All Articles 35
RSSPostel's Law for the human-AI interface
When one end of a software contract is an LLM, Postel's Law isn't a courtesy — it's load-bearing. The shape that lets you ship: document-as-contract.
Demo mode as a pattern for software
Ship every software product with built-in demo mode. The pattern serves authors, users, sales teams, and compliance — and synthesis engineering makes it cheap e
Synthesis Console: open-source tooling for synthesis engineering
An open-source local tool that renders project management markdown and YAML as browsable, searchable pages. Three dependencies, no client-side framework, and a
Transferable Knowledge: The Fifth Pillar of Synthesis Coding
You understand your AI-generated code. Can your teammates? Transferable Knowledge is the fifth pillar of synthesis coding -- ensuring AI-assisted work is compre
"All tests pass" is a warning, not a clearance
Why a green test suite after a schema change should trigger suspicion, not confidence. A verification methodology that catches what tests structurally cannot —
Stop asking me: configuring Claude Code permissions for uninterrupted flow
A practitioner guide to eliminating Claude Code approval prompt fatigue. Why granular command patterns fail for compound commands, the Bash(*) plus deny list ap
Managing AI agent skills at scale: a three-repo architecture
A three-repo architecture for managing public, private, and team AI agent skills with provenance tracking, drift detection, and synthesis merge — the first stan
Synthesis Skills: install methodology directly into your AI workflow
22 open-source Agent Skills encoding synthesis coding and synthesis engineering methodology. One command installs code review, content quality, project manageme
Synthesis merging: what happens after the first PR
Synthesis merging goes beyond conflict resolution. It is the creative act of integrating contributions into a coherent whole, making the combined result better
When a code review runbook becomes an upgrade playbook
I built a code review runbook to find problems. Then I used it on codebases I owned, and the review categories became execution phases. A checklist for assessme
What reviewing real codebases taught me about code review
I published a 900-check code review runbook. Then I used it on real engagements. The checklist worked, but the real lessons were about the process — starting wi
When Someone Else Contributes to Your Synthesis-Coded Project
Standard merge workflows break down for synthesis-coded projects. The adopt-and-adapt pattern provides a disciplined integration methodology that respects contr
The research lineage from recursive neural networks to human-AI collaborative development
Tracing the intellectual thread from Richard Socher's compositional representations through DecaNLP to the systems-level engineering challenges of human-AI soft
From learned representations to engineered context: what Richard Socher's research tells us about working with AI
Richard Socher's research arc — from GloVe to DecaNLP to 'managers of AI' — maps directly onto the principles behind synthesis coding. The connections are struc
Code Review That Scales: An Open-Source Runbook for Agentic Engineering
Most code review checklists are either too shallow or too heavy. This open-source runbook tiers review depth by project complexity — and is designed for agentic
The Part of Your Job AI Can't Do (And Why It Matters More Now)
There's a lot of anxiety about AI making engineering skills obsolete. But the most valuable part of what you do was never the typing. The judgment, the architec
RAG Architecture Lessons from Practice
Building a retrieval-augmented generation system revealed patterns the tutorials don't cover. Contractions break search. Not everything needs an LLM. Full docum
Data Format Contracts for AI Pipelines
When tools interact, implicit assumptions break silently. Explicit data format contracts prevent the debugging sessions you don't have time for.
Context Loss and How to Prevent It
Why AI assistants forget what you told them, and practical strategies to prevent it. The difference between context that survives and context that gets lost.
The Foundation-First Pattern
Why the most effective AI-assisted projects start with humans writing code by hand. The counterintuitive pattern that makes everything else work.
How Claude's Memory Actually Works (And Why CLAUDE.md Matters)
Understanding Claude's context architecture changes how you work with it. The tradeoffs between automatic continuity and on-demand depth explain why persistent
What OpenAI's Sora Build Teaches Us About Synthesis Coding
Four engineers shipped a #1 Play Store app in 28 days using AI agents. Their approach validates the patterns I've been writing about — and adds new ones worth s
Scaling Synthesis Coding in Your Organization
A practical guide for CTOs and engineering leaders: cost analysis, team rollout strategy, training curriculum, and metrics for adopting synthesis coding at s...
Building ownwords: A Synthesis Coding Case Study
What separates synthesis coding from vibe coding isn''t the tools — it''s the decisions. This technical case study walks through the architectural choices,...
Why Synthesis Coding Still Writes Code in the Age of LLMs
The answer is not "just let the model do it" — and code matters more, not less, as AI gets dramatically better Last spring, my son Fitz and I had an aftern...
Vibe Coding and Synthesis Coding: Two Complementary Approaches
Why the conversation isn''t about which approach is better — it''s about knowing when to use each This blog post is for software engineers, engineering lea...
Polyrepo Synthesis: Synthesis Coding Across Multiple Repositories with Claude Code in Visual Studio Code
I wrote this blog post for software engineers, architects, and technical leads. It is code-heavy and implementation-focused. This weekend I was working acr...
Seventeen years ago, I built a tool for the open Web. This weekend, I modernized it using Synthesis Coding with Claude Code AI
In 2008, I released a WordPress plugin called Blogroll Links. The plugin displayed lists of links on WordPress pages using a shortcode. But the idea behind...
Iterative Context Building: The Fourth Pillar of Synthesis Coding
AI effectiveness compounds when context accumulates systematically. The fourth pillar of synthesis coding treats context like compound interest -- each session
Active System Understanding: The Third Pillar of Synthesis Coding
AI can generate code faster than you can read it. That is exactly why you must read it. The third pillar of synthesis coding is active system understanding.
Systematic Quality Standards: The Second Pillar of Synthesis Coding
AI-generated code should meet the same quality standards as human-written code. But the way you achieve those standards changes fundamentally when AI is your co
Human Architectural Authority: The First Pillar of Synthesis Coding
AI can write code faster than any human. But it cannot hold a consistent architectural vision across months of development. That is why the first pillar of synt
Synthesis Coding with Claude Code: Technical Implementation and Workflows
A hands-on guide to practicing synthesis coding (a.k.a. synthesis engineering) with concrete examples, real workflows, and lessons from production systems ...
The Synthesis Engineering Framework: How Organizations Build Production Software with AI
From individual practice to organizational capability: a systematic approach to human-AI collaboration in professional software development This blog post ...
Synthesis Engineering: The Professional Practice Emerging in AI-Assisted Development
Why the most effective engineering organizations are developing systematic approaches that go beyond vibe coding — and why this practice needs a name This ...