Intelligence Feed
showing 30 items
What is Code
Martin Fowler · Software Engineering · src 8 · 2026-05-12T09:30:00-04:00 · HIGH 66
<p>Increasingly humans delegate writing code to agents. Will there even be
source code in the future? To wrestle with this question, we have to
understand what code is. <b class="author">Unmesh Joshi</b> sees code as having
two distinct but intertwined purposes: <i>instructions to a machine</i> and a
<i>conceptual model of the problem domain</i>. He explores why it's vital
to build a voc
Bliki: Interrogatory LLM
Martin Fowler · Software Engineering · src 8 · 2026-05-14T11:04:00-04:00 · HIGH 66
<p>When we need an LLM to perform a complex task, we often need to feed it a
lot of context. Coming up with a design for a new feature requires
descriptions of how we want the feature to appear to the user, guidelines on
how it should be implemented, information on external systems to consult, and
so on. All this can be several pages of markdown. The obvious way to do
this is for a human to write this conte
DSLs Enable Reliable Use of LLMs
Martin Fowler · Software Engineering · src 8 · 2026-07-14T08:51:00-04:00 · HIGH 66
<p> LLMs generate code incredibly fast, but to ensure they generate
exactly what is intended, they need clear boundaries. Abstractions and
Domain-Specific Languages (DSLs) provide a strong harness that guides LLMs
right from the start. <b class="author">Unmesh Joshi</b> describes how the example
of Tickloom - a domain model and DSL for illustrating distributed system
behavior - <a href="
Fragments: May 5
Martin Fowler · Software Engineering · src 8 · 2026-05-05T12:23:00-04:00 · MEDIUM 48
<p>Over the last couple of months Rahul Garg published a series of posts here on how to <a href="https://martinfowler.com/articles/reduce-friction-ai/">reduce the friction in AI-assisted programming</a>. To make it easier to put these ideas into practice he’s now built an <a href="https://martinfowler.com/articles/reduce-friction-ai/#ThesePatternsAsInstallableInfrastructure">open-source framework to operationalize th
Why I’m Writing Rachel’s Ramblings
Martin Fowler · Software Engineering · src 8 · 2026-07-28T08:32:00-04:00 · MEDIUM 48
<p class="precis"><b>TL;DR</b><br /><i>I have ideas. I haven’t been writing them. That’s about to change. I promise… myself.</i></p>
<img src="https://martinfowler.com/rachels-ramblings/card.png" />
<p>I’ve been thinking a lot about talent. Actually, I’ve been thinking a lot about thinking. And writing. Or more specifically, not writing. This really hit me earlier this year at the Future of Software conference. I was
The Conductor Developer
Martin Fowler · Software Engineering · src 8 · 2026-07-31T09:48:00-04:00 · MEDIUM 48
<p class="precis"><b>TL;DR</b><br /><i>Why I think software development is starting to feel a little more like conducting an orchestra.</i></p>
<img src="https://martinfowler.com/rachels-ramblings/card.png" />
<p>There’s a shift happening in software development that I don’t think we’re talking about clearly enough.</p>
<p>For the last couple of years we’ve framed AI as a productivity tool. How much faster can it wr
Fragments: May 27
Martin Fowler · Software Engineering · src 8 · 2026-05-27T15:40:00-04:00 · MEDIUM 44
<p>At the GOTO Conference in Copenhagen in 2025, <a href="https://www.youtube.com/watch?v=ii_rLjQfjp0&list=PLEx5khR4g7PINwOsYrkwz3lTTJUYoXC53">Kent Beck and I spent some time on stage</a> talking and answering questions from the audience - a format I refer to as “two old geezers on a park bench”. We talk about our experiences with LLM-augmented programming (at that point - October 2025), we show our frustration t
Fragments: May 14
Martin Fowler · Software Engineering · src 8 · 2026-05-14T17:52:00-04:00 · MEDIUM 41
<p>Last week I spent a day at The Orchard Retreat, hosted by <a href="https://www.mechanical-orchard.com/">Mechanical Orchard</a>. that brought together several people working in software development to talk about the profession’s future with the rise of agentic programming. The event was help under the <a href="https://www.chathamhouse.org/about-us/chatham-house-rule">Chatham House Rule</a>, so I can’t attribute the
Bliki: Vibe Coding
Martin Fowler · Software Engineering · src 8 · 2026-05-21T07:49:00-04:00 · MEDIUM 41
<p>Vibe coding is building a software application by prompting an LLM, telling it
what to build, trying it out, prompting for changes - but without looking at
any of the code that the LLM generates. This technique can be used by people
without any knowledge of programming. However the resulting software often
shows problems with maintainability, correctness, and security - so is best
used for disposable sof
Building Reliable Agentic AI Systems
Martin Fowler · Software Engineering · src 8 · 2026-06-16T13:11:00+01:00 · MEDIUM 41
<div class="img-link"><a href="https://martinfowler.com/articles/reliable-llm-bayer.html"><img src="https://martinfowler.com/articles/reliable-llm-bayer/card.png" width="350px" /></a></div>
<p>One of the most interesting projects my colleagues have done with LLMs
has been building a system with Bayer to allow pharmaceutical researchers to query
decades of information about studies buried in PDF reports.
