Operations | Monitoring | ITSM | DevOps | Cloud

Connect Codex to CircleCI: Fix Failing CI Without Leaving Your Terminal

Connect Codex to CircleCI and give your coding agent direct access to the CI feedback it needs to keep working. In this tutorial, we’ll walk through setting up the CircleCI CLI and CircleCI plugin for Codex, then show how Codex can check pipeline results, validate your CircleCI config, diagnose failed builds, trigger new pipelines, and keep iterating on a fix until CI is green. Instead of bouncing between your terminal and CircleCI to copy logs and errors back to your agent, you can bring the full CI feedback loop directly into your Codex session.

How to Use Claude Code with CircleCI to Fix Failed Builds

Give Claude Code direct access to CircleCI and let it diagnose failed builds, fix issues, and keep iterating until your pipeline is green. In this tutorial, we walk through how to connect Claude Code to CircleCI using the CircleCI CLI. You’ll see how Claude can read pipeline results, identify test failures, make fixes, trigger new builds, and monitor CircleCI without leaving the terminal.

How to set up CircleCI with Cursor Origin

CircleCI now integrates with Cursor Origin, bringing scalable CI/CD to Origin-hosted repositories. In this demo, see how to connect an Origin repository to CircleCI, configure your pipeline triggers, run a build, and report CI status back to your Origin pull request. Already using CircleCI? Your existing.circleci/config.yml works as-is, with no Origin-specific CI syntax or separate config to maintain.

CircleCI Smarter Testing: Stop running tests that don't matter

Testing consumes up to 50% of CI/CD pipeline time. That’s the single most expensive place in your delivery pipeline, and a meaningful share of that time is often wasted running tests unaffected by the change. Every time a developer pushes a commit, the full test suite runs. A two-line bug fix in auth.py triggers 2,000 tests, including 1,900 that don’t touch anything near auth.py. Those unrelated tests are overwhelmingly likely to pass, but the pipeline still spends 20 minutes running them.

MCP vs API: How they work together and when to use each

Summary: An API defines how software interacts with a service. MCP defines a standard way for AI applications to discover and invoke tools exposed by a service. They usually work together: an MCP server can sit in front of APIs you already run, turning low-level operations into capabilities an agent can find and use at runtime. Your API may already expose everything an AI agent needs. The harder problem is helping the agent figure out which operations matter for the task it has been given.