The Hidden Cost of Fewer Tokens: Why context efficiency makes the Playwright CLI slower

We wanted to know whether the Playwright CLI would make our tooling more context efficient, faster, and cheaper. The results were decidedly mixed.

When a Test Fails: Solving Automated Triage

Building agents for complex problems — how we improved our Triage agent's accuracy by 400% through better evaluation, better questions, and understanding how agents think.

Product Drift

Agents can generate features faster than you can read them. The product doesn't just move forward — it starts to drift.

Why You're Overthinking Background Agents

If you can run your system locally on your machine, you can have background agents that anyone at your company can use to ship features from Slack. That's really the bar.

Why We Built a QA Agent for Our Background Agent

Our background agent writes the code like any other coding agent, but can now use Ranger to close the loop by testing itself and showcasing its work back to us for review.