Data boundary
Prompts, responses, model files, traces, and operational logs are designed to stay inside customer-controlled infrastructure when Clustra is deployed to that boundary.
Clustra is designed for environments where security teams need architectural control, evidence, reviewability, and customer-owned retention from the first deployment.
The platform is shaped around the questions that decide whether private AI can move beyond a prototype: where data goes, who can access models, what gets logged, and who owns the evidence.
Prompts, responses, model files, traces, and operational logs are designed to stay inside customer-controlled infrastructure when Clustra is deployed to that boundary.
Access is designed to align with customer identity, groups, team boundaries, and role-based operating policies.
Applications and agents reach models through one governed entry point where approved model access and rate policy can be enforced.
Model actions, gateway traffic, request traces, and operational changes create reviewable evidence for security and compliance teams.
Model frontends stay private behind the platform boundary instead of being exposed as separate public surfaces.
Secrets are treated as runtime configuration owned by the customer environment, not public website configuration or hardcoded assets.
A review should connect each control to an owner, evidence source, and deployment assumption. This matrix is representative; the pilot version is mapped to the customer's environment.
| Control | Clustra provides | Customer owns | Review evidence |
|---|---|---|---|
| Identity and SSO/RBAC | Maps users, teams, applications, and model access to the approved enterprise identity path. | Identity provider, group ownership, role approval, and production access decisions. | Access-policy map, reviewer owners, approved model list. |
| API keys and access policy | Centralizes gateway access, model routing, rate policy, and team attribution. | Key issuance process, consuming applications, revocation policy, and exception approvals. | Gateway policy, key status, route history, policy outcomes. |
| Secrets handling | Treats secrets as runtime configuration within the customer environment. | Secret store, rotation process, break-glass access, and audit owner. | Secret references, rotation owner, deployment change record. |
| Logs, traces, and retention | Produces request traces, usage attribution, audit events, and runtime health signals. | Retention target, log access policy, review cadence, and legal hold requirements. | Trace sample, audit event sample, retention mapping. |
| Redaction and output handling | Supports review of policy outcomes such as allowed, redacted, masked, or blocked. | Sensitive-data rules, application handling, and reviewer signoff. | Policy outcome, redaction event, application owner. |
| Network isolation | Keeps model frontends behind the gateway and maps the approved consumer-to-runtime path. | Network zones, ingress path, firewall rules, and incident handoff. | Network path notes, gateway boundary, health and incident signals. |
We will map the data boundary, access model, audit story, and operating evidence before a pilot runs.