Practical engineering writing and free developer tools.

An agent that has to prove its work catches its own mistakes. One that only has to look right ships them to you. This is how to build the feedback loop: the verification ladder, test-first prompting, and letting the agent iterate to green on its own without weakening your tests.

Most prompt advice treats every task the same. Real tasks are not the same: a typo fix and a payment refactor need different prompts. Here are four patterns, a way to pick between them, copyable templates, and the anti-patterns that quietly wreck a run.

You correct the agent, it apologizes, and ten minutes later it makes the same mistake. That is not a model problem; it is a memory problem. Here is how the context window works as a budget, what belongs in CLAUDE.md and AGENTS.md, and when to restart a session instead of patching it.

The agent one-shots your feature on Monday and quietly rewrites your auth module on Tuesday. Here is the workflow that keeps the speed without the wreckage: plan-first prompting, reviewable diffs, and verification the agent runs itself. With interactive tools to grade your own prompts.

Your fix is deployed but users still see the old version. A service worker is usually why. Here is how the three caching strategies behave, with interactive demos, the mistakes that ship to production, and how to monitor all of it.

Compare Sobel, Canny, and Laplacian edge detection with an interactive browser demo. Tune thresholds, upload images, and see how each algorithm finds boundaries.