Test Driven Development With AI Agents: A Step-by-Step Guide
Learn how to run test driven development with AI agents: write failing tests first, constrain the agent, verify results, and roll back safely when it drifts.
Guides on programming languages, tools and engineering practice.

Learn how to run test driven development with AI agents: write failing tests first, constrain the agent, verify results, and roll back safely when it drifts.
A step-by-step routine to stop AI assistants from breaking working code: characterization tests, scoped diffs, protected files, CI gates and rollback.
An agent harness is everything around the model: tools, context, permissions, loop control and checks. Learn how it works, when to build one, and a worked example.
Build GDPR erasure that works in code: self-service deletion, staff review, one transactional path, outbox search deletes and anonymized orders.
Claude Code vs Cursor for professional work, compared on review control, repo scale, security, cost and team fit, with a pick for each situation.
Remove release downtime for a PHP monolith, a Next.js frontend and search on Kubernetes: probes, preStop drain, safe rollouts and Redis sessions.
A step-by-step guide to using Claude Code in large codebases: layered CLAUDE.md files, plan mode, scoped tasks, hooks, and a rollback routine.
Write a CLAUDE.md that Claude Code actually follows: what to include, what to cut, how to scope rules, and how to test and roll back changes.
An AI code review checklist for teams: nine checks for AI-generated diffs, each with its strength and limit, plus a routine to run weekly.
A practical guide to reviewing AI generated code: check intent, dependencies, tests and security, then turn it into a routine your team repeats.
Set up Keycloak on Kubernetes with PostgreSQL, TLS ingress, HA clustering, a hardened image and realms as code. Step-by-step, production-minded guide.