Connect sources and send data out with the AI Agent
In a Build chat, ask the AI Agent to connect a source ("Connect to our Postgres", "Pull my HubSpot deals") or send a view's rows somewhere ("Send Orders to our BigQuery"). Sign-in details go into a card, never into the chat, and sending data out waits for your OK.
Why the agent won't connect a source in an Ask chat
In an Ask chat, connecting a source, building a connector or sending data out counts as a change, so the agent doesn't start it. It says "Changes happen in Build. This chat stays for asking." and offers:
- Send instructions to the workspace's Owners (for example Send instructions to Pat Lee, or Pat Lee and 2 others);
- Copy instructions for Build, to paste the request in a Build chat.
Connect a data source with the agent
The agent can create, list, edit and delete connections, preview tables, and import a table as a dataset. For a source reached through its REST API, it builds a connector draft that opens beside the chat (see Connect a database or app and REST API).
When it needs sign-in details, it shows a sign-in card: you type the key or password there, never into the chat. It checks the key with the source, for example "Connected" or "The key works but can't read what's needed".
Connect a source with no built-in connector
For a source with no built-in connector and no usable REST API, the agent builds one with you:
- SOAP or WSDL services, XML-RPC, GraphQL and OData feeds;
- bulk exports that submit a job and download a file;
- Trino, Starburst or ClickHouse over HTTP;
- a full export of an Elasticsearch or OpenSearch index;
- SaaS apps Mammoth knows but has no connector for.
The chat shows "Building your connector". The agent first checks whether your workspace already has a connector for the source, and offers Use it or Build a new one. Otherwise it researches the source, asks for sign-in, runs the connector against your system and shows a draft card:
- "It will call:" lists every address it contacts.
- A sample of what it returned, and the rows read in the preview.
- Save it or Save as dataset saves it. Change something asks for a change.
Send data out of Mammoth with the agent
Ask to send, export or sync a view's rows. The agent checks which export options your plan has (Mammoth-managed databases, a live link, a download, or a built-in destination) and adds the send as a plan step that waits for your OK. See Send data to a database or BI tool.
Send data to an API with no built-in export
For an API with no built-in export (an ERP, a CRM or an internal API that takes JSON, NDJSON or XML), open the view and ask the agent to send it there. It writes a delivery plan and runs it with sending switched off. The card shows "Dry run · nothing sent", "The first request, exactly as it will be sent", and "Data and credentials go only to:" with each host.
| Button | What it does |
|---|---|
| Add sign-in details | Opens a form for the API's key or password |
| Send a few test records first | Sends a few real records so you can check what the API answers |
| Change something | Asks the agent to change the plan |
| Save it | Saves it as an export step on the view |
Only Save it saves the export: typing "yes" in the chat doesn't. Workspace Owners can limit which hosts custom destinations may send to with Export destinations in workspace settings.
Related
- What the AI Agent can do: every skill and who can use it.
- Plans and runs: approve the send step.
- Ask mode: why Ask chats change nothing.
- AI Agent access: who has the agent and at which level.
Something wrong? support@mammoth.io