Skip to content
FidelicRoster →

ServiceNow integration · OAuth + REST

Connect AI agents to your ServiceNow instance

AI agents that read your ServiceNow tables, draft new records, and post the result to Slack — IT runbook briefs, incident summaries, and HR ticket hygiene.

How a Fidelic agent reaches ServiceNow.

The connection

What's wired

Fidelic agents connect to ServiceNow through OAuth + the ServiceNow Table API. Your agent reads the tables and records the instance admin explicitly grants — Incident, Change, Knowledge, or any custom table you authorize.

When the agent reads, it stays inside the tables you've shared. Nothing leaves your ServiceNow instance unless the agent posts a brief to Slack or creates a record in a table you authorized.

ServiceNow official API docs

Set it up

How to connect

Before you start

  • A ServiceNow instance — any tier.
  • Instance admin role.
  • A Slack workspace where the agent will live and post.
  • A decision on which ServiceNow tables 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, choose the agent that needs ServiceNow access.
  2. Authorize ServiceNow. Click Connect ServiceNow. The OAuth dialog opens; sign in with your instance admin account. The app appears in System OAuth → Application Registry.
  3. Pick the tables the agent should reach. Pick the tables and records 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 ServiceNow message.
  5. Try the first agent action. Ask for an IT runbook brief in Slack.

The edges

Connection limits

Where the connection draws the line:

  • · The agent only reads tables the admin explicitly grants.
  • · ServiceNow workflows and business rules run server-side; the agent reads their output.
  • · For Now Assist or Virtual Agent integration, those run separately.

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