For healthcare teams

Control AI paths before sensitive workflows depend on them.

The metadata-minimized architecture is being built with later BAA and dedicated-deployment requirements in mind—without claiming compliance prematurely.

Working sandbox capture
For healthcare teams controls in the working console.Current interface evidence: Data path scoped · Rollout staged · Evidence retained. This sanitized capture contains no customer secrets or prompt bodies.
No prompt persistence by default
Tenant-bound provider credential encryption
Access, audit, incident, and risk-analysis foundations
In plain language

Design the AI path so later assurance does not require rebuilding the product.

Healthcare readiness is more than encryption or a badge. The service begins with minimized hosted telemetry, tenant-bound credentials, explicit workload/data context, and provider eligibility controls. A BAA, risk analysis, retention validation, workforce procedure, vendor review, and deployment boundary are still required before ePHI use.

The readiness outcomeA non-sensitive pilot can validate the control model now while keeping regulated production outside the boundary until administrative and technical prerequisites are complete.
For the operating team

Make every regulated dependency explicit.

Treat provider contracts, data class, region, retention, support, incident response, and deployment model as release gates.

What administrators configure
Workload classification

Require an explicit data class and prohibit regulated traffic from unapproved routes.

Provider boundary

Limit credentials and models to reviewed accounts, contracts, regions, and telemetry behavior.

Administrative gate

Document BAA, risk analysis, procedures, training, incident handling, and validation before ePHI.

What happens to each request
  1. 01
    Classify

    Use explicit workload and data-class context; never infer authorization from a model name alone.

  2. 02
    Restrict

    Limit eligible providers, models, credentials, and telemetry before the request can leave the gateway.

  3. 03
    Operate

    Run the tested rule in Observe, Shadow, or Enforce according to the approved rollout stage.

  4. 04
    Review

    Retain metadata evidence and administrative change history for authorized operational review.

See the working control

Calibrate local protection before enforcing it.

Versioned profiles govern prompt attacks before spend, sensitive output before release, and the tool names, types, and MCP hosts a model may use—without retaining schemas, arguments, or results.

  • Rendered by the real customer console and control API
  • Exercised with safe OpenAI- and Anthropic-compatible simulators
  • Sanitization gate rejects credential-shaped values and private owner email
Follow the operating workflow
Payload and tool safeguardsCalibrate local protection before enforcing it.

Versioned profiles govern prompt attacks before spend, sensitive output before release, and the tool names, types, and MCP hosts a model may use—without retaining schemas, arguments, or results.

Control surface

Useful on day one. Explainable on day one hundred.

Each control has an operating path, an owner, and evidence that can be reviewed without collecting prompt bodies by default.

01

Design for ePHI handling

Provider eligibility and telemetry decisions are explicit, but retention enforcement and regional/dedicated cells remain required work.

02

Keep keys customer-controlled

Customers bring provider credentials today. A customer-VPC data plane and customer-managed KMS options are not currently included.

03

Administrative readiness

BAA execution, risk analysis, policies, workforce procedures, vendor review, and validated operations are required before any HIPAA use.

Evidence, not assertions

Build evidence now without claiming compliance early.

The trust center separates implemented controls, deployment dependencies, unavailable capabilities, and assurance that still requires an independent review.

Review security boundaries and current status
  • Reason-coded policy, route, retry, fallback, and denial metadata
  • Bounded tool names, types, MCP hosts, and authorization outcomes—without schemas, arguments, or results
  • Provider-reported usage reconciliation for complete responses and supported terminal streams
  • Tenant-bound credential encryption and fail-closed tenant authorization
  • Signed, retryable administrative audit delivery with payloads and configuration snapshots excluded
  • Clear labels separating available controls from items that still require validation
Questions teams ask

Know the boundary before you deploy.

Clear answers for buyers, administrators, and security reviewers.

Can we send PHI through the hosted service today?

No. AI Gateway HQ does not currently claim HIPAA readiness or offer a BAA. Use only non-sensitive test data until contractual, administrative, and technical gates are completed.

Are prompt bodies retained?

The hosted gateway is designed not to persist prompt or response bodies by default. Provider retention and application logging remain separate customer review responsibilities.

Will customer-VPC deployment be supported?

It is an enterprise design path, not a generally available package. The deployment, update, support, and evidence boundaries require implementation and validation.

Start safely

See what the policy would do before it can block production.

Connect a provider credential, create a workload key, and begin in Observe mode. Move a tested rule to Enforce when your team is ready.

Start guided setup