Martin Fowler(@martinfowler)

Fragments: mismatched views of AI between engineering and C-suite, comparing dotcom and AI bubbles, ...

Martin Fowler (@martinfowler) — Tue, 21 Jul 2026 13:17:07 GMT

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/2026…

💬3🔄10❤️129👀17859📊35

⚡ Powered by xgo.ing

NEW POST Nik Malykhin needed to run a Java 1.5 codebase on today's hardware. His initial try to use...

Martin Fowler (@martinfowler) — Thu, 16 Jul 2026 13:37:51 GMT

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/archa…

💬5🔄6❤️45👀13000📊15

⚡ Powered by xgo.ing

NEW POST LLMs generate code incredibly fast, but to ensure they generate exactly what is intended, ...

Martin Fowler (@martinfowler) — Tue, 14 Jul 2026 13:30:52 GMT

NEW POST

LLMs generate code incredibly fast, but to ensure they generate exactly what is intended, they need clear boundaries. @unmeshjoshi  shares his experience using abstractions and Domain-Specific Languages (DSLs) to provide a strong harness.

martinfowler.com/articles/llm-a…

💬20🔄109❤️787👀84614📊272

⚡ Powered by xgo.ing

Fragments: FOSD discussions on harness engineering, self-hosting models, grand narrative, and bringi...

Martin Fowler (@martinfowler) — Mon, 13 Jul 2026 16:08:30 GMT

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/2026…

💬3🔄9❤️85👀21061📊28

⚡ Powered by xgo.ing

NEW POST After setting out her factors of viability, Birgitta Böckeler now reports on her experienc...

Martin Fowler (@martinfowler) — Wed, 08 Jul 2026 14:29:30 GMT

NEW POST

After setting out her factors of viability, Birgitta Böckeler 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/explo…

💬2🔄10❤️105👀16222📊28

⚡ Powered by xgo.ing

NEW POST Birgitta Böckeler recently spent some time trying out running local LLMs for some programm...

Martin Fowler (@martinfowler) — Tue, 07 Jul 2026 12:40:55 GMT

NEW POST

Birgitta Böckeler 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/explo…

💬5🔄30❤️159👀26399📊51

⚡ Powered by xgo.ing

Fragments: Second future of software development retreat, ethics of working with AI, censorship via ...

Martin Fowler (@martinfowler) — Mon, 06 Jul 2026 13:06:04 GMT

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/2026…

💬2🔄3❤️52👀16097📊14

⚡ Powered by xgo.ing

NEW POST We've used AI with Bayer to help pharmaceutical researchers query decades of information b...

Martin Fowler (@martinfowler) — Tue, 16 Jun 2026 12:38:27 GMT

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/relia…

💬6🔄26❤️271👀24590📊90

⚡ Powered by xgo.ing

Fragments: enjoying programming with LLMs, four types of LLM conversation, the crevasse between AI e...

Martin Fowler (@martinfowler) — Tue, 16 Jun 2026 06:47:40 GMT

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/2026…

💬2🔄18❤️131👀15916📊37

⚡ Powered by xgo.ing

Fragments: Dodgy metrics for AI usage, history of tech removing jobs, benchmarking closed and open m...

Martin Fowler (@martinfowler) — Tue, 02 Jun 2026 09:26:01 GMT

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/2026…

💬4🔄10❤️104👀16072📊26

⚡ Powered by xgo.ing

Fragments:GOTO chat with Kent Beck, using AI to help restructure a gnarly codebase, open-source and ...

Martin Fowler (@martinfowler) — Wed, 27 May 2026 19:46:03 GMT

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/2026…

💬2🔄2❤️34👀8612📊11

⚡ Powered by xgo.ing

NEW § Birgitta Böckeler finishes her post on sensors for coding agents by examining the role of a t...

