Practical guide
AI-Assisted Software Engineering
Context, codebases, work systems, reviews, agents, and orchestration — a practical path through AI-assisted software engineering.
Start the seriesWriting
Thoughts on AI, software engineering, and how systems are becoming intelligent.
I write to understand ideas better — and to make them clearer for others working with or around these systems.
Choose Your Path
Start with the reader path closest to what brought you here.
Path 01
New to AI concepts
Start with plain-English foundations for AI, machine learning, LLM systems, and the wider AI ecosystem.
Path 02Using AI coding assistants
Follow the ordered software engineering series on context, repositories, review, agents, and orchestration.
Path 03Leading AI adoption
Read about context, knowledge debt, process, evidence, and the operating model changes behind useful AI adoption.
Path 04Exploring practical systems
Jump to system stories, workflow experiments, demos, and practical builds connected to the writing.
Start With the Main Series
A structured reading path for software engineers working with AI assistants.
Recommended Starting Points
A manually curated set of strong entry points for first-time readers before going deeper into the clusters below.
Business Rules as Context: The Missing Layer in AI-Assisted Development
AI assistants can read the code. They can read the ticket. That still may not tell them what the software is allowed to do.
Read articleKnowledge Debt Is the New Technical Debt
Technical debt makes code harder to change. Knowledge debt makes the system harder to understand.
Read articleDocumentation Is Becoming Executable Context
How AI-assisted software work is changing documentation from a passive reference into an active part of delivery.
Read articleTopic Clusters
Browse the writing by theme. These are topic groupings, not date-based feeds or separate series.
Topic cluster
AI Foundations
Begin here if you want the concepts behind AI, machine learning, data science, and LLM systems explained without hype.
- AI, Machine Learning and Data Science — Explained Simply AI Foundations
- Understanding the AI Ecosystem AI Systems
- How Modern LLM Systems Really Work AI Systems
Prefer guided practice? Follow the staged path from Python foundations for data science through data analysis and machine learning.
Topic cluster
AI-Assisted Software Engineering
Practical essays on the context, repository structure, prompts, and review habits that make AI-assisted delivery more reliable.
- AI-Assisted Software Engineering Series Ordered Path
- Beyond the Repository: Why AI Needs Work Context Too Work Context
- How I Structure Repositories So AI Can Actually Understand Them Repository Context
- Stop Prompting Harder. Start Giving Better Context. Context Design
- Coding Assistants Are Not Junior Developers Engineering Judgment
Topic cluster
Architecture in the AI Era
How architecture, boundaries, contracts, ownership, and review change when AI makes implementation faster.
Topic cluster
Engineering Context and Knowledge
How business rules, documentation, standards, and organizational knowledge become usable context for humans and AI assistants.
- Business Rules as Context: The Missing Layer in AI-Assisted Development Business Rules
- Knowledge Debt Is the New Technical Debt Knowledge Debt
- Documentation Is Becoming Executable Context Documentation
- Why AI Punishes Tribal Knowledge in Software Teams Tribal Knowledge
- The Context Supply Chain: How Organizational Knowledge Reaches AI Output Knowledge Flow
Topic cluster
AI Agents and Review
Practical judgment for using AI assistants, reviewing generated work, assigning tasks, and coordinating agent-like workflows.
- The Agent Risk Register: What to Check Before Letting AI Act Governance
- From Developer to AI Orchestrator Series
- Using Multiple AI Agents as a Software Engineering Team Series
- Why Reviewing AI-Generated Work Is a Different Skill Series
- Not All Engineering Tasks Belong to AI Series
- How To Tame Your Agent? Series
Topic cluster
Review and Governance
How teams review AI-assisted work, evaluate evidence, scale scrutiny with risk, and keep human accountability visible.
Topic cluster
Agile, Process, and Engineering Leadership
For architects and leaders thinking about AI adoption, delivery systems, process quality, evidence, and engineering standards.
Topic cluster
Systems and Experiments
Articles connected to practical builds, workflow experiments, and system-level explorations. The deeper build notes and demos live in Systems.
Writing to systems
Looking for the practical builds?
The Writing page explains the ideas and tradeoffs. The Systems section shows applied experiments, demos, architecture notes, and working examples.
Latest Writing
Recent articles for returning readers, listed by publication date.
- 06 Jul 2026 Why Architecture Matters More in the AI Era Architecture in the AI Era
- 04 Jul 2026 The Agent Risk Register: What to Check Before Letting AI Act Review and Governance
- 04 Jul 2026 AI Governance Without Bureaucracy Review and Governance
- 03 Jul 2026 The Human + AI Responsibility Map Review and Governance
- 01 Jul 2026 Human Review Gates in AI-Assisted Delivery Review and Governance
- 30 Jun 2026 AI Code Review Is Not Just Code Review Review and Governance
- 29 Jun 2026 Business Rules as Context: The Missing Layer in AI-Assisted Development Engineering Context
- 29 Jun 2026 Knowledge Debt Is the New Technical Debt Engineering Context
- 27 Jun 2026 Documentation Is Becoming Executable Context Engineering Context
- 26 Jun 2026 Why AI Punishes Tribal Knowledge in Software Teams Engineering Context
- 26 Jun 2026 The Context Supply Chain: How Organizational Knowledge Reaches AI Output Engineering Context
- 25 Jun 2026 Enterprise AI Adoption Is a Context Problem Enterprise AI
- 25 Jun 2026 Stronger Evidence Chains for AI-Assisted Engineering Changes AI Review
- 24 Jun 2026 Process as Code: Making Engineering Standards Visible to Humans and AI Assistants Engineering Standards