Archives
- 08 Jul The Reasoning Model Revolution — Beyond Next-Token Prediction
- 07 Jul CrewAI for Enterprise Multi-Agent Workflows
- 06 Jul Building Production Agents with LangGraph — A Hands-On Walkthrough
- 05 Jul Scaling Agentic Systems — Cost, Latency, and Reliability
- 04 Jul Observability for Complex Agentic Systems
- 03 Jul Evaluating Agent Quality at Production Scale
- 02 Jul EU AI Act for Engineers — What You Actually Need to Do
- 01 Jul Agent Containment — Controlling Blast Radius in Autonomous Systems
- 30 Jun Prompt Injection in Production Agents — Attack Patterns and Defences
- 29 Jun The 62% Problem — Security Flaws in AI-Generated Code
- 28 Jun Tool Orchestration at Scale — Beyond Simple Function Calling
- 27 Jun Long-Term Memory Patterns for Production Agents
- 26 Jun Multi-Model Orchestration — SLM + LLM Hybrid Architectures
- 25 Jun Reasoning Models for Agents — When Thinking Tokens Are Worth It
- 24 Jun Computer Use Agents — The New Agentic Paradigm
- 23 Jun Stateful Agents — Managing State in Production
- 22 Jun Evaluating RAG Pipelines — The Metrics That Matter
- 21 Jun Chunking Strategies That Actually Work in Production RAG
- 20 Jun Vector Databases in 2026 — Which to Use and When
- 19 Jun Context Window Management in Production Agents
- 18 Jun RAG vs Fine-Tuning — The Hybrid Answer in 2026
- 17 Jun RAG in Production — Beyond the Basics
- 16 Jun The LLM Pricing Collapse — How $0.10/Million Tokens Changes Architecture
- 15 Jun The 13% Problem — Why Enterprise AI Adoption Is Failing
- 14 Jun LangGraph vs CrewAI — Picking the Right Agent Framework in 2026
- 14 Jun Fable 5 Launched. The Government Killed It Three Days Later.
- 13 Jun A2A Protocol — Agent-to-Agent Communication at Enterprise Scale
- 12 Jun MCP Explained — The Protocol That Connects AI to Everything
- 11 Jun The Model Wars Are Over — What Model Convergence Means for Engineers
- 10 Jun Production Agentic AI — Engineering for Scale: 30-Day Plan
- 09 Jun One Year of Building an AI-First Team — What I Learned
- 09 Jun Future-Proofing Your AI Toolchain Against Pricing Changes
- 08 Jun What Doesn't Change — The Human Core of Great Engineering
- 08 Jun Copilot vs. Alternatives — Does the New Pricing Change the Build-vs-Buy Equation?
- 07 Jun Measuring ROI and Making the Business Case for AI
- 07 Jun Calculating Copilot ROI Under the New Pricing — The Honest Maths
- 06 Jun Security, IP, and Compliance in an AI-First Team
- 06 Jun Copilot Cost Governance for Enterprise Teams — Controls That Don't Kill Adoption
- 05 Jun Scaling AI Adoption Across a Larger Engineering Org
- 05 Jun Which Copilot Feature for Which Task — A Decision Framework
- 04 Jun Prompt Patterns That Cut Copilot Costs Without Cutting Value
- 04 Jun Enterprise AI Governance for Engineering Teams
- 03 Jun Avoiding Over-Reliance and the Skill Atrophy Problem
- 03 Jun Auditing Your Copilot Usage Before the Bill Arrives
- 02 Jun Learning and Upskilling in an AI-First Culture
- 02 Jun GitHub Copilot's New Pricing Model — The Token Economy Problem and How to Navigate It
- 01 Jun Hiring for an AI-First Engineering Team
- 31 May The AI-Skeptic on Your Team — How to Bring Them Along
- 30 May Senior Engineers in an AI-First Team — What Seniority Means Now
- 29 May Junior Engineers in an AI-First Team — Different, Not Lesser
- 28 May Cross-Functional Communication — PMs, Designers, and AI Engineers
- 27 May AI-Assisted Incident Response — When Production Breaks
- 26 May Knowledge Transfer and Institutional Memory with AI
- 25 May Onboarding New Engineers into an AI-First Codebase
- 24 May Architecture Decisions with AI — ADRs, Design Reviews, and Technical Debt
- 23 May Documentation Culture in an AI-First Team — Better or Worse?
