About seven months ago, I wrote about using AI for code reviews. At the time, it felt pretty novel. I had a GitHub Action that gathered up our Cursor rules, fed them to Codex, and posted review comments on pull requests (PRs), and I was also trying out Sentry’s AI review beta. I said something […] T...

At this point, I’m about three years into my AI adoption, and throughout the process I’ve learned what burns me out, what speeds me up, what helps keep me thorough, and, most importantly, how I stay engaged in agentic development work. The best part—most of these are the same strategies I’ve used si...

My colleague Sam posted recently about LinkedIn shipping a “seems like AI slop” button. His take: it’s pointed at the wrong target, because slop predates the tools. “AI didn’t create the emptiness; it industrialized it.” I commented, offered a yes-and, and promised to stop before going full Foucault...

This spring I built myself an AI cycling coach. It reads my actual ride data, knows what my week looks like and writes my training around both. I’m not a developer. I’m a Delivery Lead – I bring the files to the customers so the engineers don’t have to. I spend all day around people […] The post How...

On a recent project, our team experimented with spec-driven development using AI agents. We expected to spend more time writing specifications and documenting project decisions. We also expected to review more generated code than we normally would. What I wasn’t prepared for was how much time we spe...

Live software demos have a special way of finding the one thing you did not rehearse. I recently put together a complicated sprint demo involving manual and automated behavior, smaller UI fixes, and an endpoint used to seed data. It went well! It also included an unavailable log source, unexpected s...

Atomic recently published Agentic Engineering for Teams, our process-level guide to pairing with AI agents for sustainable speed. This post is the view from the trenches. For the past two months, my team has been piloting agentic development on a HIPAA-compliant healthcare application, following a v...

I recently had the good fortune of speaking at CascadiaJS (shoutout to Carter Rabasa and the whole CJS team for putting on a truly wonderful event). I wanted to take the opportunity to reflect on the content, it’s reception, and where I think we go from here. I’ll note here that I’m specifically foc...

I’ve made a lot of slide decks for design work presentations over the years. It started with PowerPoint, where one minor movement of an image or paragraph could mysteriously break the entire page. I then moved to Google Slides, Miro, and Figma Slides, with each feeling slightly better than the last,...

‘For most of my eight-year career, my development environment was never really designed. It accumulated. Every new project, language, and workflow added another alias, plugin, editor setting, or command-line utility. Some of those additions became indispensable. Others solved a problem I had once an...

On my latest project, I was tasked with rebuilding a mobile app’s order customization workflow. This included work such as modifying the product itself and persisting that state live as well as in the cart when it was finally ready to be ordered. The work was planned as one feature branch that could...

I was at the AI Engineer World’s Fair in San Francisco a few weeks ago, and one phrase was everywhere: loops. The line everyone riffed on came from Claude Code creator Boris Cherny in an earlier talk: “I don’t write prompts for Claude anymore. … My job now is writing loops.” As an engineer, I was bo...

Anyone working on software can speak to the importance of documentation. They will tell you how helpful well-written documentation is, and how they would be lost without it. However, when it comes time to write said documentation, it becomes a chore. And by the time it is finally done, it always see...

Every city with innovation ambitions has the same ingredients list: capital, talent, universities, corporates, founders, and a calendar full of convenings. What separates the ecosystems that compound from the ones that stall isn’t the ingredients. It’s orchestration, the connective tissue that moves...

Every team optimizes for something, whether or not anyone says so out loud. Some optimize for reliability, some for speed to market, some for polish. Building fast and shallow is one of those choices, and on the right project, it’s a legitimate one. On my current project, that’s exactly the choice t...

Recently, I’ve been thinking a lot about the pace of our work. If you’re like me, you’ve probably noticed that using LLMs and AI agents can accelerate our output exponentially. It’s a rush. We can spin up environments, stub out boilerplate, and debug in seconds. We are moving projects forward, shipp...

A political campaign runs on volunteers, and almost none of those volunteers are programmers. For more than the past six months, I’ve been volunteering for a U.S. Senate campaign, building tools that help the campaign and other volunteers organize people and visualize data. What started as a small b...

Agent loops are in fashion these days, so I thought I’d talk about one of my favorite ones. Strangely, designing a useful agent loop turns out to be eerily similar to designing feedback loops in “pre-AI” software engineering. Or any sort of engineering, come to think of it. But let’s not overthink t...

I’ve been preparing a talk on getting real, reliable work out of AI, and I went down a deep research rabbit hole along the way. I read peer-reviewed studies, engineering write-ups from companies building these tools, and a surprising number of accounts from ordinary operators — a window importer, a ...

Recently, we welcomed a bright new member of Atomic’s Accelerator to our team. Coming straight from school, they’ve had limited exposure to development in the wild. As a result, there are tools I take for granted every day that they have never heard of. This includes tools that may seem obvious to e...

Google Sheets is one of those tools that feels forgiving, and it becomes miserably unhelpful when it breaks. You type something in, drag a formula down, and everything looks fine — until a formula starts pointing at the wrong cells, or a perfectly good ID number turns itself into a date. After years...

A couple of weeks ago, I had the pleasure of attending the AI Engineer World’s Fair. I stepped off the subway and made my way up the stairs toward Moscone West, nervous and excited. Finally — a few days to devote my full attention to sorting the real innovation from the hype. And I came […] The post...

In late June, our office quietly crossed a threshold worth reflecting on. With two new accelerators joining the team, we now have 9 women and 7 men in our Raleigh office. For the first time, women make up the majority of the people at my workplace, something not many in the tech industry can say. […...

A couple of months ago, I wrote about my client team’s decision to make human code review optional: an approval from an AI tool became all that was needed to merge. At the time, I said it was too early to tell. Now, enough time has passed to share some honest reflections. The Norms Didn’t […] The po...

Agentic development is fast. An agent can scaffold a feature, write the tests it thinks it needs, and open a pull request before you’ve finished your morning coffee. That speed is real, and agentic development is not going away. Which means the QA analysts who thrive in this brave new world won’t be...

Agentic engineering is changing the shape of how software teams work, and in doing so, is raising the value of judgment work. Strong consulting on what’s actually worth building becomes an even larger differentiator. Framing ambiguous problems clearly, validating the assumptions that a plan rests on...

If you’ve been a developer for a while, you’re probably adopting AI one way or another. I still remember the early days when prompts never got me what I wanted. I figured it would be a while before AI took over my job. Within weeks, however, as the models improved and I got better at […] The post Gr...

Every software system fails. This is inevitable. But burying errors doesn’t make them go away. As developers, we want to believe that our systems work as intended. So it’s easy to gloss over error handling. Until something actually goes wrong, it’s easier to log something vague and return success an...

On a recent project, I watched a team spend the better part of a week tracking down a single regression. The pipeline was a long-running simulation suite. Each test run took hours. There were dozens of commits to check, and the only way to check them was manually: run the sim, wait, evaluate the res...

Whether you use or even like AI, the genie is out of the bottle. What used to feel like a more personalized Google search can now index your entire codebase, explain how unfamiliar areas are structured, warn you of system design implications, and build features of surprising complexity. (Assuming, o...