IntSen

Platform

One governed gateway.
Five layers of accountability.

IntSen is a control plane around the model traffic your applications and agents generate. Your agents keep running where they run today; IntSen governs the calls they route through its gateway.

Book a live demoSee how it works

Control

Every agent signs in with its own OAuth client and belongs to a registered use case with named owners. The gateway checks the client, use case, provider, model and data class before a call leaves your network.

Model access by agent

Which agents may use which models
AgentData classgpt-5.4-minigpt-4.1-minigpt-5.4
Fleet Service Advisorconfidentialallowedalloweddenied
Support Copilotinternalalloweddenieddenied
Contract Q&Arestricteddenieddeniedallowed
Explore control

Illustrative product scenario — synthetic data

Capabilities

Explore the platform

AI Gateway

Every governed model call starts here.

The IntSen AI Gateway is the single entry point for your applications' and agents' model calls: it authenticates the caller, checks what it may use, applies your controls and records the result.

Learn more

Guardrails

Make AI policies enforceable—not just documented.

IntSen Guardrails check governed model calls for prompt injection, personal data, secrets and harmful content, plus rules you write yourself—and record, mask or block according to your settings.

Learn more

Agent tracing

Understand the decisions behind every governed turn.

IntSen rebuilds what your agent did—conversations, turns, model calls, the tools the model asked for and the results it got back—from the traffic that passes through the gateway. No tracing SDK required.

Learn more

Evaluations & compliance

Don't just monitor AI. Measure how well it performs.

Score real turns with live evaluations, gate releases with golden tests from your CI pipeline, and review completed turns with configured compliance assessments—each with its own purpose and timing.

Learn more

Spend management

Know the cost of every turn—not just the monthly bill.

IntSen costs every governed request and rolls it up to the turn, agent, use case and team—then enforces the budgets and per-turn limits you set.

Learn more

Observability & audit

Evidence for every governed call.

IntSen keeps request and usage records, policy verdicts, turn records and evaluation results in one place—with operational metrics, logs and alerts to run it with confidence.

Learn more

Architecture

Customer runs. IntSen governs.

Every model call passes one governed door. The gateway is the source of truth: turns, tool calls, cost and quality are all derived from the traffic it sees.

  1. 01Resource RegistryUse cases, agents, evaluations, models and providers declared in YAML—validated, approved and versioned.
  2. 02AI GatewayThe single entry point: identity, model access, guardrails, budgets, routing and recording.
  3. 03GuardrailsInput, output and task-level checks with record, mask or block.
  4. 04Task trackingTurns and steps rebuilt from gateway traffic, with end-of-turn detection.
  5. 05Metering & budgetsCost per request, rolled up and enforced per turn, agent and use case.
  6. 06Evaluations & complianceLive scores, golden tests from CI, replay and post-turn assessments.
  7. 07ConsoleOne place for owners to see traces, quality, guardrails, compliance and spend.

Availability

Where IntSen is today

IntSen is in its first release and available to enterprises through pilots. The first release supports OpenAI models. These items are on the roadmap and are not part of the first release.

  • NextAzure OpenAI and Anthropic providers
  • NextOwners create and change resources from the Console
  • LaterGovernance control checks and an auditor evidence export
  • LaterOptional OpenTelemetry enrichment for steps the gateway can't see
  • LaterChargeback and invoice reconciliation
  • LaterRunning golden tests from the Console, on a schedule

Ready to make your enterprise AI accountable?

See how IntSen can help your teams govern access, safety, quality and spending across the AI applications and agents you already run.

Book a live demoDiscuss an enterprise pilot