Blog
204 posts · page 1 of 9
In a previous post I listed eleven ways an agent eval can lie, and one of them was trusting an uncalibrated LLM judge. This post covers what can go wrong with LLM-as-a-judge…
- The Bread Got Thicker·1 min
Matheus Lima's Brain Sandwich describes working with AI as think first, delegate, then think again. It maps neatly onto how I see the developer role changing. For most of my…
A SQL agent is asked the simplest question finance can ask: what was our net revenue last month? It answers 320.00. The right answer is 210.00. Nothing errors, the query looks…
That Test isn't Flaky. It's Broken. - In the era of AI agents, basic software engineering matters more, not less. Will Keleher argues for zero tolerance for intermittently failing…
I recently listened to two books back to back: Trillion Dollar Coach , about Bill Campbell, and Build by Tony Fadell. Campbell mentored Fadell, so I expected overlap. But the…
In January 2026, tldraw announced it would automatically close pull requests from external contributors "until GitHub provides better tools for managing contributions", and curl…
Twenty years ago this month I started my CS degree. Most of what I learned there has expired. What hasn't is more interesting, and it's mostly not what the syllabus was about.…
A PR label can carry intent. needs-review asks for a look; release-ready tells another group it can move forward. Getting that signal to the right people shouldn't need a second…
A pull request can fix a bug, change documentation, and add a test at the same time. Labeling it means answering several small questions, not writing an explanation. I built…
Engineering managers are writing more code again. What does that actually mean for the role, and is it something to celebrate or worry about? Several posts and articles published…
Computer use means an agent that looks at the screen, moves the mouse and types, so it can work with software that has no API: legacy portals, desktop apps, internal tools. It's…
In August, Stripe announced it had agreed to acquire OpenRouter — reportedly for more than $7 billion, per Bloomberg . OpenRouter helps businesses route and optimize token usage…
- Lead with Context·1 min
In recent weeks, I completed Northwestern University’s Organizational Leadership Specialization on Coursera. While the courses span different topics- storytelling, social…
Ron Wallace started as a UPS driver in rural Idaho in 1966 and retired 36 years later as President of UPS International, running operations in 200+ countries. His book,…
As I wrote in Tokens as Currency , token usage is becoming a real operating constraint. AI coding agents burn tokens on things they don't need to see in full - verbose logs,…
- Spec-Driven Development·2 min
I recently read Spec-Driven Development by Haim Michale, and it resonated with some day-to-day thoughts about SDD. The problem SDD aims to solve isn't new Missing, incomplete, and…
- RAG Made Simple·1 min
📚 Just finished " RAG Made Simple: The Complete Visual Guide to Retrieval-Augmented Generation " by Nir Diamant, and it happened to be one of those rare cases where the book…
- Kill Skill·2 min
Three recent incidents that should make all of us pause: → A hallucinated npx command spread through a single LLM-generated skill file to 237 repositories. Real agents executed…
- Make PRs Logical Again·1 min
The day-to-day work of software engineers is shifting - less time is spent on implementation, and more on specifying, planning, and reviewing. As AI coding tools improve, the…
Fun fact about me - I played Rugby Sevens for years, including on a national team. It taught me more about engineering leadership than I expected. Small teams, huge space, high…
The Quarterback Paradox - while I'm not sure I agree that it is a paradox - i.e., recruiting a critical position to an organization is hard even if you have a lot of data, I love…
With the growing adoption of AI and recent moves like Anthropic’s Cowork plugin marketplace , there’s a popular narrative that traditional SaaS is dead . The implication is that…
Last update: February 1st, 2026 Coding agents are no longer a novelty - they’re everywhere. Over the past year, we’ve seen massive adoption across startups and enterprises,…
A sense of humor is one of the most underestimated leadership skills Following the recommendation in “The Great CEO Within” I listened to “ The One Minute Manager ”. In one of the…
- Tokens as Currency·1 min
Half-baked thought: Tokens will become currency. Right now, the direction is obvious - more money buys more tokens. But what if, in the near future, tokens themselves become a…