Martin Fowler

10.7K posts

Martin Fowler banner
Martin Fowler

Martin Fowler

@martinfowler

Author on Software Development. Works for Thoughtworks. Also hikes, watches theater, and plays modern board games. He/him.

Boston Katılım Ekim 2008
166 Takip Edilen350.2K Takipçiler
Martin Fowler
Martin Fowler@martinfowler·
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…
English
15
47
398
74.5K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
2
10
98
19.7K
Martin Fowler
Martin Fowler@martinfowler·
@_damienf I'm glad you liked the distinction, but the credit should go to Kief Morris, as he's the author of the article. I'm just the publisher.
English
0
4
88
7.2K
Damien Filiatrault
Damien Filiatrault@_damienf·
Martin Fowler makes a useful distinction: humans in the loop vs on the loop. The real leverage with AI agents may be in designing the system around them (specs, checks, tests, and feedback), not manually catching every mistake. martinfowler.com/articles/explo…
Damien Filiatrault tweet media
English
2
8
81
8.4K
Martin Fowler
Martin Fowler@martinfowler·
@GeoffreyHuntley @_mjmeyer We apologize for our ignorance. We've added a footnote to the article to link to what I think is the best ref - do let me know if you'd prefer a different href. (Kief isn't on here, but I can forward comments to him, or ping me on email.)
English
1
0
7
332
geoff
geoff@GeoffreyHuntley·
@_mjmeyer Yeah, I'm pretty sure I defined the term being on the loop, not in the loop @martinfowler🫡 also completely misses that ralph is a memory management technique.
English
2
0
18
1.3K
mj
mj@_mjmeyer·
great article. but the framing of "ralph wiggumming" here is a bit unfair. @GeoffreyHuntley never framed ralph as "leaving the agents to it". if anything, he was one of the first people i heard talking about being "on the loop". strange seeing people straw-man it while rebranding the same ideas as a new engineering paradigm.
Martin Fowler@martinfowler

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…

English
1
0
4
2.3K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
0
4
33
8.7K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
11
41
218
31.3K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
3
24
184
24.1K
Martin Fowler retweetledi
Donald J. Trump
Donald J. Trump@realDonaldTrump·
Now that Obama’s poll numbers are in tailspin – watch for him to launch a strike in Libya or Iran. He is desperate.
English
3K
44.9K
64.1K
0
Martin Fowler retweetledi
Aaron Reichlin-Melnick
Aaron Reichlin-Melnick@ReichlinMelnick·
This is because Anthropic said: - We don't want our technology changed to permit for mass surveillance of American citizens - We don't want our technology changed to permit the use in fully autonomous lethal weapons Ask yourself why Trump and his crew want those powers.
Aaron Rupar@atrupar

Trump: “THE UNITED STATES OF AMERICA WILL NEVER ALLOW A RADICAL LEFT, WOKE COMPANY TO DICTATE HOW OUR GREAT MILITARY FIGHTS AND WINS WARS! That decision belongs to YOUR COMMANDER-IN-CHIEF, and the tremendous leaders I appoint to run our Military.    The Leftwing nut jobs at Anthropic have made a DISASTROUS MISTAKE trying to STRONG-ARM the Department of War, and force them to obey their Terms of Service instead of our Constitution. Their selfishness is putting AMERICAN LIVES at risk, our Troops in danger, and our National Security in JEOPARDY.    Therefore, I am directing EVERY Federal Agency in the United States Government to IMMEDIATELY CEASE all use of Anthropic’s technology. We don’t need it, we don’t want it, and will not do business with them again! There will be a Six Month phase out period for Agencies like the Department of War who are using Anthropic’s products, at various levels. Anthropic better get their act together, and be helpful during this phase out period, or I will use the Full Power of the Presidency to make them comply, with major civil and criminal consequences to follow.   WE will decide the fate of our Country — NOT some out-of-control, Radical Left AI company run by people who have no idea what the real World is all about. Thank you for your attention to this matter. MAKE AMERICA GREAT AGAIN!   PRESIDENT DONALD J. TRUMP”

English
33
517
1.5K
71.6K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
2
20
110
17.9K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
6
41
201
25.5K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
3
9
70
13.8K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
4
8
111
14.4K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
3
29
192
25.4K
Cbelle
Cbelle@cbelle1234·
@martinfowler Unrelated funny question - is there a way to know ahead of time in which conferences you're going to speak at?
English
1
0
0
1.3K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
10
29
170
22.1K
Martin Fowler
Martin Fowler@martinfowler·
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…
English
8
48
368
43.7K