agentic-ai 126
- Which Copilot Studio Harness? — A Decision Framework for Enterprise Teams
- Copilot Studio Multi-Agent Architecture — Connected Agents and the A2A Protocol
- Copilot Studio Skills and Memory — Modular Agents with Persistent Context
- Inside the Copilot Studio Agents Experience — Build, Preview, Evaluate, Monitor
- The GitHub Copilot Harness — Copilot Studio Gets a New Agent Runtime
- AI Governance at Engineering Scale — What Actually Works
- The Engineering Skill Stack for 2027 — What to Invest in Now
- Voice and Audio Agents in Engineering Workflows — Practical Patterns
- Fine-Tuning vs. RAG in 2026 — An Updated Decision Framework
- Supply Chain Security for AI Systems — Models, Packages, and Data
- AI-Native Database Interfaces — Beyond Text-to-SQL
- Real-Time Agents — Latency Patterns for Interactive AI Systems
- Agent Swarms vs. Single Powerful Agents — When Each Architecture Makes Sense
- Long-Context Strategies for Large Codebases — When the Repo Won't Fit
- Multimodal Agents — Using Vision + Code for UI Automation and Testing
- Technical Leadership in the Age of AI Agents — What Changes, What Doesn't
- Knowledge Management in AI-First Teams — Staying Current Without Burning Out
- The Engineering Manager's Guide to AI Agent Deployment
- Measuring AI Engineering Productivity — The Metrics That Actually Matter
- The AI Platform Engineering Team — A New Organisational Function
- Spec-Driven Development at Enterprise Scale — Adoption Patterns That Work
- Compliance Automation with AI Agents — Audit Trails, Policy Checks, and Evidence Collection
- OpenSpec — An Open Standard for Machine-Readable AI Specifications
- Prompt Injection Defences In Depth — 2026 Attack Patterns and Mitigations
- The BMAD Method — Structured Multi-Agent Development with AI
- GitHub Speckit — Spec-First Development in the Copilot Ecosystem
- Testing Non-Deterministic Systems — Strategies That Actually Work
- AWS Kiro — The IDE Built Around Specs, Not Prompts
- Spec-Driven Development — Why Specs Are the New Source of Truth
- Agent Incident Response — When Your AI System Goes Wrong
- Multi-Tenant AI Infrastructure — Isolation, Quotas, and Cost Attribution
- Building an Internal LLM Gateway — Control, Cost, and Compliance
- Agent Sandboxing — Isolation Patterns for Safe Tool Execution
- Semantic Caching — Cutting AI Costs Without Cutting Quality
- Debugging Production Agents — Reading the Trace
- Agent-to-Agent Negotiation — Coordination Without a Central Planner
- Spec-Driven Development — Writing Specs That AI Agents Can Execute
- Self-Healing CI — Agentic Pipelines That Fix Their Own Failures
- Autonomous PR Agents — How to Review Code When AI Opens the PR
- MCP Goes Stateless — What the July 2026 RC Means for Your Stack
- Beyond Vibe Coding — What AI-Native Engineering Actually Looks Like
- Context Engineering — The Discipline That Replaced Prompt Engineering
- Harness Engineering — Building the AI Control Plane
- Where Agentic AI Goes Next — The Honest View
- Open-Source vs Commercial Models — The 2026 Decision
- The Reasoning Model Revolution — Beyond Next-Token Prediction
- CrewAI for Enterprise Multi-Agent Workflows
- Building Production Agents with LangGraph — A Hands-On Walkthrough
- Scaling Agentic Systems — Cost, Latency, and Reliability
- Observability for Complex Agentic Systems
- Evaluating Agent Quality at Production Scale
- EU AI Act for Engineers — What You Actually Need to Do
- Agent Containment — Controlling Blast Radius in Autonomous Systems
- Prompt Injection in Production Agents — Attack Patterns and Defences
- The 62% Problem — Security Flaws in AI-Generated Code
- Tool Orchestration at Scale — Beyond Simple Function Calling
- Long-Term Memory Patterns for Production Agents
- Multi-Model Orchestration — SLM + LLM Hybrid Architectures
- Reasoning Models for Agents — When Thinking Tokens Are Worth It
- Computer Use Agents — The New Agentic Paradigm
- Stateful Agents — Managing State in Production
- Evaluating RAG Pipelines — The Metrics That Matter
- Chunking Strategies That Actually Work in Production RAG
- Vector Databases in 2026 — Which to Use and When
- Context Window Management in Production Agents
- RAG vs Fine-Tuning — The Hybrid Answer in 2026
- RAG in Production — Beyond the Basics
- The LLM Pricing Collapse — How $0.10/Million Tokens Changes Architecture
- The 13% Problem — Why Enterprise AI Adoption Is Failing
- LangGraph vs CrewAI — Picking the Right Agent Framework in 2026
- Fable 5 Launched. The Government Killed It Three Days Later.
