# Drive

One run of our AI agent through a real product: it reads the docs, signs up, gets a key, does the core work, pays where it can and deletes the account.

Also called agent drive.

Source: https://agentdrives.com/glossary/drive · as data: https://agentdrives.com/glossary/drive.json · licence CC BY 4.0

## In our drives

Every step is saved with its evidence: the calls, the answers and the screenshots. A product's page shows its latest drive and the ones before it.

How we test: https://agentdrives.com/method?via=md

## Products we drove most recently

151 products driven so far.

- [UploadThing](https://agentdrives.com/tools/uploadthing.md?via=md): L1 Needs a person
- [zcal](https://agentdrives.com/tools/zcal.md?via=md): L0 Read-only
- [Zulip](https://agentdrives.com/tools/zulip.md?via=md): L4 Runs on its own
- [BookStack](https://agentdrives.com/tools/bookstackapp.md?via=md): L4 Runs on its own
- [Memos](https://agentdrives.com/tools/usememos.md?via=md): L1 Needs a person
- [Postiz](https://agentdrives.com/tools/postiz.md?via=md): L2 Gets in
- [Tinybird](https://agentdrives.com/tools/tinybird.md?via=md): L1 Needs a person
- [Basecamp](https://agentdrives.com/tools/basecamp.md?via=md): L1 Needs a person

## Related terms

- [Agent access](https://agentdrives.com/glossary/agent-access.md): Whether an AI agent can use a product on its own: find it, sign up, get a key, do the work, pay and leave, with no person stepping in.
- [Agent Access Levels](https://agentdrives.com/glossary/agent-access-levels.md): Our scale from L0 to L5 for how far an AI agent gets in a product on its own. L0 means there is nothing for an agent to use. L5 means it gets in, does the work, pays and leaves without a person.
- [Needs a human](https://agentdrives.com/glossary/needs-a-human.md): A step a person had to do for the agent: solve a CAPTCHA, type a phone code, enter a card or click a link in a browser.

Every term: https://agentdrives.com/glossary.md