Start a conversation over Ada's email channel

Start a conversation with an end user over Ada’s native Email channel, providing context for their inquiry. This endpoint is exclusive to the native Email channel and cannot be used for custom channels. Your AI Agent can start conversations only with the default Ada-provided email address, or with email addresses you’ve configured through Bring Your Own Domain (BYOD) settings. To include files the customer attached to their inquiry, send the request as multipart/form-data. Put the JSON request body in the data part and add one attachments part per file. A request can include up to 10 attachments and 30 MB in total. Attachments follow the attachment handling setting of the inbox the AI Agent replies from, the same as attachments on an email sent to the AI Agent. The AI Agent reads at most 3 images per request, and only on inboxes set to reply using the attachment. It keeps every other file and passes it to a human agent on handoff.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

namestringRequired

The customer's full name

subjectstringRequired

The subject of the customer's inquiry; used as the subject for the AI Agent's reply

reply_tostringRequired

The customer's email address

textstringOptional

The customer's inquiry, limited to 10 KB

reply_asstringOptional

The company email address you want to use to reply to the customer. Defaults to the Ada provided email address.

cclist of stringsOptional

The email addresses in the email's CC field

metadataobjectOptional

Any metadata associated with the conversation, up to 4 KB. All metadata passed through this field will appear as metavariables in your dashboard.

Response

Conversation Created

conversation_idstringOptionalRead-only

The Ada-generated conversation id

Errors

400

Bad Request Error

401

Unauthorized Error

413

Content Too Large Error

422

Unprocessable Entity Error

429

Too Many Requests Error

500

Internal Server Error