Architecting for AI
Everything Changes, Except the Fundamentals
“Am I here just to press Enter?”
Vendors say AI will cut delivery effort by half. The people doing the work are quietly asking whether they still have a job. Both are reacting to the same thing: a component that is clever, fast, cheap, probabilistic and unaccountable has arrived inside systems designed before it existed.
What the book covers
Architecting for AI separates the hype from the engineering. Part I shows what the model really changes: the market, the delivery method, the architecture and the risk register. Part II shows what still holds: capability maps, domain models, data discipline and decisions written down. Part III gives the method for deciding, feature by feature, what to hand to AI and what to keep.
The stories belong to Archie, an architect who made every mistake in this book so you need not.
AI amplifies whatever you give it, including the mess.
The model read what it was given. The system gave it the wrong page.
Press Enter, by all means. Then read what comes out.
Contents
Preface · Introduction: “Am I here just to press Enter?”
Part I. The Disruption
- The Market Shifts: When Effort Stops Being the Product
- The Method Strains: Agile and the SDLC Meet AI-Written Code
- The Architecture Breaks: Probabilistic Parts in Deterministic Systems
Part II. What Still Holds
- Why Architecture Still Matters: TOGAF, DDD and the Fundamentals AI Doesn't Change
- Data Still Decides: RAG and Document Intelligence
Part III. An AI Framework That Fits
- Extending the ADM for AI: A Framework That Fits
- Evaluation Is the New Testing
- Agents Inside Guardrails
- Trust by Design: Governance and Security for Regulated AI
Closing: “Architects Are Next?” · Appendices: glossary, ADR template for AI decisions, evaluation checklist, AI reference architecture, choosing a cloud AI platform