturuuu/ai-studio type-check
bun --filter @tuturuuu/ai-studio build
```

Keep the global kill switch disabled outside dedicated test workspaces until
security, billing, privacy, and legal publication reviews are complete.