Fragments: responsibility for rogue agents, indicators of a bubble bursting, dread of AI, praise for gov.uk, getting data out of closed packages, eyes on Clacton martinfowler.com/fragments/20...

NEW POST Giles Edwards-Alexander does an experiment to see if decomposing a large function helps reduce token costs, suggesting that is may now be possible to measure the economic benefit of refactoring martinfowler.com/articles/exp...

The Economic Benefit of Refactoring

Notes from my Thoughtworks colleagues on AI-assisted software delivery

martinfowler.com

NEW POST Subagents get justified by time saved and parallel execution, but Rahul Garg explains that what really matters is protecting the orchestrator's context. martinfowler.com/articles/orc...

The Orchestrator's Tax

Use subagents to protect the orchestrator's working memory, not just to save time or run tasks in parallel.

martinfowler.com

Fragments: mismatched views of AI between engineering and C-suite, comparing dotcom and AI bubbles, LLMs build it we run it, law professors prefer LLM answers, using DSLs with LLMs, the stench of LLM-speak martinfowler.com/fragments/20...

Fragments: July 21

fragments 21 Jul 2026

martinfowler.com

NEW POST Nik Malykhin needed to run a Java 1.5 codebase on today's hardware. His initial try to use LLMs wasn't helpful, but he made progress when he guided the process with careful steps. martinfowler.com/articles/arc...

The Archaeologist’s Copilot

Lessons from modernizing a Java 1.5 codebase with AI, a stable Docker environment, and test-guided incremental refactoring.

martinfowler.com

NEW POST LLMs generate code incredibly fast, but to ensure they generate exactly what is intended, they need clear boundaries. Unmesh Joshi shares his experience using abstractions and Domain-Specific Languages (DSLs) to provide a strong harness to guide an LLM. martinfowler.com/articles/llm...

DSLs Enable Reliable Use of LLMs

Why Domain-Specific Languages and good abstractions make LLM code generation reliable and reviewable.

martinfowler.com

Fragments: FOSD discussions on harness engineering, self-hosting models, grand narrative, and bringing rocks. Saving money with fable, bleak future for developer education, does electron have a future, interactional and contributory expertise. martinfowler.com/fragments/20...

Fragments: July 13

fragments 13 Jul 2026

martinfowler.com

I added an appendix to my article on "Maintainability sensors for coding agents", about the little sidecar application I built to run all the computational sensors I had next to the agent, and give both human and agent the ability to monitor their state martinfowler.com/articles/sen...

NEW POST After setting out her factors of viability, @birgitta410.bsky.social now reports on her experiences with local LLMs for programming. She compares them with two standard tasks and tries the best LLM in day-to-day use martinfowler.com/articles/exp...

Experiences with local models for coding

Notes from my Thoughtworks colleagues on AI-assisted software delivery

martinfowler.com

NEW POST @birgitta410.bsky.social recently spent some time trying out running local LLMs for some programming tasks. In this memo she outlines the factors that influence how viable they are for the job. martinfowler.com/articles/exp...

Viability of local models for coding

Notes from my Thoughtworks colleagues on AI-assisted software delivery

martinfowler.com

Fragments: Second future of software development retreat, ethics of working with AI, censorship via DMCA, reacting to the high cost of tokens, a radical document in 1776 martinfowler.com/fragments/20...

Fragments: July 6

fragments 06 Jul 2026

martinfowler.com

NEW POST We've used AI with Bayer to help pharmaceutical researchers query decades of information buried in PDF reports. Sarang Sanjay Kulkarni describes the evolution from keyword-based search to a research assistant that can draft regulatory reports martinfowler.com/articles/rel...

Building Reliable Agentic AI Systems

AI helping pharmaceutical researchers query decades of information buried in PDF reports

martinfowler.com

Fragments: enjoying programming with LLMs, four types of LLM conversation, the crevasse between AI enthusiasts and skeptics, AI companies get product/market fit, the need for decentralization martinfowler.com/fragments/20...