Martin Fowler (@martinfowler) — Wed, 27 May 2026 15:07:54 GMT

NEW §

Birgitta Böckeler 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/senso…

💬0🔄8❤️45👀9217📊12

⚡ Powered by xgo.ing

NEW POST Four of my colleagues share their experiences in applying good security practices to vibe ...

Martin Fowler (@martinfowler) — Wed, 27 May 2026 14:45:50 GMT

NEW POST

Four of my colleagues share their experiences in applying good security practices to vibe coding.

martinfowler.com/articles/vibes…

💬2🔄22❤️159👀16493📊46

⚡ Powered by xgo.ing

NEW § Birgitta Böckeler adds exploration of three sensors for static code analysis, with mixed resu...

Martin Fowler (@martinfowler) — Wed, 20 May 2026 14:33:15 GMT

NEW §

Birgitta Böckeler 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/senso…

💬2🔄6❤️56👀9921📊14

⚡ Powered by xgo.ing

NEW POST Birgitta Böckeler begins an article about her experiences with sensors in an agent harness...

Martin Fowler (@martinfowler) — Tue, 19 May 2026 16:45:04 GMT

NEW POST

Birgitta Böckeler 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/senso…

💬2🔄24❤️116👀17252📊37

⚡ Powered by xgo.ing

Fragments: thoughts from a software development retreat, would I be a writer without text editors, u...

Martin Fowler (@martinfowler) — Thu, 14 May 2026 21:55:43 GMT

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/2026…

💬2🔄12❤️99👀16277📊28

⚡ Powered by xgo.ing

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...

Martin Fowler (@martinfowler) — Thu, 14 May 2026 15:13:17 GMT

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/Interrog…

💬8🔄25❤️329👀83783📊100

⚡ Powered by xgo.ing

NEW POST Will there be source code in the future? To wrestle with this, we have to understand what ...

Martin Fowler (@martinfowler) — Tue, 12 May 2026 13:33:56 GMT

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/what-…

💬9🔄49❤️270👀28434📊83

⚡ Powered by xgo.ing

Fragments: open-source framework for prompting patterns, musician sues google for defamation, apple ...

Martin Fowler (@martinfowler) — Tue, 05 May 2026 16:26:34 GMT

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/2026…

💬1🔄17❤️103👀14547📊31

⚡ Powered by xgo.ing

Fragments: updated guide on AI coding, video on harness engineering, how long should a function be, ...

Martin Fowler (@martinfowler) — Wed, 29 Apr 2026 13:26:02 GMT

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/2026…

💬1🔄33❤️233👀28695📊73

⚡ Powered by xgo.ing

NEW POST Thoughtworks internal IT use a workflow for agentic programming called Structured-Prompt-D...

Martin Fowler (@martinfowler) — Tue, 28 Apr 2026 13:15:46 GMT

NEW POST

Thoughtworks internal IT use a workflow for agentic programming called Structured-Prompt-Driven Development (SPDD). @WeiZhang595190  and Jessie Jie Xia describe how this works with a simple example plus details in a github project. 

martinfowler.com/articles/struc…

💬25🔄123❤️868👀96001📊347

⚡ Powered by xgo.ing

Fragments: 34th Thoughtworks Technology Radar, what happens when developers don't read the LLM's cod...

Martin Fowler (@martinfowler) — Tue, 21 Apr 2026 14:39:37 GMT

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/2026…

💬7🔄24❤️143👀25676📊46

⚡ Powered by xgo.ing

Fragments: pragmatic summit video with Kent and Gergely, virtue of laziness, TDD and prompts, inspir...

Martin Fowler (@martinfowler) — Tue, 14 Apr 2026 13:22:20 GMT

Fragments: pragmatic summit video with Kent and Gergely, virtue of laziness, TDD and prompts, inspiration from Dark Star

martinfowler.com/fragments/2026…

💬1🔄13❤️69👀12096📊18

⚡ Powered by xgo.ing

Last night I saw Central Square Theater’s excellent production of Breaking the Code. It’s about Alan...

