Showing category results for AI

All five agent runs produced a working script, and nothing in the eval score looked wrong. The trajectories told a different story. Every run read a DLL as raw bytes to find plugin names, and three scripts would quietly reroute a CI runner's network traffic. Here are the patterns to look for in your own agents' trajectories, and what to change in y...

Your eval might be telling the agent it's a test before the agent reads a single instruction. Eval tools need a fresh folder for every run, and the easiest way to get one is a temp directory with a random name like . The agent sees that path on every turn, in the system prompt as its working directory and in the output of every tool call. If models...

We swapped GitHub for a local git remote in our agent evals. Rebasing and pushing on request were unaffected, but the agent pushed on its own 11 points less often. Here's when a local remote is a safe shortcut, and when it isn't.

AI coding agents now pick the SDK, the version, and the pattern for your developers. The AX Practitioner Playbook is our method for finding out whether they get your technology right, and for fixing the sources they rely on when they don't.

How presets, extensions, bundles, workflows, and governed catalogs make Spec-Driven Development adaptable at scale This article continues Spec-Driven Development: A Spec-First Approach to AI-Native Engineering, which introduced the principles and lifecycle of SDD. Here, we focus on the next challenge: adapting that workflow to the standards, dom...

Your agent says it's done, and the code compiles, but did it pick your technology? Did it use it correctly? Learn what Agent Experience (AX) is, how to measure it, and why the obvious fix isn't always the right one.

See how Azure Canvases bring plans, code, previews, and deployment feedback together in a collaborative workspace for agent-assisted development.

Learn to direct AI coding agents, review their work, and build reliable development workflows with this free GitHub Copilot app course.

A model can fail on features released before its knowledge cutoff, then succeed on ones released after it. We tested hundreds of product changes and found that the date tells you far less than the work does.