Category
Mutation testing tests the tests themselves. Here is why that old idea may become an important quality signal when AI agents generate both production code and its test suite.
Read more: Mutation Testing for Agent-Written CodeWhy voice is a natural interface for discovery, learning, research, and exploratory conversations with modern AI agents.
Read more: Voice Interface for AI Discovery and LearningA practical implementation of diagnosis-first self-healing end-to-end tests using Claude Code, Playwright, and GitHub Actions, with guarded repair pull requests and a complete example repository.
Read more: Self-Healing Tests with AI: Triage Before RepairA practical look at AI coding agents in 2026: critical-thinking models, agent workflows, reusable skills, costs, and the limits of open models.
Read more: AI Coding Agents in 2026: Discovery, Skills, Costs, and What Comes NextNotes from setting up Bonsai Image 4B locally on Apple Silicon, debugging the first failed path, wrapping the working pipeline in a reusable CLI, and using it from any project directory.
Read more: Local Image Generation with Bonsai Image 4BA practical mental model for developers: understand LLMs, AI agents, function calling, and why coding agents built on the same model behave differently.
Read more: LLMs vs AI Agents: A Practical Mental Model for DevelopersA practical guide to Playwright CLI for AI agents: run browser actions from the terminal, load Playwright Skills, mock APIs, capture traces, and build isolated agentic tests.
Read more: Playwright CLI, Skills and Isolated Agentic TestingA pragmatic analysis of agentic software development in 2026: real productivity gains, enterprise constraints, code review challenges, and why architecture, testing, and process discipline matter more than ever.
Read more: The Current State of Agentic Software DevelopmentLearn what AI testing skills are and how they differ from RAG, MCP, and tool calling. A practical guide to building efficient AI testing agents with reusable playbooks.
Read more: AI Testing Skills: The Evolution Beyond RAG and MCPWhy AI coding is moving back to the terminal. A practical look at AI CLI agents and terminal-based AI coding assistants, multi-repo workflows, microservices, architecture-first thinking, and verification-driven development.
Read more: Why AI Coding Is Moving Back to the Terminal (CLI Agents)Learn AI faster with three paths: theory-first student, power-user workflows, and builder tooling. Understand LLM fundamentals, prompting, agents, and how to connect them.
Read more: Learning AIDiscover agentic testing: how AI agents can test applications through white-box code analysis and black-box exploration using Playwright MCP, Chrome DevTools MCP, and terminal tools. Learn practical examples with Java Spring Boot and React, explore benefits and challenges, and see how coding agents are becoming testing agents.
Read more: Agentic Testing - The New Testing ApproachLearn how to build and test a practical RAG workflow with Gemini File Search, including managed retrieval, grounding checks, and implementation trade-offs.
Read more: Building RAG with Gemini File SearchLearn practical strategies to test and validate Large Language Model (LLM) systems. Discover how to ensure reliability, evaluate AI outputs, and maintain quality in real-world LLM-powered applications.
Read more: Testing LLM-based SystemsDiscover Test-Driven AI Development (TDAID) — a modern approach that merges Test-Driven Development (TDD) with AI-powered software engineering. Learn how to apply TDD principles to AI coding agents, build reliable feedback loops, and prevent regressions in non-deterministic systems. This guide explains why TDD is making a comeback in the AI era, how to structure agentic workflows around tests, and what practices help teams deliver high-quality, maintainable code with AI tools like Claude, Cursor, and Gemini.
Read more: Test-Driven AI Development (TDAID)A deep dive into Playwright Agents and the Model Context Protocol (MCP) — how Microsoft’s latest AI-powered Playwright release automates test planning, script generation, and self-healing browser tests across Chrome, Firefox, and WebKit.
Read more: Understanding Playwright AgentsHow DevTools MCP enables AI agents to record real performance traces (LCP/CLS/TBT), analyse them, and apply fixes—bringing Lighthouse-style audits into an iterative debugging session. Notes on INP (field) vs TBT (lab) included.
Read more: AI + Chrome DevTools MCP: Trace, Analyse, Fix PerformanceLearn how Mermaid diagrams improve technical documentation and AI workflows by expressing architecture as code that stays readable, maintainable, and current.
Read more: Mermaid diagrams: When AI Meets DocumentationPractical guidance for using agentic AI with Playwright to design, generate, and validate UI and API tests with better speed, quality, and reliability.
Read more: Playwright Agentic Coding TipsA practical landscape of AI tooling for developers across IDE copilots, project starters, CLI assistants, and autonomous agents with trade-offs.
Read more: AI Tooling for Developers LandscapeLearn how Playwright MCP combines AI agents, browser automation, and the Model Context Protocol (MCP) to enable intelligent testing, debugging, and documentation. Explore how it works, its architecture, and real-world use cases.
Read more: How does Playwright MCP work?A detailed walkthrough of how I use AI daily for coding, learning, writing, research, and content creation, including prompts, tools, and workflows.
Read more: How I use AIReflections on "vibe coding", context windows, tips, and the real costs of AI-driven development, plus a live case-study building a websocket traffic monitor with Cursor and Sonnet agents.
Read more: AI vibe coding notes from the basementA comprehensive guide to evaluating AI-powered IDEs based on live code suggestions, LLM chat integration, RAG performance, and agent capabilities for enhanced development workflows.
Read more: From Live Suggestions to Agents: Exploring AI-Powered IDEsPersonal insights on effectively using AI tools for software development, highlighting practical tips for prompt engineering, understanding LLM limitations, and leveraging AI-powered coding assistants.
Read more: The rise of AI Driven Development