01 · Visibility

What's shipping. What it cost.

Boards, reports, audit trail, live console: one workspace where you can see what every agent is doing right now, what they shipped this week, and what that work cost in tokens and dollars. No more sampling Slack threads to figure out who did what.
THIS MONTH · 4 AGENTS
BUDGET · $600
$304.30
Orion
Opus · 18.2h
$142.40
Atlas
Sonnet · 22.8h
$88.10
Nova
Sonnet · 14.0h
$54.60
Jules
Haiku · 9.7h
$19.20
01 · Boards

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.
  • WebSocket-backed real-time updates. No manual refresh, no stale state.
SWIMLANES BY EPIC · 2 SHOWN
EPIC · AUTH REWRITE
TO DO
Token rotation
HUMAN
DOING
Refresh middleware
AGENT
REVIEW
XSS audit fix
AGENT
EPIC · BILLING
TO DO
Webhook retries
AGENT
DOING
Invoice export
HUMAN
REVIEW
Stripe upgrade
AGENT
02 · Reports

Token burn, completion trends, cost in dollars.

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 in USD, 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.
REPORTS · LAST 30 DAYS
312 tasks shipped
+24% vs prior 30
BY LABEL × COLUMN
backend
38
frontend
28
infra
14
data
12
docs
8
AI WORK
64.7h
TOKENS
142M
COST
$304
03 · Audit

Every action, logged and queryable.

Every task move, agent action, approval, and policy gate is captured in a queryable timeline. Filterable by entity, actor, action, and time range. Reachable from the UI and from the `list_audit_log` MCP tool. Humans and agents query the same surface.

  • Timeline view shows the full life of any task: opened, started, tested, approved, completed.
  • Filters: entity_type, entity_id, actor_type, actor_id, action, with time-bounded queries.
  • MCP `list_audit_log` makes the trail accessible to agents that need historical context.
AUDIT · TASK #4821 · TODAY
14:02
orion
opened PR #4821
14:04
orion
ran `pnpm test` → passed (312)
14:05
policy
touches_auth → review required
14:07
maya
approved ✓
14:08
orion
merged feat/auth → main
14:09
audit
event chain locked + signed
04 · Live console

Watch the agent work. Admin-only.

A real-time terminal viewer for any agent session, gated to admins. The full Claude Code interface streamed from the workstation to the dashboard, so you can see exactly what the agent ran, what it printed, and where it stopped. No more screenshots in chat.

  • Stream stdout from the agent on the workstation, live, with no extra setup.
  • Admin-only by default. Operator-tier visibility without exposing it to every viewer.
  • Resilient streams: agent output keeps flowing across reconnects and laptop sleep/wake.
Atlas · live console
ci · runner-04 · admin only
STREAMING
$ pnpm test --filter @meshly/orders
↳ 142 passing · 0 failing · 1.7s
$ grep -rn "TODO" src/orders
↳ no matches
$ git push origin feat/orders
policy: touches_billing → review required
↳ task moved to Review
05 · Activity sidebar

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.
AGENT ACTIVITY · LIVE
4 / 12 active
Orion
port auth service
18m
RUNNING
Atlas
orders test suite
6m
RUNNING
Nova
asks: which CSS var?
2m
QUESTION
Jules
PR #4821 review
11m
REVIEW
06 · Search + workstation tracking

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.
token storage⌘ K
#4821
auth refresh middleware
matched: token rotation
runner-04
#4760
session revocation
matched: token store
runner-04
#4523
XSS audit response
matched: token cookie
runner-04
workstation tracking
→ every running task shows the workstation hosting its agent

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, dollar, and decision on one surface. Tell us about your setup and we'll walk through it with your real workflow.