How I Built an AI Agent to Handle My Support Email
I built a CLI tool that reads my support inbox, classifies emails, generates responses using an LLM, and knows when to escalate to a human. Here's a deep dive into the architecture.
I built a CLI tool that reads my support inbox, classifies emails, generates responses using an LLM, and knows when to escalate to a human. Here's a deep dive into the architecture.
Beyond CI/CD: unconventional and surprisingly practical things you can build with GitHub Actions—from chess games in issues to SSL certificate monitoring.
Complete, battle-tested GitHub Actions workflows from real projects. The full YAML, the bugs we hit, the lessons learned, and the evolution from first commit to production.
When GitHub's runners aren't enough—whether it's cost, performance, or specialized hardware—here's how to run your own infrastructure for Actions.
Slow CI is a productivity killer. Here's how to slash your GitHub Actions workflow times—with real examples, benchmarks, and the caching strategies that actually work.
Push and pull_request are just the beginning. Here's how to trigger workflows from Slack, schedule nightly builds, chain workflows together, and turn GitHub into a surprisingly capable automation platform.
Your GitHub Actions workflows have access to your secrets, your code, and your deployment pipelines. Here's how to lock them down before someone else does.
Your GitHub Actions workflows don't have to be unmaintainable YAML spaghetti. Here are the design patterns, refactoring techniques, and organizational strategies that keep workflows clean as they grow.
GitHub Actions can do far more than run your tests. Here's a tour of the surprising, useful, and unconventional things people build with workflows—and the start of a series going deeper.
I built a CLI that converts documentation docsets to Markdown files—because Apple's online docs don't work without JavaScript, and I don't want MCPs in my workflow.