Buttondown vs Kit for AI agents
As of 6 Oct 2026, Buttondown gets an AI agent further: L4 · Runs on its own against L1 · Needs a person.
- Find: Some docs for agents: llms.txt and an OpenAPI.
- Access: Sign-up in a browser.
- Use: 83% of the work.
- Pay: Reaches the checkout: Stopped at the card form.
- Leave: Leaves on its own: Nothing to cancel, deletes its account.
Through every checkpoint. Next: pay without a person
Runs on its own: our agent got in on its own through a plain sign-up form, no CAPTCHA, confirmed by mail, and reached the dashboard to get a key with no documented key API. From there it drafted, scheduled, sent, personalised, archived, exported, imported and bulk-edited email through the API, every step read back and matched. It stayed on the free plan, so paying was never tried: upgrading needs a card at a dashboard billing page with an hCaptcha script present. Deleting the account also needs the dashboard: the first try didn't take, the second did, and after that the key stopped working.
Gets furtherDriven 2 Oct 2026 · The drive and its evidence- Find: Docs for agents: llms.txt, an OpenAPI and an MCP server.
- Access: Can't sign up.
- Use: Work not reached.
- Pay: Payment not reached.
- Leave: Leaving not reached.
Stopped at sign up: needs a human. Next: let an agent sign up on its own
L1 · Needs a person describes Kit for an agent today. Developer docs are agent-friendly: llms.txt, Markdown pages, OpenAPI, a read-only docs MCP our agent reached on its own. Sign-up is where it stopped: app.kit.com/users/signup showed a Cloudflare 'Verify you are human' challenge that never cleared, so no account, no key, and no call to the API past an unauthenticated 401. A person has to sign up, verify, and make the key in the web app before an agent can do any core email work through the API or the paid Kit MCP. No plan was started, so paying and cancelling were never reached.
Driven 6 Oct 2026 · The drive and its evidenceThe two summaries: written and checked by our agents from each product's drive. How we write.
Where each one stops.
ButtondownThrough every checkpoint
KitStopped at sign up: needs a human
| Checkpoint | Buttondown | Kit |
|---|---|---|
| Docs | Headless | Headless |
| Sign up | In a browser | Needs a human |
| Verify | Headless | Not reached |
| Key | In a browser | Not reached |
| First call | Headless | Not reached |
| First action | Headless | Not reached |
| Pay | In a browser | Not reached |
| Cancel | Not needed | Not reached |
| Delete | In a browser | Not reached |
Headless or in a browser.
How our agent passed each checkpoint, and what each product offers an agent.
Checkpoints by route, API, MCP, CLI and SDK
| Buttondown | Kit | |
|---|---|---|
| Headless (checkpoints) | 4 | 1 |
| In a browser (checkpoints) | 4 | 0 |
| Needs a human (checkpoints) | 0 | 1 |
| Blocked (checkpoints) | 0 | 0 |
| Not tested (checkpoints) | 0 | 7 |
| Work done | 83% of the core | Not measured |
| API | Yes | Yes |
| OpenAPI | Yes | Yes |
| MCP server | No | Yes (official) |
| CLI | Yes | No |
| SDK | No | No |
| llms.txt | Yes | Yes |
Bot checks, and where a person was needed.
| Buttondown | Kit | |
|---|---|---|
| Bot check | None met | Cloudflare managed challenge (Turnstile 'Verify you are human') stopped it at sign up, with a visible challenge |
| Wall type | No bot-check wall | A check of our network and browser |
| First wall | None | Cloudflare challenge on the sign-up page |
| A person helped | No | No |
A check of our network and browser: It judged where our agent connects from and its browser, not a person. An agent that works on its own from a data center doesn't get through unless the owner lets signed agents in. How agents in a person's own browser fare isn't measured yet. Where we drive from.
Level and part scores.
| Buttondown | Kit | |
|---|---|---|
| Level | L4 · Runs on its own | L1 · Needs a person |
| Agent-ready setup | 85 of 100, fair | 90 of 100, good |
| Standards | None recorded | MCP client registration (behind) · OpenAPI 3.0.3 (2 versions behind) |
Holds up: not measured in these drives. Docs match is measured in an Audit. What the scores mean.
Pay, cancel and delete.
| Buttondown | Kit | |
|---|---|---|
| Pay | Reaches the checkout | Payment not reached |
| Free plan or trial | Free plan | Free plan |
| Cancel | Not needed | Not reached |
| Delete the account | In a browser | Not reached |
How each one takes payment
- Buttondown: Reaches the checkout: stopped at the card form.
- Kit: Payment not reached.
Buttondown vs Kit: the short answers.
Which can an AI agent use, Buttondown or Kit?
Buttondown gets an AI agent further: L4 · Runs on its own against L1 · Needs a person. With Buttondown our agent went through every checkpoint; with Kit it was stopped at sign up (needs a human). Driven 2 Oct 2026 (Buttondown) and 6 Oct 2026 (Kit).
Can an AI agent sign up for Buttondown and Kit on its own?
Buttondown: yes, in a browser. Kit: no, needs a human.
Do Buttondown and Kit have an MCP server?
Buttondown: none found. Kit: yes (official).
Can an AI agent delete its Buttondown or Kit account?
Buttondown: yes, in a browser. Kit: not reached.
The drives and the category.
Put your own shortlist side by side.
A Stack check drives the tools you're choosing between and shows which ones your agents can use. $490 for three tools, ready in 24 hours.