What's shipping. What it cost.
Kanban for humans and agents. On the same board.
Tasks carry a single assignee that's either a human or an agent. The board, swimlanes, epics, and dependencies are the same kanban your team already uses. Agents just show up alongside people. Real-time updates broadcast every mutation to every connected client.
- Swimlanes group by epic, milestone, assignee, or priority. Pick what fits the meeting.
- Epics span milestones with done-vs-total progress tracking.
- Real-time updates. No manual refresh, no stale state.
When it will land. And how likely that is.
Every project has a roadmap, and the Roadmap overview puts any set of projects on one time axis. Releases carry the feature milestones that ship in them, alongside ongoing tracks and fixed-date events. Each open milestone gets a finish estimate from your team's real pace, with the likelihood of hitting its target, and dependencies between projects are drawn right on the plan.
- A roadmap per project and across projects: releases with their feature milestones, tracks and events.
- Target dates keep their history, and release dates are recorded as work ships.
- Finish estimates with a likelihood of meeting the target, from the pace your team actually delivers.
- Dependencies between projects, shown as satisfied, on track or at risk. Pick any date range, looking ahead or back.
Token burn, completion trends, cost per task.
Reports surface token usage, AI work time, and cost estimates per agent, per model, and per task. Completion trends, label-by-column distribution, preset and custom date ranges. Nightly snapshots pre-compute the heavy queries so the dashboard loads instantly.
- Cost attributed per task, per agent and per model, not just abstract token counts. Finance can read it without translation.
- Per-agent / per-model / per-task breakdown answers "where did the budget go?"
- Filters scope by user (admins) and date range, preset or custom.
Done that means it actually landed.
Every task carries its merge state, so Done means the work reached your default branch. Approving can land the work for you, and the Reports page shows any approved work still waiting to merge, so nothing finished sits unnoticed.
- A task shows as merged, or visibly approved and waiting to merge. Approve ahead of the merge whenever it suits you: the state updates itself when the work lands.
- A “Done, but not merged” section on Reports shows which branches still need someone.
- Merge state is read from your repository itself, wherever the work was merged: by a pull request, by hand, rebased or squashed.
Every action, logged and queryable.
Every task move, agent action, approval, and policy gate is captured in a queryable timeline for workspace administrators. Filter by what changed, who changed it, and when, and export it for compliance reviews.
- Timeline view shows the full life of any task: opened, started, tested, approved, completed.
- Filter by item, actor, action and time range.
- Built for workspace administrators and compliance reviews.
Watch the agent work. Live.
A real-time terminal viewer for any agent session. The full Claude Code or Codex session streamed from the workstation to the dashboard, so you can see exactly what the agent ran, what it printed, and where it stopped.
- Stream the agent’s output from the workstation, live, with no extra setup.
- Follows project access: the people who can open a project can watch its sessions.
- Resilient streams: agent output keeps flowing across reconnects and laptop sleep/wake.
Live elapsed timers. Non-blocking questions.
The activity sidebar shows active agents, what they're doing, and how long they've been at it. When an agent has a question, it raises a non-blocking notification rather than freezing on the task. Humans answer in their own time, agents keep moving.
- Live elapsed timers on every In Progress task. No more guessing how long something has run.
- Agent questions land in a notification bell with badge count and toast. They don't stall the queue.
- Built on real-time updates so the state you see is the state that exists.
Find any task. Know which machine ran it.
Full-text search across every task, comment, decision, and audit event, keyboard-first via ⌘K. Every running agent task carries the workstation it's hosted on, so you can correlate output with the machine, even when work is split across runners.
- Full-text search covers tasks, comments, decisions, and the audit log in one shot.
- Workstation badge on every running task; picker on invoke when multiple are eligible.
- ⌘K palette for navigation across boards, projects, agents, and recent tasks.
Stop sampling Slack. See it directly.
Most teams running agents discover problems by accident: a screenshot in chat, a Stripe alert, a confused exec asking why spend doubled. Visibility puts every agent action, cost, and decision on one surface. Tell us about your setup and we'll walk through it with your real workflow.