Live / Salesforce / Incident
Salesforce: Degradation: Agentforce (91 instances)
Salesforce · salesforce.comMinor incidentResolved2026-10-30 18:14 UTC
Public — what happened
Summary
Salesforce said some Agentforce customers, across multiple regions, were getting errors or incomplete responses when their requests used large language models run by an outside provider. It reported the problem began around 15:31 UTC on 2026-10-30, and later said it reached more instances than first thought and that the start time had been revised. By 18:08 UTC Salesforce said the provider had pointed to a recent update to how it routes requests as a possible problem and was rolling it back, with a follow-up fix planned afterward. The incident was still listed as under investigation, with no recovery time given.
Timeline
- Started — 2026-10-30 15:31 UTC
- Investigating — 2026-10-30 15:48 UTC (8 updates)
- Resolved — 2026-10-30 18:14 UTC · 2h 42m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach Salesforce against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for Salesforce: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the Salesforce report →
More from Salesforce
Covered in The Squid’s Ink, Week 45, 2026, our weekly internet health report.