Frequently asked questions

Plain answers to the things people ask us most. If yours isn't here, email us — we read everything.

Do I need to know how to code?
No. If you can describe what you want done in plain English, you can build it. There's nothing to install and nothing to configure.
What can my agents do?
They can read websites, summarize text, send email, work with images, and turn speech into text and back. Each agent is a series of steps that hand off to each other — read this, summarize that, email me. We add new things they can do all the time.
Where does my agent run?
On our computers, in the cloud. You don't need to leave your laptop on, and your agent will keep running whether your browser is open or not.
Who can see what my agents do?
Only you. Your agents, the things they read, and the things they write are tied to your account. We don't share them with other users.
Is my data private?
Yes. We don't sell your data and we don't use your agents' inputs to train anything. See our Privacy Policy for the details.
How much does it cost?
Building and testing your agents is free. You only pay when an agent actually runs — at the cost of the work it does, with no subscription and no hidden fees. See [pricing](/pricing) for examples.
What if my agent does something wrong?
You can stop it at any time. Every run shows its work — what it read, what it decided, what it sent — so you can see exactly what happened and fix it.
Can I change my agent after I build it?
Yes. Everything about your agent — its personality, its instructions, what it reads, what it sends — stays editable. Change a sentence, run it again, see what's different.
How do I cancel my account?
Settings → Account → Delete account. Your agents, runs, and history are removed immediately.