> ## Documentation Index > Fetch the complete documentation index at: https://docs.rippit.com/llms.txt > Use this file to discover all available pages before exploring further. # Ada > Technical reference for the Rippit Ada data integration: Data Export API key authorization, API endpoints, what a conversation becomes in Rippit, and sync behavior. A read-only API key integration that syncs Ada AI agent conversations and messages into Rippit on a schedule, using Ada's Data Export API. Ada is in beta. For what applies to every integration, see [how data integrations work](https://docs.rippit.com/plg/data-integrations.md). For the security model, see [Data integration security](https://docs.rippit.com/security/data-integrations.md). This page covers importing Ada conversations as data. To let the Rippit agent read Ada's metrics and configuration directly, see the [Ada connector](https://docs.rippit.com/agentic-chat/connectors/ada.md). ## Connection summary | | | | - | - | | Authorization | An Ada Data Export API key, sent as `Authorization: Bearer ` | | Scope parameter | None | | Writes to Ada | None. Every call is a `GET` | | Credentials shared with Rippit | The API key. Rippit stores it and uses it for every sync | | Credential check | The handle and key are tested against Ada before the connection is saved. Rejected credentials create no connection, and Rippit does not keep them | | Connection identity | Your Ada handle, the part of your dashboard URL before `.ada.support`. One connection per handle | | Required Rippit role | Workspace admin | | API base | `https://.ada.support/api/v2` | | API version | `v2`, in the path | | Sync method | Scheduled polling | | Images | Pictures sent in a conversation are downloaded and stored by Rippit | | Historical backfill | 30 days by default, up to 90 days, counted back from the start of today (UTC) | | Field selection limit | 150 fields at setup, plus Rippit's standard columns. You can add more later with **Add new columns** on the table | ## Before you connect Rippit asks for two values. The Ada handle is the part of your Ada dashboard URL before `.ada.support`: `acme` in `acme.ada.support`. You can paste the whole URL and Rippit extracts the handle. Rippit always connects to `https://.ada.support`, and the handle accepts only letters, numbers, and hyphens. The API key must be a **Data Export** API key, created in your Ada dashboard. If you don't see the Data Export API in your dashboard, it may not be included in your Ada contract. Contact your Ada team or email `help@ada.support` to confirm. ## Data handling | Question | Answer | | - | - | | Is conversation content ingested, or only metadata? | Full content: every message, plus the conversation's channel, CSAT score and comment, topics, intents, and, for generative AI agents, the Playbooks, knowledge articles, and coaching used. Rippit stores each conversation and message exactly as Ada returns it | | Are images stored? | Yes. Pictures sent in a conversation are downloaded and stored rather than linked | | Is CSAT ingested? | Yes. The conversation's CSAT score and comment become fields, and each CSAT rating given in the chat is stored as a survey answer | | Can Rippit modify Ada? | No. No write code path exists | ### What a conversation becomes in Rippit Each Ada conversation becomes one conversation in Rippit. | Rippit record | Content | | - | - | | Subject | The first of these that is set: the last question the customer asked, the conversation's inquiry summary, its platform, or its channel | | Agent | One agent per connection, named `Ada`, who authors every message from your Ada AI agent | | Customer | Each other message sender, recorded by their Ada sender ID | | Start and end | The conversation's creation time, and its last update time | | Fields | Subject, platform (the conversation's platform or channel), CSAT score, CSAT comment, Ada topics, Ada intents, Ada Playbooks, Ada Playbook outcomes, Ada knowledge articles, Ada coaching types, source, and the commenter fields | | Default selected fields | Subject, platform, CSAT score, Ada topics, Ada intents, commenters, first commenter, and last commenter | | Message comments | Every message, in order. Text messages keep their text. Links and web windows become clickable links. Quick replies, list selections, and suggested buttons are stored with the options shown. A CSAT rating appears as `CSAT: `, and thumbs up or down feedback as `Feedback: 👍` or `Feedback: 👎`. Pictures are attached as files. Ada system messages are kept but have no author | **Ada intents** list each intent with its Ada status in parentheses, such as `Billing question (pending)`, so intents Ada has not yet accepted are not shown as settled. **Ada Playbooks, Playbook outcomes, knowledge articles, and coaching types** are filled only for conversations handled by a generative Ada AI agent. On other conversations they are empty. When you choose fields during setup, the list shows the fields above plus other attributes from your Ada conversations: top-level conversation attributes, and metavariables, shown with `metavariables_` in front of the name. Rippit finds them by checking the first 50 conversations updated in the last 7 days. An attribute shows if at least one of those conversations has a single text, number, or true/false value for it. Lists and nested objects never show, and neither do metavariables whose names end in `jwt`, `token`, `secret`, or `password`. The sample decides what shows in the list: * An attribute used only on conversations outside the 50 checked does not show. * If no conversation was updated in the last 7 days, the list shows only the fields above. After setup, the list of fields you can add to the table is built from one page of conversations updated in the last 30 days. ## API endpoints | Object | Endpoint | Method | | - | - | - | | Credential check when you connect | `/export/conversations?page_size=100&updated_since=<30 days ago>&updated_to=` | GET | | Conversations | `/export/conversations?page_size=10000&updated_since=&updated_to=` | GET | | Messages | `/export/messages?page_size=10000&created_since=&created_to=` | GET | | Messages for one conversation, to re-sync it | `/export/messages?page_size=10000&created_since=