AI & Data Articles
The AI Collaboration Paradox
One of our teams at SEP has gone all-in on agentic development. I don’t mean they’re simply using AI tools heavily; I mean they’re deliberately redesigning their team processes, shared infrastructure, and ways of working around it. When I was talking to the team about their experiences, one thing kept jumping out at me: AI […]
AI Agent Collaboration Starts with the Right Mental Model
You’re probably treating your AI agent like a junior developer. I know I was. It makes sense, right? The framing shows up in genuinely respected places — OpenAI’s own prompt engineering documentation advises treating GPT models like “a junior coworker” who needs explicit instructions to produce good output; engineering teams at major consultancies have characterized […]
Where AI Fatigue Actually Comes From
If you’ve spent time with agentic development, you’ve probably felt that particular flavor of mental exhaustion that hits harder than the work seems to justify. I wasn’t stuck on a hard problem. I wasn’t debugging something gnarly. I was just… keeping up. And then suddenly I wasn’t. Steve Yegge calls this the AI Vampire: the […]
The ‘Should We?’ Question: Evaluating AI Before You Commit
There is a common type of discussion happening at lots of companies right now. It may start when a competitor ships an AI feature, when a key stakeholder asks about the AI strategy, or when someone returns from a conference excited about what AI could do. The conclusion of “we need AI in our product” […]
I Had Claude Design an App via Figma Console MCP. Here’s What Happened.
I connected Claude to Figma via the Figma Console MCP and gave it one task: build an app with a scalable design system from scratch. Here’s what worked, what broke, and what it changed about how I specify design work.
Why the Best AI Agents Are Powered by a 3-Step Loop from 2022
Part 1 of the Data Governance & AI series I spent a month building an agent framework the “right” way. There were prescriptive JSON based workflows with staged pipelines, and a persistence layer for coordinating human-in-the-loop feedback. A gate review system enabled agents to validate each other’s work and loop back on failures. A debate […]
The Most Important Software Development “Tool” in the Age of AI
The software industry is rapidly evolving right before our eyes. It’s both exciting and somewhat terrifying to witness. Paradigm shifts are often uncomfortable, but we know that AI tooling is here to stay, so we need to make the most of it — in a responsible manner. It’s very easy to tell a coding agent […]
A Manager’s Guide to AI Adoption in Software Engineering Teams: Just Keep Prompting
AI tools for coding aren’t a nice-to-have anymore — they’re table stakes. At SEP, we recognized that early and gave engineering teams the green light to start using them, provided the tools met our security standards and our clients’. Once the green light was given, engineers across the organization were free to use AI in their work. The only stipulation: each […]
If You Can’t Wait 5 Years: Start Experimenting with AI for Robotics Today
In my last post, I discussed why the ChatGPT moment for robotics is likely still 5 years away. But if you can’t wait that long, this post has practical advice on how to start experimenting today. Be warned: the ecosystem is fragmented, the learning curve is steep, and (AI + hardware) == quirky. If you thought LLMs […]
Robot Foundation Models Are Not What I Was Expecting (I’m 5 Years Too Early)
When Physical Intelligence announced the π0 foundation model, I thought a ChatGPT moment in robotics was near. Here was a model that could control different kinds of robots to perform a variety of dexterous tasks. It could fold clothes, make coffee, assemble cardboard boxes, and more. I thought we’d get another post like swyx’s signaling robotics as an emerging capability of the […]
AI at the Table
I sit at a really weird saddle point currently. Professionally, I’m obliged to engage with generative AI technologies. I’m an AI technologist. I’ve been doing this for nearly twenty years at this point, and over ten past the doctorate. I can’t just ignore a new technology because I personally find it ethically dubious. Conversely, I’m […]
Planning-First AI Methodology: The Foundation of Successful AI Collaboration
Why starting with understanding, not code, is the key to unlocking AI’s full potential in software development Picture this: You’re 7 hours into your work day, you’re on your third cup of coffee, and the AI just generated 200 lines of code that compile perfectly… and do absolutely nothing you wanted. Sound familiar? If you’ve […]