The brain sandwich is a practical AI coding workflow: understand the problem, let an agent help, then verify and explain its work before sharing it.

You already have enough time. You just need to know what to do with it.

No tokens were spilled in the writing of this post, other than researching some of the references. This is entirely hand-crafted, artisan...

A French engineer discovered why people slack off in groups (social loafing). Progressive organizations like Buurtzorg and Haier found the antidote.

At some point, “moving fast” stopped being a practical concern and became a moral position. You see it damn near everywhere now. How fast can we ship this...

What 18 Years at Amazon Taught Me About Defining Problems

I treated MCPs as service connectors. The useful shift is a capability layer: search, execute, and reusable primitives an agent can compose on its own.

Or, perhaps the problem isn't that AI has broken code review, maybe it’s that we've been using code review to solve the wrong problems

Why review is the most leveraged skill in software right now.

Is your code ready for advanced agentic tooling? River Bailey explores the foundational practices that help both humans and AI amplify good work, and avoid repeating the existing problems.

Adapted from Mix and Match Robot expressions by anarres (Openclipart, CC0) I've been skeptical in general about sharing workflow skills. I have a bunch I share with direct collaborators, but there are a lot of "AI skills" repos out there and I've only found 2 of them really useful to me (#1, #2). I thought working out what you wanted and making your own was important - but I kept packaging up a similar set of skills to share with specific people, because I underestimated the value of having a starting point.

Magical thinking is a crutch for leaders who don’t know how (or don’t want) to do their jobs.

For real this time. It’s died N times already.

Cutting scope is a decision you defend. Cutting quality is one you hide.

Reversible decisions are sometimes not static!

Part 3 of a series where we take public "token saver" add-ons for coding agents and run the same paired A/B benchmark against each of them. Part 1 was the caveman skill (advertised −65%, measured −8.5

Practical frameworks for CTOs, CPOs, tech&product leaders scaling teams, delivery, and AI adoption. From a CTPO who ships with the teams she works with. Strategy, metrics, and field lessons from scal...

Evolving an agent's harness, not its model, on Harvey's LAB

AI acts as an amplifier of existing systems, and a sample first-year ROI of 39% only materializes after teams budget for a J-Curve productivity dip.

AI is great when it extends your brain. It gets dangerous when it quietly replaces the part that was supposed to think.

We won't ask whether it ever mattered...

YouTube video by BridgingTheGap

The most powerful thing about a Large Language Model is what sets it apart from any other regular task a computer might perform. Computers normally do someth...

How wiring the JetBrains MCP server into Claude Code gives your agent proper code navigation and refactoring, and stops it burning tokens reading half your repo

Harness Engineering is pretty trendy at the moment. Harness engineering is a way to better drive or operationalize an LLM model. The idea is...

A mental model for building trust in coding agents through feedforward guides, feedback sensors, and iterative harness engineering.

If you are still tied to your IDE, whether Cursor or Copilot, you are working a year behind. Coding turned out to be AI’s home territory. The best tooling ha...

Event-Driven by Oskar Dudycz

264 milliards d'euros s'échappent d'Europe chaque année. Pourquoi l'open source, sans une vraie stratégie de communs numériques, ne nous sauvera pas.

In 1958, Mao ordered every village to produce steel. The steel was useless. The crops rotted. Today's top-down AI mandates are producing the same pattern: ba...

Five git commands that tell you where a codebase hurts before you open a single file. Churn hotspots, bus factor, bug clusters, and crisis patterns.

Five git commands that tell you where a codebase hurts before you open a single file. Churn hotspots, bus factor, bug clusters, and crisis patterns.

Trisha is looking for her next career move. Also, new website design.

I know a software developer, call her A. B is the manager of another team, handling a critical project with plenty of tasks to be done, and dealing with escalations from other teams. A offered to …

Stop spamming the permission button. Learn how to set up Claude Code’s sandbox so your AI agent works freely and securely without constant interruptions.

In a previous article, I proposed replacing the technical debt metaphor with a road network analogy: our code is a network of roads that we…

AI coding sessions generate knowledge that disappears when the session ends. A TDD-inspired loop captures what you learned and routes it where your team will find it.

Per Anthropic’s most recent article on AI’s implications on the labor market, I belong to the most exposed occupation: computer programmers, with a 74.5% exposure risk. Such predictions undoubtedly …