Martin Fowler (@martinfowler) — Sat, 11 Apr 2026 13:09:00 GMT

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 near Boston this month.

centralsquaretheater.org/shows/breaking…

💬0🔄2❤️33👀10944📊5

⚡ Powered by xgo.ing

Fragments: two podcasts, a worryingly well-done supply-chain attack, framework for tech documentatio...

Martin Fowler (@martinfowler) — Thu, 09 Apr 2026 13:25:56 GMT

Fragments: two podcasts, a worryingly well-done supply-chain attack, framework for tech documentation, and a particularly thoughtful AI coding experience

martinfowler.com/fragments/2026…

💬0🔄9❤️52👀9596📊14

⚡ Powered by xgo.ing

NEW POST @techygarg finishes his series on reducing the friction in AI-Assisted Development with a...

Martin Fowler (@martinfowler) — Wed, 08 Apr 2026 13:41:38 GMT

NEW POST

@techygarg  finishes his series on reducing the friction in AI-Assisted Development with a practice that feeds back learnings from AI sessions into the team's shared artifacts, turning individual experience into collective improvement.

martinfowler.com/articles/reduc…

💬3🔄19❤️169👀18676📊58

⚡ Powered by xgo.ing

NEW POST Modern hardware is fast, but software often fails to leverage it. Caer Sanders guides his ...

Martin Fowler (@martinfowler) — Tue, 07 Apr 2026 13:45:09 GMT

NEW POST

Modern hardware is fast, but software often fails to leverage it. Caer Sanders guides his work with mechanical sympathy. He distills this into principles: predictable memory access, awareness of cache lines, single-writer, natural batching

martinfowler.com/articles/mecha…

💬6🔄55❤️279👀41339📊85

⚡ Powered by xgo.ing

Fragments: three layers of system health, AI as cognitive system 3, what's expensive if agents make ...

Martin Fowler (@martinfowler) — Thu, 02 Apr 2026 16:44:11 GMT

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

martinfowler.com/fragments/2026…

💬1🔄14❤️93👀13171📊31

⚡ Powered by xgo.ing

NEW POST Birgitta Böckeler wrote some initial thoughts about Harness Engineering last month. Since ...

Martin Fowler (@martinfowler) — Thu, 02 Apr 2026 13:28:13 GMT

NEW POST

Birgitta Böckeler wrote some initial thoughts about Harness Engineering last month. Since then she's been researching more and has now written a thoughtful mental model for understanding the topic.

martinfowler.com/articles/harne…

💬3🔄53❤️274👀24841📊100

⚡ Powered by xgo.ing

NEW POST The quality of what AI coding assistants produce depends on how well the prompter articula...

Martin Fowler (@martinfowler) — Tue, 31 Mar 2026 15:25:48 GMT

NEW POST

The quality of what AI coding assistants produce depends on how well the prompter articulates team standards. @techygarg proposes treating such instructions as infrastructure: versioned, reviewed, and shared artifacts.

martinfowler.com/articles/reduc…

💬16🔄55❤️408👀34267📊60

⚡ Powered by xgo.ing

Fragments: 80,000 people's opinion on AI, fixing the common gap in spec-driven development, weakenin...

Martin Fowler (@martinfowler) — Thu, 26 Mar 2026 17:17:57 GMT

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.

martinfowler.com/fragments/2026…

💬4🔄12❤️111👀15907📊15

⚡ Powered by xgo.ing

NEW POST ADRs are short documents that capture a decision, structured into logs that reveal a histo...

Martin Fowler (@martinfowler) — Tue, 24 Mar 2026 15:36:29 GMT

NEW POST

ADRs are short documents that capture a decision, structured into logs that reveal a history of architectural thinking for a product

martinfowler.com/bliki/Architec…

💬11🔄68❤️590👀50951📊159

⚡ Powered by xgo.ing

Fragments: code review isn't just catching bugs, what role for observability in agentic programming,...

