Subagents get justified by time saved and parallel execution, but Rahul Garg 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 f...

TL;DRI have ideas. I haven’t been writing them. That’s about to change. I promise… myself. 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 conferen...

With this post, I’ll wrap up my notes from the second Future of Software Development Retreat. But before I do, I should note that the full Thoughtworks report on the retreat is now available. They have five headline findings: Code generation is no longer the bottleneck — verification is. ‘Harness en...

When people think of legacy modernization, most folks aren't imagining the target environment will be Java 8. But this was the challenge facing Nik Malykhin when he needed to run a Java 1.5 codebase on today's hardware. His early use of LLMs gave plausible answers that did not hold up in the codebas...

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. Unmesh Joshi describes how the example of Tickloom - a domain model ...

Some more of my notes from Thoughtworks Future of Software Development Retreat. When we had our first retreat in Utah early this year, nobody had heard of Harness Engineering. This time we had a whole session on it. When comes to the guide side of harnesses, most of the discussion is about context m...

Birgitta Böckeler now reports on her recent experiences trying local models for coding. She compares them using two standard tasks, and tries out the most promising model for day-to-day use. more…

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. more…

Last week, Thoughtworks ran a second Future of Software Development Retreat, 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 conclusion...

One of the most interesting projects my colleagues have done with LLMs has been building a system to allow pharmaceutical researchers to query decades of information about studies buried in PDF reports. Sarang Sanjay Kulkarni describes its evolution from keyword-based search to an intelligent resear...

“Prag Dave” Thomas (co-author of the outstanding “Pragmatic Programmer”) has loved programming since he was young. 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...

Greg Wilson has noticed that lots of folks are using dodgy metrics to figure out if AI tools are worth their costs. 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 dif...

At the GOTO Conference in Copenhagen in 2025, Kent Beck and I spent some time on stage 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 ou...

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. more…

Vibe coding has significantly accelerated software prototyping but AI agents frequently recommend insecure configurations, creating security problems. Gautam Koul, Lucian Moss, Neil Drew-Lopez, and Daberechi Ruth Edeokoh share their experience while building applications for Thoughtworks's global ma...

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 softwar...

Birgitta Böckeler adds discussion of three more sensors for static code analysis, focusing on checking and enforcing better modularity. Computational sensors for dependency checks were good at enforcing rules, but the rules were limited. Building a computational sensor for coupling data proved lackl...

In her recent article about harness engineering for coding agent users, Birgitta Böckeler laid out a mental model for expanding a coding agent harness: a system of guides and sensors that increase the probability of good agent outputs and enable self-correction before issues reach human eyes. Birgit...

Last week I spent a day at a retreat 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 Chatham House Rule, so I can’t attribute the comments and stories I heard. (If anyone rec...

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 o...

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. Unmesh Joshi sees code as having two distinct but intertwined purposes: instructions to a machine and a conceptual model of the proble...

Over the last couple of months Rahul Garg published a series of posts here on how to reduce the friction in AI-assisted programming. To make it easier to put these ideas into practice he’s now built an open-source framework to operationalize these patterns. AI coding assistants jump straight to code...

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 The Mythical Man-Month which became one of the most influential books on software development after its publication in 1975. Reading it in 2026, we'll fi...

Chris Parsons has updated his guide on using AI to code. 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...

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 method and workflow called Structured Prompt-Driven Development (SPDD). Wei Zhang and Jessie J...

Last week Thoughtworks released the 34th volume of our Technology Radar. This radar is our biannual survey of our experience of the technology scene, highlighting tools, techniques, platforms, and languages that we’ve used or otherwise caught our eye. This edition contains 118 blips, each briefly de...

I attended the first Pragmatic Summit early this year, and while there host Gergely Orosz interviewed Kent Beck and myself on stage. The video runs for about half-an-hour. I always enjoy nattering with Kent like this, and Gergely pushed into some worthwhile topics. Given the timing, AI dominated the...

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.

I mostly link to written material here, but I’ve recently listened to two excellent podcasts that I can recommend. Anyone who regularly reads these fragments knows that I’m a big fan of Simon Willison, his (also very fragmentary) posts have earned a regular spot in my RSS reader. But the problem wit...

Rahul Garg finishes his series on reducing the friction in AI-Assisted Development. He proposes a structured feedback practice that harvests learnings from AI sessions and feeds them back into the team's shared artifacts, turning individual experience into collective improvement. more…