- 22 May AI in the CI/CD Pipeline — Automated Quality Gates
- 21 May Testing in an AI-First Team — Trust, Verification, and Coverage
- 20 May AI-First Pull Request and Commit Hygiene
- 19 May Code Review Culture When AI Writes the Code
- 18 May Writing Code as a Team with AI — Pair Programming Norms
- 17 May AI-First Sprint Planning and Task Breakdown
- 16 May Measuring Progress — What Metrics Actually Matter for an AI-First Team
- 15 May AI-First Team Culture: Norms, Expectations, and Psychological Safety
- 14 May Rethinking Team Roles in an AI-First World
- 13 May The Full AI Toolchain for Engineering Teams
- 12 May The AI-First Team Maturity Model — Where Is Your Team Today?
- 11 May What Does 'AI-First Engineering Team' Actually Mean?
- 10 May The AI-First Engineering Team — 30-Day Blog
- 09 May 30 Days Done — What I Learned, What Changed, What's Next
- 08 May Multi-Agent Debugging and Observability — Staying Sane
- 07 May Connecting Copilot Studio Agents to Enterprise Systems
- 06 May Designing Multi-Agent Workflows in Copilot Studio
- 05 May Microsoft Copilot Studio for Developers — What You Need to Know
- 04 May Evaluating Coding Agent Quality — Beyond 'Did It Run?'
- 03 May Multi-Step Coding Agents — Patterns and Failure Modes
- 02 May Agent Memory and Context Management — The Hard Part
- 01 May Tool Use in AI Agents — Patterns That Work in Production
- 30 Apr Building Your First Coding Agent — A Practical Walkthrough
- 29 Apr What Makes a Good Coding Agent — Design Principles
- 28 Apr GitHub Copilot in Enterprise Governance Frameworks
- 27 Apr Copilot Workspace — Hands-On with Agentic GitHub Copilot
- 26 Apr Copilot for PR Descriptions, Docs, and Commit Messages
- 25 Apr GitHub Copilot for Test Generation — Does It Actually Work?
- 24 Apr Writing Better Prompts for GitHub Copilot in VS Code
- 23 Apr GitHub Copilot Beyond Autocomplete — The Features Most Engineers Miss
- 22 Apr Claude Code in Regulated Environments — A Security-First Look
- 21 Apr Integrating Claude Code into CI/CD Pipelines
- 20 Apr Claude Code for Code Reviews at Scale
- 19 Apr Prompt Engineering for Coding Tasks — What Actually Works
- 18 Apr Claude CoWork — Async AI Pair Programming in Practice
- 17 Apr Claude Code for Legacy Code Modernisation
- 16 Apr Setting Up Claude Code for Enterprise Teams
- 15 Apr 11 Years In, AI-Augmented — How My Workflow Actually Changed
- 14 Apr Choosing Your AI Toolchain — Claude Code, Copilot, or Copilot Studio?
- 13 Apr Agent Skills 101 — Building Blocks of Useful AI Agents
- 12 Apr The Agentic AI Mental Model Every Engineer Needs
- 11 Apr AI in the SDLC — The Honest State of Things in 2026
- 10 Apr Why I'm Writing 30 Days of AI Engineering
- 09 Apr GitHub Copilot
- 09 Apr GenAI
- 09 Apr Claude Code
- 09 Apr AI in SDLC
- 09 Apr Agentic AI
- 09 Apr Agent Skills
- 09 Apr 30 Days of AI Engineering — My Content Plan as a Lead AI Engineer