Martin Fowler (@martinfowler) — Thu, 19 Mar 2026 15:59:44 GMT

Fragments: code review isn't just catching bugs, what role for observability in agentic programming, what we lose with GPS over maps

martinfowler.com/fragments/2026…

💬4🔄18❤️146👀21938📊20

⚡ Powered by xgo.ing

NEW POST Conversations with AI are ephemeral, decisions made early lose attention as the conversati...

Martin Fowler (@martinfowler) — Tue, 17 Mar 2026 14:07:41 GMT

NEW POST

Conversations with AI are ephemeral, decisions made early lose attention as the conversation continues, and disappear entirely with a new session. @techygarg  explains how to externalize the decision context into a living document.

martinfowler.com/articles/reduc…

💬15🔄47❤️409👀83477📊144

⚡ Powered by xgo.ing

Fragments: supervisory engineering, 2 sets of 8 levels, generating code to an architecture, perils o...

Martin Fowler (@martinfowler) — Mon, 16 Mar 2026 14:22:33 GMT

Fragments: supervisory engineering, 2 sets of 8 levels, generating code to an architecture, perils of detecting AI-aided writing, should humans review code?

martinfowler.com/fragments/2026…

💬2🔄11❤️103👀20750📊32

⚡ Powered by xgo.ing

Fragments: reporting fines, engaging with gen AI, experience engineering, watching the ralph loop, m...

Martin Fowler (@martinfowler) — Tue, 10 Mar 2026 17:55:25 GMT

Fragments: reporting fines, engaging with gen AI, experience engineering, watching the ralph loop, migrating COBOL

martinfowler.com/fragments/2026…

💬1🔄11❤️50👀13962📊16

⚡ Powered by xgo.ing

NEW POST Naresh Jain has long been uncomfortable with software patents. But a direct experience of ...

Martin Fowler (@martinfowler) — Thu, 05 Mar 2026 14:07:26 GMT

NEW POST

Naresh Jain has long been uncomfortable with software patents. But a direct experience of patent aggression, plus practical constraints startups face, led him to resort to defensive patenting

martinfowler.com/articles/paten…

💬0🔄5❤️33👀9300📊10

⚡ Powered by xgo.ing

NEW POST There's been much talk about how AI agents affect the workflow loops of software developme...

Martin Fowler (@martinfowler) — Wed, 04 Mar 2026 15:14:52 GMT

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.

martinfowler.com/articles/explo…

💬11🔄43❤️224👀36180📊91

⚡ Powered by xgo.ing

NEW POST @techygarg uses a structured conversation with an AI agent that mirrors whiteboarding wit...

Martin Fowler (@martinfowler) — Tue, 03 Mar 2026 14:07:13 GMT

NEW POST

@techygarg  uses a structured conversation with an AI agent that mirrors whiteboarding with a human: progressive levels of design alignment, reducing cognitive load, and catching misunderstandings at the cheapest possible moment.

martinfowler.com/articles/reduc…

💬3🔄24❤️185👀24568📊64

⚡ Powered by xgo.ing

Fragments: how organizations are using AI, reflections from the Utah retreat, agentic engineering pa...

Martin Fowler (@martinfowler) — Wed, 25 Feb 2026 15:03:02 GMT

Fragments: how organizations are using AI, reflections from the Utah retreat, agentic engineering patterns, inserting friction for security, training biological neural networks

martinfowler.com/fragments/2026…

💬2🔄20❤️111👀18180📊39

⚡ Powered by xgo.ing

NEW POST @techygarg sees a frustration loop when working with AI and identified five patterns to he...

Martin Fowler (@martinfowler) — Tue, 24 Feb 2026 14:55:36 GMT

NEW POST

@techygarg 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.

martinfowler.com/articles/reduc…

💬6🔄40❤️199👀25708📊74

⚡ Powered by xgo.ing

Fragments: security with OpenClaw, impressions from Pragmatic Summit, era of highly bespoke software...

