What Agent is
Agent gives you a team of AI workers led by your AI CEO. You give the CEO an outcome. It plans the work, hands parts to its team, and asks you before risky steps.
The ideaLink to The idea
Agent is an organization of AI workers. You start with one worker, your CEO (chief executive). You talk to the CEO in web chat or on WhatsApp. The CEO plans the work, does what it can itself, and hands parts to the workers that report to it.
What a worker isLink to What a worker is
A worker is an AI employee with a name, a handle such as @ceo, a role, a level and a budget. A worker uses a model to think. Code work runs on a repository you connect, on your own computer or in Agent's cloud.
What you controlLink to What you control
- Autonomy: how much workers do before they ask you. See Autonomy modes.
- Approvals: risky actions wait for a person. See Approvals.
- Budgets: daily limits for the organization, each worker and each item. See Budgets and spend limits.
- The team: the CEO proposes hires and you approve them. See How your team grows.
What you seeLink to What you see
LimitsLink to Limits
Agent shows its evidence, but it does not guarantee that a result is correct. Check the evidence of important work. See Things Agent cannot do yet.
Checked against the product on 2026-10-05.
Was this helpful?
Related articles
- Quick start: 10 minutes to your first taskSix short steps take you from sign-up to your CEO's first plan.
- How your team growsYou start with one worker. When work needs a specialist, the CEO proposes a hire with the role, the reason, the evidence and a daily budget. You approve or decline.
- The CEOThe CEO is your chief executive worker. It is the front door to your organization: it takes your requests, plans them, hands parts to its team and reports back.
- Ava, your assistantAva is the assistant on every page. She answers questions about Agent and your organization, takes you to the right page, and proposes changes that run only when you confirm them.