Present a good team with problems & they'll thrive on finding solutions. Ask them to implement your solution & they'll only find problems.

Not a podcast person? Prefer a long read, or asking Claude or GPT to read it for you? I’ve written a deep dive into this week’s The Next Commit episode with Michael Tweed. We explore how Skyscanner turns local AI experiments into shared engineering practice, and how engineers’ work shifts toward guiding agents and verifying what they produce. thenextcommit.substack.com/p…

Are your teams sharing how they work with agents? Today on The Next Commit, Michael Tweed explains how @Skyscanner turns local experimentation into shared skills, infrastructure and standards without imposing one workflow on every engineer. thenextcommit.substack.com/p…

One run won’t tell you how coding agents work. You need repeated experiments and traces to see the patterns. I burnt some tokens benchmarking agents and reasoning settings with Sol. Codex and I wrote up what changed when I turned reasoning effort up and down: thenextcommit.substack.com/p…

If you’d prefer a long read to this week’s @TheNextCommit podcast, here’s my analysis of the conversation with @tottinge. Agents don’t make XP obsolete. They give testing, refactoring and evolutionary design new leverage, while making human judgement matter more. thenextcommit.substack.com/p…

With the right guidance, agents can write quality code at extraordinary speed. Tim Ottinger (@tottinge) gives them room to work, but there’s one situation where he always tells them to stop and collaborate. Can you guess when? thenextcommit.substack.com/p…

NEXT WEEK! We're heading to London for the @Gartner_inc Application Innovation & Business Solutions Summit 🇬🇧 Find us at Booth #404 to say hi. Don't miss @leantomato's talk on shipping enterprise-quality code with AI agents, Tuesday September 15 at 2:45pm BST. #GartnerAPPS

I’ve written about what I took from my conversation with Ian Johnson, Staff Engineer at Parento and author of ‘Harness Engineering’. Ian employs small tickets, honest coding rules, layered checks and a development system that learns from its mistakes. Or, as Ian puts it, “building the thing that builds the thing.” Read: substack.com/home/post/p-214…

The Next Commit is live! This new podcast and newsletter is about how software engineering is changing with AI, told by the engineers doing the work. Our first guest is Ian Johnson, author of Harness Engineering. Watch and subscribe: substack.com/home/post/p-214…

I’ve been working on something new with some incredible colleagues at @Sonar. Looking forward to sharing it with you tomorrow.

Code quality, taste and judgment matter - especially now that agents write most of the first draft. @SonarSource helps set your quality gate: fandf.co/45bRKE8

I have @reach_vb to thank for persuading to move away from the CLI and embrace the @OpenAI Codex app. I now spend my whole day in it and it just keeps getting better. If you're stuck in the CLI give it a try!

Better code quality = lower AI costs 💸 Agents use 7.1% fewer input tokens on better-structured code, doing the same work for less. And because agents tend to make code messier over time, keeping quality up is what protects the savings. Details: sonarsource.com/blog/your-ai…

This is some great research, Sonar's new tools help agents develop quality code (which is necessary for production applications) - now we know they work more efficiently on that code too!

Preparing for demos at AI Dev 26 and I can see Claude is planning to have fun with me! (I’m a Tom!)

SlopCodeBench is a great framework for testing out different agent configurations and the impact they have on quality. I'm excited to try out the latest release!

Off to speak in San Francisco at @DeepLearningAI AI Dev 26 next week. Will be talking about how to ship enterprise quality code with agents. My first time in SF! ai-dev.deeplearning.ai/

Claude Code builds 🤝 SonarQube verifies. Now, they do it in the same place. The SonarQube plugin for Claude Code is available now in the Anthropic marketplace.

I'm over trying to get agents to do everything and getting back to crafting the good stuff and leaving agents for a) the mundane b) experiments c) scripting and automating d) (re)searching and distilling e) analytics. Feels good!

For the last 6 months I’ve been working on Agentic Analysis, a new product for @SonarSource that was launched as an open beta today. It provides Sonar’s comprehensive analysis to AI Agents in seconds and together with its sister product Context Augmentation allows the agent to produce quality code from the outset. sonarsource.com/blog/agentic…

To strengthen the Guide, Verify, & Solve phases of the Agent Centric Development Cycle, we've strengthened our offering with: 🔷 Sonar Context Augmentation 🔷 SonarQube Agentic Analysis 🔷 SonarSweep 🔷 SonarQube Remediation Agent Read the news: sonarsource.com/company/pres…