# Intermittent failures creating agent tasks

DevFeed: [Intermittent failures creating agent tasks](<https://devfeed.tech/articles/intermittent-failures-creating-agent-tasks-75739.md>)

Original publisher: [Read original article](<https://www.githubstatus.com/incidents/bhbcjn4n3jzp>)

Published: 2026-08-20T14:43:00Z

Content type: news

Language: en

Sources: [GitHub Status - Incident History](<https://devfeed.tech/sources/github-status-incident-history.md>)

Topics: [intermittent failures](<https://devfeed.tech/topics/intermittent-failures.md>), [Post Mortem](<https://devfeed.tech/topics/post-mortem.md>), [Amazon RDS](<https://devfeed.tech/topics/amazon-rds.md>)

Tags: [capacity](<https://devfeed.tech/tags/capacity.md>), [cloud-database](<https://devfeed.tech/tags/cloud-database.md>), [failover](<https://devfeed.tech/tags/failover.md>), [incident](<https://devfeed.tech/tags/incident.md>), [intermittent-failures](<https://devfeed.tech/tags/intermittent-failures.md>), [outage](<https://devfeed.tech/tags/outage.md>), [prevent](<https://devfeed.tech/tags/prevent.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

## AI overview

A regional outage at a third-party cloud database delayed visibility of Copilot Cloud Agent task status and results for some users. The tasks continued to run and complete, and no task data was lost. GitHub failed over to a healthy region, added processing capacity to clear the backlog, and plans to remove the vulnerable database configuration and improve failover procedures.

## Source excerpt

Between 13:57 UTC on August 20 and 00:37 UTC on August 21, 2026, some users of the Copilot Cloud Agent experienced delays of up to 60 to 90 minutes in seeing the status and results of their agent tasks. The agent tasks themselves continued to run and complete during this time; only the visibility of their status was delayed. The cause was a regional outage in a third-party cloud database service that Copilot uses to store agent task status. We failed over the affected database to a healthy region, added processing capacity to work through the backlog, and restored normal operation once the underlying service recovered. No task data was lost during the incident. To prevent repetition of similar incidents, we are removing the database configuration that made us vulnerable to this regional outage and improving our database failover procedures.