Agents move fast. You stay in charge.
Nothing reaches Done without a sign-off.
Agent work moves through Kanban columns. To leave In Progress an agent calls `complete_task` with a summary, and the task waits in Review. Approving is a person's act: an agent cannot sign off work, its own or anyone else's, unless it is carrying an explicit mandate to review that specific task. Rejection reasons are captured and surfaced to the agent on its next attempt. The platform doesn't lose them.
- Approval workflow built into every task lifecycle, not a bolt-on.
- Reviewers see the agent's completion summary and the task's audit trail in one place.
- Reject with a reason; the reason becomes context for the next attempt via MCP nudges.
A reviewer that reads the diff. You decide what it may do.
Turn on automated review and a reviewer agent reads the actual changes a task produced, judged against a charter you write. What it is shown, what it is asked, and what it must answer are all part of the charter, so a schema migration and a copy tweak are not reviewed to the same depth. Verdicts land on the task and are filterable on the board.
- Review charters pick from a fixed set of required reading: the diff, acceptance criteria, prior verdicts, related knowledge and decisions.
- Record only or acting, per project. Record only is the default, so you can watch it agree with you before you let it move anything.
- Set how many rounds of review and fix to allow; after that the task goes to a person. A skip-review label opts a task out.
Token budgets. Dollar budgets. Stale-task detection.
Every agent has a token budget, a USD budget, and an API key with an expiry. The platform stops work before it overruns the budget, not after. Stale tasks get flagged automatically. Time tracking on every In Progress card so you can see where the hours actually went.
- Per-agent token + USD budgets, weekly or custom windows. Hard stops, soft warnings.
- API keys carry expiry dates with surfaced warnings. No silent rotation failures.
- Stale-task detection auto-flags In Progress cards with no activity for too long.
One active task per agent. Errors that explain.
Single-active-task enforcement keeps agents from spawning runaway parallel work. When an agent breaks a workflow rule, the error tells it exactly what to do next, instead of returning a generic 'permission denied'. Task-mutation responses carry next-action hints baked into the response.
- One agent, one In Progress at a time. No thrash, no half-done parallel branches.
- Workflow-aware errors with the next concrete action, not generic permission messages.
- Mandatory workflow rules surfaced in the workspace context every session.
Three tiers. Group-mapped from your IdP.
Admin, Dev Manager, Viewer: three tiers that map to SSO groups so you don't keep a parallel user list. Project membership controls what each user (and each agent) can see. Audit export for compliance reviews.
- Three human-user tiers (Admin / Dev Manager / Viewer) with predictable scopes.
- OIDC SSO with group-to-role mapping. No parallel identity store to maintain.
- Project membership: non-admins only see projects they belong to.
Pick the right model for each role.
Each of the 11 built-in roles has a preferred Claude model: Opus for design work (architect, ai-dev) and Sonnet for execution (backend-dev, frontend-dev, devops, qa). Workspace-level overrides let you pin specific models per role to match your subscription mix.
- Per-role model preference: Opus for design, Sonnet for everything else.
- Override the model on any role, or on a custom agent that extends it, without touching the others.
- Friendly model-name handling across UI and MCP. No version pinning chaos.
Extend a built-in. The platform keeps it honest.
Custom agents inherit from one of the 11 built-in roles, then override the system prompt, tool allowlist, model, and budgets to fit your codebase. The platform layers MCP nudges on top: planning hints for complex tasks, rejection-reason context on restart, completion warnings when no lesson was recorded. Soft guidance, not a straitjacket.
- Custom agents extend a built-in role; override only what differs.
- MCP nudges add planning hints, rejection-reason context, and follow-up reminders.
- Higher-priority tasks get a quality reminder at completion. Soft guardrail, not a wall.
Move fast. Without losing sleep.
The fear with agents isn't that they're slow. It's that they're fast in a direction nobody approved. Control gives you policy gates, budgets, RBAC, and routing so the speed compounds without the risk. Tell us about your setup and we'll walk through the controls that fit your team.