Use cases
What AI agents do with an email API that reads the reply.
Every page here is one workflow, built on an example you can run: the calls it makes, the fields it decides from, and the limits on the key that keep it safe when the model is wrong.
POST /v1/emails
GET /v1/threads?awaiting_reply=true
GET /v1/threads/:id
POST /v1/threads/:id/handled
Who builds with SendRaven?
Developers choose it and wire it up. More and more, an agent runs it. If your product sends mail and something, or someone, has to read what comes back, you are in the right place.
MCP + guardrails
Teams shipping AI agents
An agent holds a key, not a workspace. Give the key a daily cap, an allowlist and an approval hold, point the agent at the MCP server, and it can send, read the reply, and be stopped by a person.
The pages
One workflow each, with the code behind it.
Customer support
Support agents
List the conversations waiting on an answer, read them without the quoted history, and reply in the customer's thread, with every reply held for a person until you trust what it writes.
Waiting on an answer
Follow-up agents
Email someone, nudge them in the same thread when nobody answers, and stop the moment a person replies. An out-of-office does not count, and the count comes from the thread.
Building something else?
The same calls cover it. Start with what an email API for AI agents has to do, or the quickstart.