Connect Zendesk AI Agents to Rig

    Sync every conversation your Zendesk AI agents have, with resolution status and tier, channel, language, message counts, triggered replies, use cases and knowledge sources, into Rig. This connector reads the AI agents - Advanced Data Export API, which is separate from Zendesk Support.

    Before you start

    • You need an admin role in the AI agents - Advanced admin. Only admins can generate the organisation API key.
    • Gather the ID of every AI agent (bot) you want to sync before the first sync. The export works per AI agent and the API cannot list them for you.
    • Decide your start date. The export holds nothing before 2024-01-01.

    Step 1: Generate the organisation API key and find your IDs

    1. In the AI agents - Advanced admin, click Organization management in the left sidebar. If you bought AI agents - Advanced before 7 October 2024, click User management then Organization management instead.
    2. Click your organisation to open its profile. The organisation ID is in the browser address, after /admin/organizations/.
    3. Select the API key tab, click Generate, then Save, and copy the key.
    4. Open each AI agent in the dashboard and note its ID from the agent's address. Zendesk's article does not cover finding bot IDs, so take them from the URL.

    Step 2: Connect it in Rig

    Adding a source needs a workspace owner, or a role with the Manage connections permission, on a workspace where you manage your own connections. If the Connectors tab says “Data ingestion for this workspace is managed by Rig”, ask an owner or Rig support to add the source.

    1. In Rig, open Connections, choose the Connectors tab and go to Sources & actions.
    2. Search for Zendesk AI Agents, open the card and click Connect.
    3. Organization API key: paste the key you generated.
    4. Organization ID: paste the ID from your organisation's address.
    5. AI agent (bot) IDs: list every AI agent ID, separated by commas.
    6. Zendesk subdomain: enter the first part of your Zendesk address, such as acme for acme.zendesk.com.
    7. History start date: leave it at 2024-01-01 to load everything the export holds, or set a later date as YYYY-MM-DD. Set it before the first sync.
    8. Click Continue. Rig checks the credentials and lists the streams it can reach, so choose the ones you want and click Connect.
    9. The source then syncs on its schedule, which is nightly unless you change it. To load data straight away, click Sync on its row; Test pulls a small sample first if you want to check the connection.

    What Rig pulls in

    Zendesk AI Agents lands in its own zendesk_ai_agents schema in your warehouse:

    • Conversations: one row per conversation, with resolution, channel, language, message counts, triggered replies, use cases and procedures, knowledge sources and labels.

    Transcripts are not part of the export. Lists such as labels and triggered replies stay as JSON columns on the one table.

    Good to know

    • Zendesk builds each day's export file at midnight UTC and files a conversation under the day its session ended. Rig re-reads the most recent days every run, so a conversation that changes or closes late is updated.
    • An AI agent added to the list after the first sync is read from that point on, without its earlier history. List every agent before you connect.
    • Moving the start date earlier after the first sync loads nothing older.
    • To disconnect Zendesk AI Agents, click the bin icon on the source's row under Sources & actions. Only whoever connected the source or a workspace owner can do this, and data already synced stays in the warehouse.

    What people use this for

    • Measure automated resolution
    • Find the use cases that fail
    • Check how well the knowledge base answers

    More ideas for using Zendesk AI Agents

    Zendesk AI Agents documentation

    Was this guide helpful?