Data and AI releases

548 this month · 176 companies

Copy Fix Prompt, diagnose and fix failures with any AI coding agent

UpdateNot yet verified

You can now copy a failure-diagnosing prompt directly from the CircleCI UI and paste it into your preferred AI coding agent. Select the wrench icon on a failing workflow and choose Copy Fix Prompt to copy a ready-to-use prompt to your clipboard. Paste it into any AI coding tool to diagnose the failure and get a fix.

AI agentsDeveloper toolsCoding agents

Read on circleci.com

Also shipped Aug 12, 2026CircleCI in August 2026 →

Glean connector in Lakeflow Connect (Beta)

You can now ingest data from Glean into Databricks using the managed Glean connector in Lakeflow Connect. The connector ingests company-wide usage insights for search, Assistant, and agents, along with the shortcuts (go links) defined in your Glean deployment, using a Glean Client API token. This feature is in Beta . See Glean connector .

Beta
Source ↗

More from CircleCIEvery CircleCI release →

Server Release 4.10.1

Updates The NGINX default image has been updated to version 1.30.1, which addresses security vulnerabilities present in version 1.30.0 that were not resolved until after its release. No action is required unless you have pinned the NGINX image tag in your deployment.

Update
Source ↗

Server Release 4.9.6

Updates nginx upstream connections to Kong now use keepalive pooling to reuse TCP connections. This prevents ephemeral port exhaustion under high load, eliminating the 502 errors that could occur in busy deployments. A connection-pool defect in the Redis client used by the oidc-tasks-service has been resolved.

Update
Source ↗

Email notifications for expiring personal API tokens

CircleCI now emails you before a personal API token expires, so you can rotate it before any scripts, pipelines, or integrations that use it start failing. You receive an email at four points ahead of the expiry date: 30 days before 15 days before 7 days before 1 day before Emails go to your default email address.

Update
Source ↗

IP ranges support available for Gen2 Docker (x86)

IP ranges is now supported for x86 Docker Gen2 resources classes. Pricing for IP ranges is unchanged and is the same across all executor generations: 450 credits per 1 GB of data used, for customers on a Performance or Scale plan, billed in addition to standard compute costs. See the x86 (gen2) Docker documentation and IP ranges documentation for details.

Update
Source ↗