Policy before inference. Evidence after.

Set organisation-scoped routing, optional budgets, and review what was used and what changed. The same rules apply to every request, whichever consumer sent it.

D×E routing policy

Set data sensitivity (D-class) defaults for messages and files, assign provider environment classes (E-class), and block incompatible requests before inference.

Explore data routing →

Budgets

Optionally cap spend per member or API key and per provider. Usage stays uncapped until you set those ceilings. Steinkauz AI does not include inference credit.

Explore Budgets →

Usage and audit visibility

Inspect inference activity across every consumer, review configuration audit events for policy and provider changes, and trace administrative actions.

Explore audit visibility →

Routing

Data routing policy

Choose which provider environment classes may handle each data sensitivity level. Incompatible chat and API requests are blocked before inference.

Interactive demo. No data is saved.

Docs

Data sensitivity defaults

Message and file sensitivity can be configured separately. When a request includes a file, Steinkauz AI uses the stricter effective sensitivity.

Default sensitivity for message content in chat before routing is evaluated.

Pre-selected sensitivity for uploaded files. Attachments can raise the effective sensitivity above the message default.

Provider

Each provider has a provider environment class (E-class). Pick one to simulate a request.

Simulate a request

Choose whether the request includes a file attachment to see how effective sensitivity is computed.

Effective sensitivity: D0: Public

D×E routing matrix

Configure which provider environment classes may handle each data sensitivity level. Toggle cells to allow or block combinations.

AllowedBlocked
Data sensitivityE0E1E2E3E4E5
D0
D1
D2
D3
D4
This request would be allowed at D0: Public.

Chat and the API share this matrix. API keys also carry a data-sensitivity default and a minimum provider environment. A request may raise sensitivity; it cannot lower the key floor.

Budgets

Optional ceilings, not included credit

Cap cost and/or tokens per member or dedicated API key, per provider. Empty means uncapped. Remaining 0 blocks further requests on that provider.

  • Caps are optional and per member or dedicated API key × provider, not a single global limit, and not included inference
  • Cost and token ceilings can be set independently; skip a field and that track stays uncapped
  • Inherit keys follow the creator’s member budget; dedicated keys have their own ceilings
  • Existing tools, custom software, and the built-in chat all share the same rules. Caps reset each UTC calendar month
Settings → Budgets
September 2026

Optional ceilings per member or dedicated API key, per provider. Empty fields stay uncapped. Remaining 0 blocks further requests on that provider.

Anthropic

Maya Chen

Member

On track
Cost ($)$58.00 / $200.00
Tokens in1.2M / 3.0M

Tom Weber

Member

Low remaining
Cost ($)$68.00 / $80.00
Tokens in410K

Uncapped

billing-bot

Dedicated API key

Exhausted
Cost ($)$50.00 / $50.00
Tokens in820K / 1.0M

Azure OpenAI

Maya Chen

Member

No cap set
Cost ($)$12.40

Uncapped

Tokens in240K

Uncapped

Preview only. Owners and admins configure live budgets in the app under Settings → Budgets. Caps reset each UTC calendar month.

Audit

Audit built in

Two complementary surfaces: AI inference activity and configuration changes.

Quick metadata shows provider, model, tokens, response time, and cost for this reply.

Per-message transparency

See which model you used, what it cost, and inspect metadata on every reply. Then follow the full trail in searchable activity history.

Click the info icon for quick metadata on a reply.

AI inference activity

  • Per-message metadata in chat: provider, model, tokens, cost, latency, and quick routing context
  • Dedicated activity page for searchable requests across chat and API with API-key attribution
  • Step-level drill-down into model calls, timing, cost, and exportable history
  • Unified usage and cost visibility for reconciliation and review
Activity details

Every inference request, whether chat or API, appears in a searchable activity log with drill-down detail.

Chat
SuccessUser messageD2: ConfidentialE3: Private cloud
Modelclaude-opus-4-6
ProviderAnthropic
Tokens1,650
Cost$0.00234
Duration2.3s
Steps3
Request IDreq_8f2a…c91d
Policy decision
Allowedpde_8f2a…c91d

Quick metadata is available per message in chat. Open Settings → Usage for the full activity page with filters, export, and step-level drill-down.

Filter by source, model, API key, or routing class. Inspect model steps, timing, cost, and the policy decision recorded for the request.

Configuration audit log

Every meaningful policy or provider change leaves a trace for review.

Routing policyToday, 09:14

Blocked D3: Restricted → E1: Public managed after matrix update.

Data sensitivityYesterday, 16:42

Default file sensitivity changed from D1: Internal to D2: Confidential.

BudgetsYesterday, 11:08

Optional cost cap set for Alex on Azure OpenAI.

ProviderMon, 08:55

Azure OpenAI provider environment class updated to E3: Private cloud.

Routing, provider, budget, and membership audit logs are available in organisation settings.

Configuration audit

  • Routing policy audit for matrix changes, blocked routing attempts, and sensitivity downgrades with reason
  • Budget audit for cap edits on members and API keys
  • Provider audit for creation, updates, deletion, and environment-class changes
  • Administrative audit for membership and billing-sensitive organization changes

Govern AI without losing agility

Set policy once. Apply it to the tools you already run, the software you build, and the included chat.

Contact SalesRead the docs