Structured-Prompt-Driven Development (SPDD)
Martin Fowler · Software Engineering · src 8 · 2026-04-28T09:02:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/structured-prompt-driven/"><img src="https://martinfowler.com/articles/structured-prompt-driven//card.png" width="350px" /></a></div>
<p>LLM programming assistants have demonstrated considerable value, but
mostly with individual developers. The internal IT organization in
Thoughtworks has been using them for their teams and have developed a
Fragments: June 16
Martin Fowler · Software Engineering · src 8 · 2026-06-16T08:44:00-04:00 · MEDIUM 26
<p>“Prag Dave” Thomas (co-author of the outstanding “Pragmatic Programmer”) <a href="https://articles.pragdave.me/p/castles-in-the-air?triedRedirect=true">has loved programming</a> since he was young.</p>
<blockquote>
<p>Programming was how I could express myself. I wasn’t an artist. When I sing, dogs howl. When I draw, friends say, “Very nice. What is it?” I didn’t connect particularly well with people, even thou
Viability of local models for coding
Martin Fowler · Software Engineering · src 8 · 2026-07-07T08:34:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/local-models-for-coding-factors.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Birgitta Böckeler</b> recently spent some time trying out
running local LLMs for some programming tasks. In this memo she outlines the factors that
influence how
Experiences with local models for coding
Martin Fowler · Software Engineering · src 8 · 2026-07-08T07:57:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/local-models-for-coding-experiences.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Birgitta Böckeler</b> now reports on her recent experiences
trying local LLMs for coding. She compares them using two standard
tasks, and tries out the most
Fragments: July 13
Martin Fowler · Software Engineering · src 8 · 2026-07-13T08:51:00-04:00 · MEDIUM 26
<p>Some more of my notes from <a href="https://martinfowler.com/bliki/FutureOfSoftwareDevelopment.html">Thoughtworks Future of Software Development Retreat</a>.</p>
<p>When we had our first retreat in Utah early this year, nobody had heard of <a href="https://martinfowler.com/articles/harness-engineering.html">Harness Engineering</a>. This time we had a whole session on it.</p>
<p>When comes to the guide side of ha
The Archaeologist’s Copilot
Martin Fowler · Software Engineering · src 8 · 2026-07-16T09:25:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/archaeologist-copilot.html"><img src="https://martinfowler.com/articles/archaeologist-copilot/card.png" width="350px" /></a></div>
<p>When people think of legacy modernization, most folks aren't imagining
the target environment will be Java 8. But this was the challenge facing
<b class="author">Nik Malykhin</b> when he needed to run a Java
Fragments: July 21
Martin Fowler · Software Engineering · src 8 · 2026-07-21T06:13:00-07:00 · MEDIUM 26
<p>With this post, I’ll wrap up my notes from the second <a href="https://martinfowler.com/bliki/FutureOfSoftwareDevelopment.html">Future of Software Development Retreat</a>. But before I do, I should note that the <a href="https://www.thoughtworks.com/content/dam/thoughtworks/documents/report/tw_future_of_software_engineering_europe_2026.pdf">full Thoughtworks report on the retreat is now available</a>. They have f
TDD inside the agent loop - theater or actual value?