- A2A Protocol — Agent-to-Agent Communication at Enterprise Scale
- MCP Explained — The Protocol That Connects AI to Everything
- The Model Wars Are Over — What Model Convergence Means for Engineers
- Production Agentic AI — Engineering for Scale: 30-Day Plan
- One Year of Building an AI-First Team — What I Learned
- Future-Proofing Your AI Toolchain Against Pricing Changes
- What Doesn't Change — The Human Core of Great Engineering
- Measuring ROI and Making the Business Case for AI
- Security, IP, and Compliance in an AI-First Team
- Scaling AI Adoption Across a Larger Engineering Org
- Enterprise AI Governance for Engineering Teams
- Avoiding Over-Reliance and the Skill Atrophy Problem
- Learning and Upskilling in an AI-First Culture
- Hiring for an AI-First Engineering Team
- The AI-Skeptic on Your Team — How to Bring Them Along
- Senior Engineers in an AI-First Team — What Seniority Means Now
- Junior Engineers in an AI-First Team — Different, Not Lesser
- Cross-Functional Communication — PMs, Designers, and AI Engineers
- AI-Assisted Incident Response — When Production Breaks
- Knowledge Transfer and Institutional Memory with AI
- Onboarding New Engineers into an AI-First Codebase
- Architecture Decisions with AI — ADRs, Design Reviews, and Technical Debt
- Documentation Culture in an AI-First Team — Better or Worse?
- AI in the CI/CD Pipeline — Automated Quality Gates
- Testing in an AI-First Team — Trust, Verification, and Coverage
- AI-First Pull Request and Commit Hygiene
- Code Review Culture When AI Writes the Code
- Writing Code as a Team with AI — Pair Programming Norms
- AI-First Sprint Planning and Task Breakdown
- Measuring Progress — What Metrics Actually Matter for an AI-First Team
- AI-First Team Culture: Norms, Expectations, and Psychological Safety
- Rethinking Team Roles in an AI-First World
- The Full AI Toolchain for Engineering Teams
- The AI-First Team Maturity Model — Where Is Your Team Today?
- What Does 'AI-First Engineering Team' Actually Mean?
- The AI-First Engineering Team — 30-Day Blog
- 30 Days Done — What I Learned, What Changed, What's Next
- Multi-Agent Debugging and Observability — Staying Sane
- Designing Multi-Agent Workflows in Copilot Studio
- Microsoft Copilot Studio for Developers — What You Need to Know
- Evaluating Coding Agent Quality — Beyond 'Did It Run?'
- Multi-Step Coding Agents — Patterns and Failure Modes
- Agent Memory and Context Management — The Hard Part
- Tool Use in AI Agents — Patterns That Work in Production
- Building Your First Coding Agent — A Practical Walkthrough
- What Makes a Good Coding Agent — Design Principles
- Copilot Workspace — Hands-On with Agentic GitHub Copilot
- 11 Years In, AI-Augmented — How My Workflow Actually Changed
- Choosing Your AI Toolchain — Claude Code, Copilot, or Copilot Studio?
- Agent Skills 101 — Building Blocks of Useful AI Agents
- The Agentic AI Mental Model Every Engineer Needs
- AI in the SDLC — The Honest State of Things in 2026
- Why I'm Writing 30 Days of AI Engineering
- Agentic AI
- 30 Days of AI Engineering — My Content Plan as a Lead AI Engineer