Create an agent

An agent is a configured principal that runs inside one of your projects. It has a model, a persona, a set of skills and tools it may call, and the connections it's allowed to use. Every run is recorded so you can see exactly what the agent did and what it cost. For the broader picture, see What is an agent?.

Create it

Open the project's agent roster at /a/<account>/p/<project>/agents and click New agent (/a/<account>/p/<project>/agents/new). You can also have Zero draft one for you — "make an agent that posts a weekly revenue recap to Slack" — and hand it back for review.

A new agent lands on its detail page, where each concern is a tab.

Or install a pack

Advanced… opens the template gallery, grouped by family (Marketing, Support, Ops, …). A pack card installs several agents together — an orchestrator plus the specialists it briefs — and says up front what installing means: how many agents, which connections it wants (and which are optional), which channels it speaks on, its cadence, and roughly what it costs a day in credits. Choosing it opens a four-step install:

1. Identity — the orchestrator's name, your company website (it seeds the first research run), icon and theme.
2. Connections — one card per connection the pack wants. A required one must be connected before you can install; an optional one can be skipped, and the console widgets that read it stay locked until you connect it later.
3. Cadence — the pack's schedules as cron expressions with a timezone. The first drives the orchestrator; it briefs the others.
4. Budget + autonomy — a daily cap for the whole pack, split evenly across its agents, and the approval policy: every draft waits for you.

Install mints the agents from their templates, grants the connections you chose to each of them, sets the schedule and the caps, and opens the orchestrator's Console — the pack's home screen: drafts waiting on you, the strategy documents, the schedule, connection health. Agents can read the same console as markdown by appending /index.md to its URL.

Configure it

At minimum an agent needs:

• A model — set it on the Model tab. This is the model the agent thinks with; see Choosing a model.
• A persona — the Identity and Persona tabs hold the display name, icon, and system prompt that shape its behaviour.
• Skills and tools — the Skills and Tools tabs. Tools are gated: the agent can only call what you expose, and each call is scoped and audited.
• Connections — the Connections tab. Grant only the connectors the task needs.

Optionally set a per-day or per-run spend cap on the Budget tab so a misbehaving agent can't run away with your credits.

Invoke it

An agent can run several ways, all producing an agent run with a full message and audit trail:

• Interactively — chat with it from the agent's Invoke tab, which opens a thread.
• On a schedule — a cron trigger runs it unattended.
• From a trigger — an inbound webhook, MCP tool call, REST call, email, or chat channel starts a run.

Configure the non-interactive triggers on the Invocations tab. See Running agents for the full walkthrough.

Least privilege

Agents default closed. A new agent can't act on a connection or call a tool until you grant it, and it can never grant access to another principal. Give each agent the narrowest set of connections and tools that lets it do its job.

Where to go next

• Running agents to dispatch it and read run status.
• Why did my run fail? when a run doesn't do what you expected.