Martin Fowler · Software Engineering · src 8 · 2026-08-11T07:39:00-04:00 · MEDIUM 26
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/tdd-in-the-agent-loop.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p>My colleagues at Thoughtworks tend to be big fans of Test-Driven
Development, and many people in the industry advocate telling LLM agents
to use TDD when building software. <b class="author">Bir
Fragments: April 29
Martin Fowler · Software Engineering · src 8 · 2026-04-29T09:23:00-04:00 · MEDIUM 23
<p>Chris Parsons has updated <a href="https://www.chrismdp.com/coding-with-ai/">his guide on using AI to code</a>. This is his third update, what I like about it is that he gives a lot of concrete information about how he uses AI, with sufficient detail that we can learn from him. His advice also resonates with the better advice I’ve seen out there, so the article makes a good overview of the state of using AI for so
Fragments: July 6
Martin Fowler · Software Engineering · src 8 · 2026-07-06T08:53:00-04:00 · MEDIUM 23
<p>Last week, Thoughtworks ran a second <a href="https://martinfowler.com/bliki/FutureOfSoftwareDevelopment.html">Future of Software Development Retreat</a>, this time in Europe. As with the previous event, I’ll be sharing some fragmentary thoughts on this. There were five parallel streams, so I could, at best, only attend ⅕ of sessions. This isn’t an event that forms conclusions, rather one that allows those explori
Fragments: August 4
Martin Fowler · Software Engineering · src 8 · 2026-08-04T08:08:00-04:00 · MEDIUM 20
<p>There’s been a fair bit of publicity of the <a href="https://www.theguardian.com/technology/2026/jul/22/openai-says-its-models-went-rogue-and-hacked-startup-in-unprecedented-incident">Open AI “rogue agent” that hacked into Hugging Face</a>. This prompted Anthropic to check what their models were up to and, to my complete lack of surprise, <a href="https://www.anthropic.com/news/investigating-incidents-cybersecurit
Alan Turing play in Cambridge MA
Martin Fowler · Software Engineering · src 8 · 2026-04-11T09:01:00-04:00 · LOW 8
<p>Last night I saw Central Square Theater’s excellent production of <a href="https://www.centralsquaretheater.org/shows/breaking-the-code-2026/">Breaking the Code</a>. 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.</p>
Bliki: Mythical Man Month
Martin Fowler · Software Engineering · src 8 · 2026-05-05T12:18:00-04:00 · LOW 8
<p>In the early 1960s, Fred Brooks managed the development of IBM's System/360
computer systems. After it was done he penned his thoughts in the book <a href="https://www.amazon.com/gp/product/0201835959/ref=as_li_tl?ie=UTF8&camp=1789&creative=9325&creativeASIN=0201835959&linkCode=as2&tag=martinfowlerc-20">The
Mythical Man-Month</a> which became one of the most influential books on software
Maintainability sensors for coding agents
Martin Fowler · Software Engineering · src 8 · 2026-05-19T12:38:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/sensors-for-coding-agents.html"><img src="https://martinfowler.com/articles/sensors-for-coding-agents/card.png" width="350px" /></a></div>
<p>In her recent article about harness engineering for coding agent users,
<b class="author">Birgitta Böckeler</b> laid out a mental model for expanding a
coding agent harness: a system of guides an
Three more static code analysis sensors
Martin Fowler · Software Engineering · src 8 · 2026-05-20T10:27:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/sensors-for-coding-agents.html#StaticCodeAnalysisDependencyRules"><img src="https://martinfowler.com/articles/sensors-for-coding-agents/card.png" width="350px" /></a></div>
<p><b class="author">Birgitta Böckeler</b> adds discussion of <a href="https://martinfowler.com/articles/sensors-for-coding-agents.html#StaticCodeAnalysisDependencyRules">three
The VibeSec Reckoning
Martin Fowler · Software Engineering · src 8 · 2026-05-27T10:03:00-04:00 · LOW 8
<p>Vibe coding has significantly accelerated software prototyping but AI
agents frequently recommend insecure configurations, creating security
problems. <b class="author">Gautam Koul, Lucian Moss, Neil Drew-Lopez, and Daberechi
Ruth Edeokoh</b> share their experience while building applications
for Thoughtworks's global marketing. They learned that to combat this we
need to write a secu
The test suite as a regression sensor
Martin Fowler · Software Engineering · src 8 · 2026-05-27T11:01:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/sensors-for-coding-agents.html#TheTestSuiteAsARegressionSensor"><img src="https://martinfowler.com/articles/sensors-for-coding-agents/card.png" width="350px" /></a></div>
<p><b class="author">Birgitta Böckeler</b> finishes her post on sensors for
coding agents by examining the role of a test suite as a regression
sensor, focusing on th
Fragments: June 2
Martin Fowler · Software Engineering · src 8 · 2026-06-02T11:21:00-04:00 · LOW 8
<p>Greg Wilson has noticed that lots of folks are <a href="https://third-bit.com/2026/05/20/twelve-ways-to-be-wrong/">using dodgy metrics</a> to figure out if AI tools are worth their costs.</p>
<blockquote>
<p>Would you measure lines of code generated, or tickets closed? Or would you send out a survey asking whether developers feel more productive? Each of those approaches is flawed in a different way;</p>
</bloc
The Orchestrator's Tax
Martin Fowler · Software Engineering · src 8 · 2026-07-28T09:10:00-04:00 · LOW 8
<p>Subagents get justified by time saved and parallel execution, but
<b class="author">Rahul Garg</b> explains that's not what matters most. Every
token in the orchestrator's context is competing for its attention, and
the real value of a subagent is what it keeps out of that context.
Subagents should be treated as a tool for protecting the orchestrator's
working memory, offloading reaso
The Economic Benefit of Refactoring
Martin Fowler · Software Engineering · src 8 · 2026-07-30T09:04:00-04:00 · LOW 8
<div class="img-link"><a href="https://martinfowler.com/articles/exploring-gen-ai/refactoring-economic-benefit.html"><img src="https://martinfowler.com/articles/exploring-gen-ai/donkey-card.png" width="" /></a></div>
<p><b class="author">Giles Edwards-Alexander</b> does an experiment to see if decomposing a
large function helps reduce token costs, suggesting that is may now be
possible to measure the eco