Drive the agent¶
A live project runs an autonomous loop: the
agent proposes experiments, writes code, schedules runs, and analyzes results.
You stay in control of that loop from autolab status.
Where am I?¶
Shows the project at a glance — the agent state (live or paused), attached nodes, experiment counts, and the experiment you're in. It also prints the project's dashboard link; the browser is where you see what the agent is actually doing right now.
Talk to the agent (browser)¶
The dashboard's Chat tab is a conversation with the research agent itself: ask what it tried and why, what a failure means, or tell it to change direction — "stop tuning the LR, try a different tokenizer". It has the project's full history in context.
Chat is browser-only — there's no CLI equivalent. The CLI's steering controls are the dials below.
Start, pause, stop & resume¶
autolab start # start the agent (first start takes the climb live); resume after a pause
autolab pause # pause the loop; queued work waits, the agent stops acting
autolab stop # cancel dispatched work and release rentals; restart with start
autolab resume # resume a live climb's loop (start does this too)
autolab say "focus on the tokenizer next" # send the agent a steering message (the web chat's channel)
The first autolab start takes the climb live: it seeds the baseline from
your code (or lets the agent write it for an empty climb) and starts the
autonomous loop. After that, start resumes a paused loop. Use autolab say to
steer the running agent; the message lands in its context for the next step.
Project status vs agent status
These are two different things. The project status is a lifecycle:
setting_up → active (taken live) → paused/stopped/completed. The agent
status is what the loop is doing right now: running, idle, paused,
needs attention, or no llm. A project stays active while its agent is
paused — that's why autolab projects and autolab status show both, and
the dashboard card reflects the agent, not the lifecycle.
Pausing is the safe way to make changes — edit settings, adjust the queue, or reassign keys — without the agent acting mid-change.
pause lets current experiments finish and releases idle rented compute. Busy
rentals are released when those experiments finish, with billing continuing until
release. stop cancels dispatched experiments and releases rentals. Both keep
queued work, code, results, and history; your own machines remain attached.
A stopped climb stays stopped across server restarts until you start or resume it.
Automatic idea generation (autogen)¶
autolab status autogen # show the current agent + ideas state
autolab status autogen on # let the agent propose new experiments on its own
autolab status autogen off # only run what you queue
With autogen off, the agent still codes, runs, and analyzes — but it only works through experiments you submit. Turn it on to let it explore the search space autonomously. This is the core human-in-the-loop dial: tighten it when you want a hand on the wheel, loosen it to let Autolab run.
Queue your own work alongside the agent with submit, and
watch what it does on the dashboard (autolab open).