Skip to content
FidelicRoster →

Zendesk integration · OAuth + REST

Connect AI agents to your Zendesk workspace

AI agents that read your Zendesk views and tickets, draft new records, and post the result to Slack — support digests, escalation briefs, and CX hygiene.

How a Fidelic agent reaches Zendesk.

The connection

What's wired

Fidelic agents connect to Zendesk through OAuth + the Zendesk Support API. Your agent reads the views and tickets the admin explicitly shares.

When the agent reads, it stays inside the views you've shared. Nothing leaves your Zendesk unless the agent posts a digest to Slack or adds an internal note to a ticket you authorized.

→ Zendesk official API docs

Set it up

How to connect

Before you start

  • A Zendesk Support account on any plan.
  • Admin role with OAuth-client permission.
  • A Slack workspace where the agent will live and post.
  • A decision on which Zendesk views the agent should reach.
  • About five minutes for the OAuth flow.

The steps

  1. Sign in to Fidelic and pick the agent. From the Roster, pick the CX agent.
  2. Authorize Zendesk. Click Connect Zendesk. The OAuth dialog opens; sign in with your admin account. The app appears in Admin Center → Apps → OAuth clients.
  3. Pick the views the agent should reach. Pick the views, brands, and ticket scopes the agent will read or write to.
  4. Confirm and finish. The agent runs a test read. When it passes, your Slack channel shows a Connected to Zendesk message.
  5. Try the first agent action. Ask for a weekly support digest in Slack.

The edges

Connection limits

Where the connection draws the line:

  • · The agent only reads views and tickets the admin explicitly shares.
  • · Zendesk triggers and automations run server-side; the agent reads their output.
  • · Zendesk Sell, Talk, and Chat are separate products with their own scopes.

The path

Where the data goes

The connection runs inside your sandboxed Anthropic project. One project key per Fidelic customer; Fidelic infrastructure does not see your platform data.

Anything the agent reads stays inside your environment. The only data that leaves is what the agent posts to Slack or writes back to a destination you authorized — and you can revoke either at any time from the platform's connections panel.

→ Read the full security architecture

Where to next