Martin Fowler (@martinfowler) — Mon, 23 Feb 2026 12:40:38 GMT

Fragments: security with OpenClaw, impressions from Pragmatic Summit, era of highly bespoke software, life-size pocket map

martinfowler.com/fragments/2026…

💬5🔄10❤️58👀13883📊21

⚡ Powered by xgo.ing

Fragments: LLMs make our days harder, an LLM reacts badly to a rejected pull request, the Promptware...

Martin Fowler (@martinfowler) — Thu, 19 Feb 2026 14:44:45 GMT

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

martinfowler.com/fragments/2026…

💬3🔄8❤️70👀13955📊23

⚡ Powered by xgo.ing

NEW POST The concept of Servant Leadership has never quite sat properly with me, because it's essen...

Martin Fowler (@martinfowler) — Thu, 19 Feb 2026 14:02:22 GMT

NEW POST

The concept of Servant Leadership has never quite sat properly with me, because it's essentially gaslighting. Recently I came across Host Leadership as a better framing.

martinfowler.com/bliki/HostLead…

💬4🔄8❤️111👀14552📊31

⚡ Powered by xgo.ing

Fragments: Detailed report on the Thoughtworks AI retreat, should we write a manifesto for AI-enable...

Martin Fowler (@martinfowler) — Wed, 18 Feb 2026 15:56:51 GMT

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

martinfowler.com/fragments/2026…

💬3🔄28❤️192👀25565📊61

⚡ Powered by xgo.ing

NEW POST I've heard a number of reports recently about people setting up LLM agents to work on thei...

Martin Fowler (@martinfowler) — Tue, 17 Feb 2026 15:46:32 GMT

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

martinfowler.com/bliki/AgenticE…

💬10🔄29❤️170👀22177📊48

⚡ Powered by xgo.ing

NEW POST Birgitta Böckeler explains why OpenAI's recent write-up on "Harness Engineering" is a valu...

Martin Fowler (@martinfowler) — Tue, 17 Feb 2026 13:48:48 GMT

NEW POST

Birgitta Böckeler explains why OpenAI's recent write-up on "Harness Engineering" is a valuable framing of a key part of AI-enabled software dev. Harness includes context engineering, architectural constraints, and garbage collection.

martinfowler.com/articles/explo…

💬8🔄47❤️372👀46371📊143

⚡ Powered by xgo.ing

NEW POST Fragments: the future of senior developers, junior developers, more on cognitive debt, Dev...

Martin Fowler (@martinfowler) — Fri, 13 Feb 2026 15:59:29 GMT

NEW POST

Fragments: the future of senior developers, junior developers, more on cognitive debt, DevEx versus AgentEx, the role of IDEs, consequences of task switching in supervisory programming

martinfowler.com/fragments/2026…

💬10🔄82❤️493👀70221📊160

⚡ Powered by xgo.ing

fragments: the consequences of absolute skepticism, cognitive debt with AI, will AI remove fun of pr...

Martin Fowler (@martinfowler) — Mon, 09 Feb 2026 19:35:47 GMT

fragments: the consequences of absolute skepticism, cognitive debt with AI, will AI remove fun of programming, the future of source code, how to survive AI contributions to open source, explaining transformers to 12/62-year-olds

martinfowler.com/fragments/2026…

💬5🔄41❤️241👀33679📊80

⚡ Powered by xgo.ing

NEW POST Powerful context engineering is becoming a huge part of the developer experience of modern...

Martin Fowler (@martinfowler) — Thu, 05 Feb 2026 15:42:37 GMT

NEW POST

Powerful context engineering is becoming a huge part of the developer experience of modern LLM tools. Birgitta Böckeler explains the current state of context configuration features, using Claude Code as an example.

martinfowler.com/articles/explo…

💬26🔄94❤️626👀60465📊224