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

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

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 see
Customers 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.

The full archive is on the Salesforce status & history page.

Related: Salesforce status & history. SquidGrid is not affiliated with Salesforce.