Fragments: June 16

fragments 16 Jun 2026

martinfowler.com

Fragments: Dodgy metrics for AI usage, history of tech removing jobs, benchmarking closed and open models, LLMs multiply existing cruft, AI slop driving us crazy, I am the Global Interpreter Lock for agents martinfowler.com/fragments/20...

Fragments: June 2

fragments 02 Jun 2026

martinfowler.com

Fragments:GOTO chat with Kent Beck, using AI to help restructure a gnarly codebase, open-source and security, cognitive endurance, Gen Z future with AI, impact of AI on jobs, fumbling AI regulation martinfowler.com/fragments/20...

Fragments: May 27

fragments 27 May 2026

martinfowler.com

NEW § @birgitta410.bsky.social finishes her post on sensors for coding agents by examining the role of a test suite as a regression sensor, focusing on the role mutation testing can play. martinfowler.com/articles/sen...

Maintainability sensors for coding agents

A practical walkthrough of computational sensors on the path to production, with a deep dive on ESLint and static analysis as feedback for coding agents.

martinfowler.com

NEW POST Four of my colleagues share their experiences in applying good security practices to vibe coding. martinfowler.com/articles/vib...

The VibeSec Reckoning

Engineering guardrails teams must adopt to move safely from vibe-coded AI prototype to production.

martinfowler.com

NEW § @birgitta410.bsky.social adds exploration of three sensors for static code analysis, with mixed results. Computational sensors alone cannot help us much, AI is needed to add semantic interpretation, and consider trade-offs. martinfowler.com/articles/sen...

Maintainability sensors for coding agents

A practical walkthrough of computational sensors on the path to production, with a deep dive on ESLint and static analysis as feedback for coding agents.

martinfowler.com

NEW POST @birgitta410.bsky.social begins an article about her experiences with sensors in an agent harness. This first part looks at static analysis with basic code linting. martinfowler.com/articles/sen...

Maintainability sensors for coding agents

A practical walkthrough of computational sensors on the path to production, with a deep dive on ESLint and static analysis as feedback for coding agents.

martinfowler.com

Fragments: thoughts from a software development retreat, would I be a writer without text editors, use LLMs as functions, don't use LLM skills, is the future of everything lies? martinfowler.com/fragments/20...

Fragments: May 14

fragments 14 May 2026

martinfowler.com

NEW POST When I need to feed an LLM a lot of context, I can write it myself, or I can get an LLM to interview me for it. martinfowler.com/bliki/Interr...

bliki: Interrogatory LLM

To give an LLM context, I can ask the LLM to interview me for it

martinfowler.com

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. martinfowler.com/articles/wha...

What Is Code?

What is code actually for in the era of LLMs.

martinfowler.com

The Democratic Establishment is trying to rig a primary in Massachusetts. And they're using AI money to help. Stand up to this by going to bethfordemocracy.com and donating to help us reboot democracy

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? martinfowler.com/fragments/20...

Fragments: May 5

fragments 05 May 2026

martinfowler.com

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 martinfowler.com/fragments/20...

Fragments: April 29

fragments 29 Apr 2026

martinfowler.com

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. martinfowler.com/articles/str...

Structured-Prompt-Driven Development (SPDD)

A structured approach to using prompts to guide AI-assisted programming.

martinfowler.com

Fragments: 34th Thoughtworks Technology Radar, what happens when developers don't read the LLM's code, DirectFile and tech in large organizations martinfowler.com/fragments/20...

Fragments: April 21

fragments 21 Apr 2026

martinfowler.com

Fragments: pragmatic summit video with Kent and Gergely, virtue of laziness, TDD and prompts, inspiration from Dark Star martinfowler.com/fragments/20...

Fragments: April 14

fragments 14 Apr 2026

martinfowler.com

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. Worth seeing if you’re in the Boston area this month. www.centralsquaretheater.org/shows/breaki...

Why are the “age verification” laws bad? Have you ever tried to use a website and been stumped by a captcha? Maybe it asked you to pick every square with a bicycle, but you aren’t sure if that tiny bit of tire counts. Then you have to read numbers: is that a 7 or a 1? At some point, you give up.