Identity
SSO direction, role mapping, workspace membership, and human ownership for each run.
Governance
Enterprise agent adoption depends on permission, review, proof, and rollback. The governance plane is designed to make agent behaviour visible and bounded.
Controls
Agents should not gain broad access because they are useful. They should receive specific access because the task, user, environment, and approval path justify it.
SSO direction, role mapping, workspace membership, and human ownership for each run.
Human checks before PR creation, deployment, sensitive commands, external calls, or stateful changes.
Scoped credentials, masked logs, non-model-visible secrets, and clear separation between instruction context and execution context.
Record prompts, commands, file changes, tool calls, tests, screenshots, decisions, and handoff artefacts.
Allow only the systems required for a run, with stronger boundaries for production, client, and regulated data paths.
Usage budgets, runtime limits, model routing, GPU allocation policy, and alerts for unusual activity.
Audit record