Present a good team with problems & they'll thrive on finding solutions. Ask them to implement your solution & they'll only find problems.
Tom Howlett
@leantomatoAI Engineering Engagement @sonarsource. Exploring the AI coding quality challenge!
Learning to use coding agents well is empowering! Here are some skills to focus on now that the agents write the code. thenextcommit.substack.com/p…
In this week’s The Next Commit, I chat with Maebh Booth, a technical engineering leader who shares the kind of clear thinking that can help steady the ship and steer teams through the AI coding storm. thenextcommit.substack.com/p…
When agents do the implementation, the experience of writing code has to come from elsewhere. My deep dive on my conversation with @johncrickett, founder of Coding Challenges, asks how developers build the judgment to assess agent-written work. Read it: thenextcommit.substack.com/p…

⟳ Tom Howlett retweeted
AI isn't killing software engineering. Not even close. Instead it's exposing how much we've confused software engineering with writing code. Yes, coding is a fundamentally important part of the job, but it's only one part. Understanding what users need, figuring out what's worth building, making architectural decisions, and delivering software that actually solves problems are all part of software engineering. AI might change who, or what, writes the code. But that doesn't make those other skills less important. If anything, it makes them more important. In fact they're critical to stopping us spending a lot of time and effort building the wrong things. This clip is from a chat I had with Tom Howlett (@leantomato) on The Next Commit podcast. We talked about how AI agents are changing software engineering, why developers still need strong fundamentals, and the growing importance of human skills, engineering judgement, and taking responsibility for the software we ship. You can listen to the full episode here: thenextcommit.substack.com/p…
0:32

⟳ Tom Howlett retweeted
When Anthropic release a new model it's always worth taking a look at their updated prompting guide - here's an entertaining tip to make Fable 5.2 less likely to be cautious in how it improves existing code: tell it "This codebase is yours" platform.claude.com/docs/en/…

⟳ Tom Howlett retweeted
Thoughts and prayers.
this is whats going to happen to epic games in about a year
Developers have always built much of their judgment by doing the implementation themselves. I talked to @johncrickett , founder of Coding Challenges, on The Next Commit about what happens to that learning as agents take on more of the work. Listen: thenextcommit.substack.com/p…
A software factory should be continually improving based on feedback from its output. In my conversation with @slashBene , we explored how review, checks and guidance can help those lessons survive beyond a single task. Here’s my write-up: substack.com/home/post/p-222…

⟳ Tom Howlett retweeted
When an agent gets it wrong, do you fix the code or the process behind it? @slashBene, co-CEO at hackers&wizards, wants engineers to fix the process so the mistake doesn't come back. Hear why on this week's ep of The Next Commit w/ @leantomato. Listen: ow.ly/eo4O5103u7J
0:36
Here’s my deep dive on my conversation with Simon Vane, Staff Engineer at M-KOPA, I look at how review, tests and design conversations fit together when agents deliver faster than people can inspect. Read the full deep dive on Substack: thenextcommit.substack.com/p…
It's tempting to put all the time agents save into building more features. But without strong foundations, adding more complexity will make every new feature harder to add. Read my newsletter for more thoughts: thenextcommit.substack.com/p…
Which parts of pairing, TDD and quality still matter when agents write the code? I asked my old friend Simon Vane from MKopa on to The Next Commit, and we worked through what can move into agent instructions and automated checks, and what still needs people. Listen: thenextcommit.substack.com/p…
How can agents have enough freedom to help, without removing the safeguards that make their work trustworthy? Find out in the deep dive on my conversation with Shashank Patwardhan, Application Security Lead at @ifxpayments. Read: thenextcommit.substack.com/p…

⟳ Tom Howlett retweeted
AI agents know architectural patterns, but they still need boundaries. @codeliftsleep shares his repeatable process for setting constraints that keep agents aligned with human architectural decisions. Watch his discussion on The Next Commit with @leantomato: hubs.la/Q04BMK520 Check out Matt's book, Grokking Software Architecture: hubs.la/Q04BMK8r0
foundations remain as important today as they did in August. continue to invest accordingly :)
organic architecture good codebases have always had strong foundations and constraints. these files go here. this kind of code goes there. the codebase is held together either by catering to the lowest common denominator developer using conventional frameworks and languages, or by strict adherence to a style guide enforced by code review. the arrival of an infinite number of monkeys armed with keyboards have obsoleted the latter. codebases designed for agents need hard constraints so that even the dumbest agent (and pilot) can contribute meaningfully. the chaos must be tamed. refactoring your codebase and choosing a tech stack with strong type systems/compiler diagnostics has far greater impact than AGENTS.md and tweaking your skills. hard constraints and well thought out architecture guide agents to do the right thing by default. the best rules are in your code. invest accordingly.
No posts match this search.





