AI Agent brings agents, workflows, connected tools, knowledge, and supervised work into one workspace. Start by completing onboarding and testing your primary agent. Add a workflow when the same process should run again, and use a project when an initiative needs its own board and progress view.
Start here
Choose the path that matches what you want to accomplish first.
Set up AI Agent
Go from an empty workspace to a tested agent and a supervised workflow.
Create an agent
Configure a focused operator, limit its tools, and test it with a representative request.
Build a workflow
Turn a repeatable process into steps you can run, inspect, and approve.
Connect your tools
Connect an external account, then control which agents and tools may use it.
For a complete introduction, finish onboarding, take the workspace tour, and follow the weekly growth review tutorial.
How the pieces fit
- Your workspace holds shared agents, connections, knowledge, and operating surfaces.
- An agent brings instructions, skills, and permitted connection tools to a task.
- A workflow defines a repeatable sequence you can test and run.
- An autopilot keeps proven work operating from a configured trigger.
- The Board, Inbox, approvals, and runs show what needs attention and what happened.
- An optional project groups tickets for a focused initiative.
Explore the concepts in more detail:
Agents
Learn how instructions, skills, knowledge, and tool access shape an agent.
Workflows and Autopilots
Compare repeatable workflows with continuously triggered automation.
Board, Inbox, and runs
Start with the Board, then learn how the Inbox, approvals, and runs make work observable.
Projects
Organize tickets for a focused initiative when a separate board is useful.
Keep control
Begin with read-only connection tools where possible. Add actions only when the agent needs them, and keep approval steps for changes such as publishing, posting, or updating records. Learn how tool access and approvals work together before expanding an automation’s permissions.