Skip to main content
Version: Next

Agent Traffic Control (ATC)

Status: live. A public interactive demo runs at griff.run/atc, and a full 76-minute governed agent session is published with hash-backed replays at griff.run/audit.

Page updated 2026-08-10 against the live platform.

ATC routes every agent action through one governed path:

  1. Request — an agent asks to do work; the request is captured with an owner and boundary.
  2. Load context — GRIFF Brain retrieves the relevant memory, documents, decisions, and operating instructions.
  3. Evaluate — the policy engine determines what the agent is trying to do and which controls apply.
  4. Approve — sensitive classes (external sends, spend, credentials, production changes) pause for a named approver. Everyday work keeps moving.
  5. Execute — the agent performs the approved task with the capabilities available to it.
  6. Record — request, context, approvals, actions, outputs, and outcome are recorded as work happens.
  7. Review — managers, security teams, customers, and auditors inspect or replay the record when needed.

What ATC enforces out of the box

ControlBehavior
Governed routingNo ungoverned back doors; one path for every request.
Human approval gatesSensitive action classes pause for a named approver.
Shared operating contextClaude, ChatGPT, Gemini, Grok, custom agents, and MCP apps work from the same current state via GRIFF Brain.
Evidence by defaultReplayable, exportable records for reviews and audits.
Budget & usage controlModel calls attributed per workspace; spend is a governed input.
Deployment freedomThe same model runs cloud-connected, hybrid, or self-hosted.

Where you see it

  • Control Center — approvals, sessions, and usage in the customer workspace (app.griff.run).
  • Audit replay — the published evidence session at griff.run/audit.
  • Governed local runtime — on-platform agents call the Brain's MCP surface where every governed call receives a policy decision and an audit entry (see the MCP API reference).