Salesforce: Feature Perf Degradation: Agentforce, Core Service
Affected components: AgentforceCore Service21 instances
Timeline of updates
- update
We're aware of an issue impacting Agentforce Coworker. A subset of customers may experience intermittent request failures, and conversations may stop partway through an answer without an error message. We engaged the third-party service provider, and we're seeing error rates decrease.
We’ll provide an update in 30 minutes or sooner if additional information becomes available. - update
Upon further investigation, we've determined that the start time of impact is different than initially understood. We've revised the start time of the Trust post to more accurately reflect the time customers may have begun to experience impact. We apologize for any confusion caused by this.
- update
Agentforce Coworker is now operating at normal service levels. Requests are completing successfully again. Error rates returned to normal after a third-party service provider recovered their services.
We apologize for how this incident affected you and your business. We will undertake a full investigation of the incident, establishing the technical trigger, the underlying cause, and preventive action to avoid a repeat in the future.
Changes Rewindex caught on this incident
Archive proof
Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert.
How the archive is checked, and what it cannot prove.
Rewindex captured this after the last checkpoint; the next run () commits it.
Impact, status and times are the vendor’s own, as last archived. View on status.salesforce.com (opens in new tab).