Recently, a partner team on one of my projects unexpectedly stepped away from work we depended on. Without their part, we could not ship the feature we were building. That made the situation both urgent and potentially difficult. A developer on my team had been leading much of the coordination and p...

Atomic Object Raleigh has several ongoing projects, all of which involve varying degrees of AI-assisted coding, as well as some creating agentic applications. Recently I asked other engineers in our office to share their thoughts on Model Context Protocol (MCP) Servers. MCP is a standard that lets A...

I recently reviewed the codebase behind a small professional services company’s custom platform. Buried in the source was this: if you send the production system a request with a header named “bypass” and a hard-coded password, you skip login entirely and get administrative access to their productio...

About a mile from the finish on Sunday, I stopped to take in a gel and some water. And my stomach turned over. I was seven and a half miles around Mackinac Island, in a wetsuit, with nothing to do about it. So I breathed. Slow and deliberate, for longer than I wanted to. It […] The post 2 Years, 2 S...

In April, I spent a morning at the Apple Manufacturing Academy Summit at MSU, where Apple and Michigan State train companies to implement AI. The room was operations leadership. People who run the work, not people who write AI strategy memos. A McKinsey presenter put up a spend breakdown for AI depl...

New agent commands and skills are being created all over the interwebs. Most of the daily emails I subscribe to have become a deluge of new agent workflows promising to supercharge my productivity. Until recently, I hadn’t spent much time creating my own agent tools, so in a lot of ways I simply had...

When we moved into our new office, the team had to decide where we’d sit. There were two real options: an area all the way across the floor from the managing partners, or the area right next to them. I said I wanted to be next to them. I was the only one. The pushback […] The post Pick the Desk Wher...

When and how do you surface a concern to your team? We all observe risks, constraints, or areas for feedback on a daily basis: an estimate that the developers feel is unrealistic, a consensus that’s gathering momentum without a team agreement, or a process that’s become more of a hindrance than a he...

I’ve developed a set of tasks where I typically leverage AI. Those are things like generating a test, explaining an unfamiliar corner of a codebase, or answering the little questions that used to cost me a browser tab and 15 minutes of an afternoon. But I’ve started to notice that other developers a...

As a developer, I’m always looking for tools that make my life easier. However, with the never-ending stream of updates Codex provides, I hadn’t taken the time to see what this harness could do for me until I watched a demo of Jason Liu’s setup (developer experience engineer at OpenAI). That demo ma...

I used to think SQLAlchemy was mostly a way to avoid writing SQL. That wasn’t a compelling pitch. I already knew SQL. Why add another abstraction and debug whatever the ORM decided to do behind the scenes? Then I built an endpoint that needed to: Update a document’s status Create signing sessions Wr...

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 ...