Your agents. Your infrastructure.
Your data.
Run your firm's agents in your cloud or on-prem, inside a security boundary your review team can sign off on.
Runs where your data lives
Deploy the full Introspection stack inside your VPC with Terraform and Helm. Encryption keys in your own account, private networking, and a zero-secrets architecture: Workload Identity, IRSA, or Managed Identity instead of passwords.
Outbound only
Every run, fully isolated
Agents execute in disposable, locked-down sandboxes that can't reach your network or your secrets, and recover cleanly when things fail.
Hardened sandboxes
Every task runs in an isolated, disposable sandbox built from a commit-pinned image. Durable state and artifacts are preserved outside the sandbox.
Default-deny egress
Agents reach only the hosts you allow. Every other outbound request is rejected at an Envoy gateway. The sandbox has no open internet.
Edge credential injection
Provider keys never enter the sandbox. A short-lived token is swapped for the real credential at the gateway edge, just before the request leaves your network.
Durable execution
Every task runs as a journaled, resumable workflow that can recover from restarts and continue from durable state.
Your data stays yours
Dedicated deployments keep runtime data in your cloud account, protected by keys you control and scoped for targeted erasure.
Single-tenant data plane
Run a dedicated data plane in your cloud account or data center for residency, isolation and control.
Encryption you control
Protect data with dedicated KMS keys in your account, with control over access, rotation, and revocation.
Per-user memory & erasure
Keep memory scoped to each user and support targeted erasure without affecting the rest of the deployment.
Bring your own ClickHouse
Point Introspection at your existing ClickHouse cluster, or let us deploy one in your VPC. Your OpenTelemetry trace data stays exactly where you want it.
Wired into your firm
Tie every agent, key, and action to your identity provider and your spend, with a full audit trail behind it.
SSO & scoped access
Authenticate through OIDC and apply scoped role-based access across agents, runtimes, integrations, and data.
Application federation
Embed agents in your client-facing apps via SPA, service-account, JWKS, or native apps, and federate your clients' users with standard token exchange (RFC 8693).
AI gateway & budgets
Route LLM traffic through your own Anthropic, OpenAI, and Gemini accounts, with per-org budgets enforced at the edge and real-time usage analytics per task and agent.
Audit logging
Export attributed audit events across administrative and runtime actions, including staff impersonation.
Deploy your way
Run in your cloud or on-prem while operating every runtime through the same platform.
- Data plane in your VPC on AWS, GCP, or Azure
- Client data never leaves your VPC
- BYOK, BYO ClickHouse, your own KMS key, private networking
- S/M/L sizing from dev to high-throughput
- Terraform + Helm + ArgoCD GitOps
- Control plane in your account
- Auth, SSO, and member management
- Billing and usage tracking
- Deployment provisioning and GitOps
- Integration credential storage
The controls a security review expects
Attributed audit logging, encryption at rest and in transit, least-privilege access, and full impersonation tracking, with the architecture to back them. Your data and prompts are never used to train models.