Sessions

A session is one conversation with an agent or one run of an assignment — and the complete record of it. Every thought, tool call, and decision streams into the session as the agent works, and stays there afterward. Transparency isn’t a report the agent writes about itself; it’s the work itself, visible.

That record is what makes delegation auditable. When a number in a report looks off, open the session and read what the agent actually did: which integration it queried, what came back, what it decided along the way. Six months later the session is still there, and it answers the question the same way.

A run, step by step

Take the Monday-morning pipeline report from the weekly report guide. At 6:00 AM the schedule fires, and a new session appears among the agent’s sessions with a live indicator. Open it and the work streams in: the agent reasons about the job, queries the CRM integration, works through the data, and produces the report — each step visible as it happens.

Partway through, you notice it is counting deals that closed last week. You type a correction into the composer without stopping the run; the message is queued, and the agent folds it into the work in progress. The finished report lands as a work product whose card links back to this session — the provenance of the artifact is the transcript that produced it.

Watching and steering

A running session shows a live indicator, and you stay in control while it runs: the stop button halts generation, and the composer stays open — a message sent mid-run is queued, so you can steer without waiting. For small corrections, steering mid-run beats stopping and restarting: the agent keeps its momentum and takes your note on board as it works. A session that ended unexpectedly is marked and offers Resume session, so an interruption picks up where it stopped.

Working with sessions

Sessions live in the sidebar; rename or delete them from the session menu, and search across them with ⌘K — handy when you remember the topic (“the churn analysis”) but not which agent or which week it belonged to. If a conversation turns out to be a recurring need, Make recurring distills it into a draft assignment — name and instructions pre-filled from what the agent actually did — so the session that got the work right becomes the template for repeating it.

Private and shared

Sessions are private to you until you share them. Share with Team makes a session visible to workspace members you give the URL to — they can read it, and fork it to continue on their own, but only you can post to the original. Forking is the natural handoff: a teammate takes your session as a starting point and continues in their own copy, while your record stays exactly as you left it. A sidebar toggle shows or hides teammates’ shared sessions in your list, so you can browse the workspace’s shared work or keep your sidebar to your own.

Multi-agent work

Agents can delegate: a session may spawn child agents, which appear inline as cards — the child’s name, its task, and its status — with an Open link to the child’s full transcript. The parent session stays readable because the detail lives one level down: you can see that research was delegated and how it went, and open the child only when you want the step-by-step. Mention another agent by typing @ in the composer to bring it into the conversation directly. Delegation is bounded by the collaboration guardrails, so an agent’s reach stays within the limits you’ve set.

Wakeups

An agent can schedule its own follow-up — “I’ll check the deploy again in an hour.” A pending wakeup shows as a pill on the session with the time, and you can cancel it. Wakeups suit the agent’s own short-horizon follow-through: checking whether something it kicked off has finished, looking again once new data should exist. For work you want repeated, use an assignment instead — assignments carry a schedule, pause controls, and a per-run audit trail, where a wakeup is a single deferred next step.