Author and loudmouth on software development. Works at Thoughtworks. Also hikes, watches theater, and plays modern board games.
NEW POST
Will there be source code in the future? To wrestle with this, we have to understand what code is. Unmesh Joshi sees code as having two distinct but intertwined purposes: instructions to a machine and a conceptual model of the problem domain.
NEW POST
Thoughtworks internal IT use a workflow for agentic programming called Structured-Prompt-Driven Development (SPDD). Wei Zhang and Jessie Jie Xia describe how this works with a simple example with details in a github project.
NEW POST
ADRs are short documents that capture a decision, structured into logs that reveal a history of architectural thinking for a product
https://martinfowler.com/bliki/ArchitectureDecisionRecord.html
NEW POST
The quality of what AI coding assistants produce depends on how well the prompter articulates team standards. Rahul Garg proposes treating such instructions as infrastructure: versioned, reviewed, and shared artifacts.
https://martinfowler.com/articles/reduce-friction-ai/encoding-team-standards.html
A trans friend of mine said that after Twitter stopped banning trans harassment, it took only 12 hours before she started getting death threats. Do we have Free Speech if bullies are allowed to make people afraid to speak?
NEW POST
Modern hardware is remarkably fast, but software often fails to leverage it. Caer Sanders guides their work with mechanical sympathy - software that is sympathetic to its underlying hardware. They distill this practice into everyday principles: predictable memory access, awareness of cache lines, single-writer, and natural batching.
https://martinfowler.com/articles/mechanical-sympathy-principles.html
NEW POST
@bboeckel@toot.thoughtworks.com wrote some initial thoughts about Harness Engineering last month. She's been researching and thinking more about this in the weeks since and has now written a thoughtful mental model for understanding harness engineering that we think will help people to drive coding agents more effectively.
NEW POST
I've heard a number of reports recently about people setting up LLM agents to work on their email and other communications. I think this is extremely risky
Fragments: LLMs make our days harder, an LLM reacts badly to a rejected pull request, the Promptware Kill Chain, horror and elation trying Claude Code for two weeks, Free Speech Poseurs' silence to real threats
Fragments: updated guide on AI coding, video on harness engineering, how long should a function be, the problems of Software Brain and why AI is unpopular
Fragments: pragmatic summit video with Kent and Gergely, virtue of laziness, TDD and prompts, inspiration from Dark Star
Last night I saw Central Square Theater’s excellent production of Breaking the Code. It’s about Alan Turing, who made a monumental contribution to both my profession and the fate of free democracies. Well worth seeing if you’re in the Boston area this month.
https://www.centralsquaretheater.org/shows/breaking-the-code-2026/
Fragments: two podcasts, a worryingly well-done supply-chain attack, framework for tech documentation, and a particularly thoughtful AI coding experience
Fragments: Detailed report on the Thoughtworks AI retreat, should we write a manifesto for AI-enabled development, is spec-driven development the return of waterfall, LLMs perform better in healthy codebases
NEW POST
Rahul Garg finishes his series on reducing the friction in AI-Assisted Development. He proposes a structured practice that takes learnings from AI sessions and feeds them back into the team's shared artifacts, turning individual experience into collective improvement.
https://martinfowler.com/articles/reduce-friction-ai/feedback-flywheel.html
NEW POST
Rahul Garg sees a frustration loop when working with AI and identified five patterns to help. Here's the first: priming the LLM with knowledge about the codebase and preferred coding patterns.
https://martinfowler.com/articles/reduce-friction-ai/knowledge-priming.html
Fragments: open-source framework for prompting patterns, musician sues google for defamation, apple is thinking differently about AI spending, running LLMs locally, will The Genie be caught in the tar pit?
NEW POST
Rahul Garg describes a structured conversation with an AI agent that mirrors whiteboarding with a human pair: progressive levels of design alignment before any code, reducing cognitive load, and catching misunderstandings at the cheapest possible moment.
https://martinfowler.com/articles/reduce-friction-ai/design-first-collaboration.html
Fragments: security with OpenClaw, impressions from Pragmatic Summit, era of highly bespoke software, life-size pocket map
Fragments: three layers of system health, AI as cognitive system 3, what's expensive if agents make coding free, and the future of source code
NEW POST
There's been much talk about how AI agents affect the workflow loops of software development. Kief Morris focuses on the goal of turning ideas into outcomes by building and managing the working loop.
https://martinfowler.com/articles/exploring-gen-ai/humans-and-agents.html
Fragments: code review isn't just catching bugs, what role for observability in agentic programming, what we lose with GPS over maps
Fragments: how organizations are using AI, reflections from the Utah retreat, agentic engineering patterns, inserting friction for security, training biological neural networks
Fragments: supervisory engineering, 2 sets of 8 levels, generating code to an architecture, perils of detecting AI-aided writing, should humans review code?
NEW POST
@bboeckel@toot.thoughtworks.com explains why OpenAI's recent write-up on "Harness Engineering" is a valuable framing of a key activity in AI-enabled software development. Harness includes: context engineering, architectural constraints, and garbage collection of the code base.
https://martinfowler.com/articles/exploring-gen-ai/harness-engineering.html
NEW POST
Conversations with AI are ephemeral, decisions made early lose attention as the conversation continues, and disappear entirely with a new session. Rahul Garg explains how Context Anchoring externalizes the decision context into a living document.
https://martinfowler.com/articles/reduce-friction-ai/context-anchoring.html
Fragments: reporting fines, engaging with gen AI, experience engineering, watching the ralph loop, migrating COBOL
NEW POST
Naresh Jain has long had a discomfort with software patents. But a direct experience of patent aggression, together with the practical constraints faced by startups, led him to resort to defensive patenting as as a shield in this asymmetric legal environment.
https://martinfowler.com/articles/patents-reluctant-pragmatism.html
Fragments: 80,000 people's opinion on AI, fixing the common gap in spec-driven development, weakening defenses against covert attacks on the U.S.
Fragments: 34th Thoughtworks Technology Radar, what happens when developers don't read the LLM's code, DirectFile and tech in large organizations
NEW POST: Recently I had an enlightening chat with Xu Hao (our Head of Technology in China) about the techniques he's using to prompt ChatGPT to generate useful code
