The question moved this week. Nobody serious is still asking whether agents can write the code: the people shipping the most are asking who verifies it, how cheaply, and how to move humans on top of t...

A stealth lab refreshes interest in narrow AI. Agentic coding keeps stressing CI platform infrastructure. The shape of the software factory is converging. Fundamentals matter more than ever. Pacing th...

dealing with AI's counterfeit utility, exasperated readers of LLMs, missing Creating Passionate Users, agents lack Verum Factum, three people making key decisions on AI

Multiple model launches took the headlines, none will change how you work on Monday. What might: an engineer shipping 2,000 PRs a month explained their actual method, AWS published what happens when f...

This week: code review collapsed, a linter that only flags problems turns out to be half a tool, and every repo is a software factory now. Cheap code made architecture visible rather than optional, to...

Anthropic shipped an invisible watermark into every Claude model launched after August 2, but how effective is it really? The AI productivity gain has a half-life, and the slop it leaves behind does n...

YouTube video by Jo Van Eyck

Will CI/CD survive agents? Steve Yegge and Jez Humble seem to disagree. OpenAI's model cracked ten long-open mathematical problems, a mathematician explained precisely what it still cannot do. Datadog...

YouTube video by Jo Van Eyck

This week we got our write-up of the Bun rewrite for $165k in tokens, Seldo published the numbers on what AI did to the junior market, and Hank Green explained why efficiency gains will make our AI bi...

fragments 06 Jul 2026

This link will take you to a page that’s not on LinkedIn

YouTube video by Jo Van Eyck

Leading the science of software success

Code is the result of hundreds of decisions an hour, coding agents that makes them in your stead are not saving you any time. Big tech is waking up to the fact that tokenmaxxing only results in higher...

OpenAI ran a negative 122% operating margin in Q1, Andrej Karpathy reframed his own term "vibe coding" as "raising the floor for everyone", putting it in sharp contrast with "agentic engineering". Gia...

Harness engineering is gaining traction, the maintenance bill from a year of vibe coding is coming due, and METR puts the first credible number on agent autonomy. The vocabulary of 2026 is stabilizing...

One type of discriminated union that is commonly used in F# is the Option type. The Option type is used to represent a value that may be p...

YouTube video by Jo Van Eyck

This week DORA weighs in on AI-assisted software development ROI in enterprise, the bottleneck conversation finally is starting to move up- and downstream from code to organization concerns, we gave t...

The honeymoon ended in stereo this week. More hard data on AI velocity landed (10-15%, not the 3X your CEO has been quoting), the pricing reset got calendar entries, the techlash got organised into ac...

This week, the receipts arrived from every direction at once. Thoughtworks' Tech Radar reads like a warning letter, frontier models silently corrupt a quarter of what you delegate to them, and the com...

Generation never was the bottleneck. This week the industry finally started noticing and we're landing on the uncomfortable truth: attention might be all transformer architectures need, but our own at...

YouTube video by Jo Van Eyck

Two independent datasets landed this week that make it hard to keep presenting AI productivity as a global rising tide, and in the same seven days DHH, Charity Majors, Fowler and Beck all arrived at the same uncomfortable conclusion: the window for rational skepticism has closed and its time for

GitHub Copilot CLI reads, writes, and runs code where you work. Code faster, smarter, together.

YouTube video by Jo Van Eyck

weekly agentic engineering digests. Curated for practitioners by practitioners

RTK cuts 80-99% of token waste from build output, git commands, and test runs. Here's how to get the automatic hook working on Windows, since the installer won't do it for you.

YouTube video by Jo Van Eyck

Welcome to F# Weekly, A roundup of F# content from this past week: News NBomber Studio 0.6.2 | NBomber F# Meetup (Recorded at NRK edition), Wed, Mar 25, 2026, 5:30 PM | Meetup Microsoft News Our co…

I don't think we have five years before agentic coding becomes the mainstream context in which professional software development happens. I think we're talking about two or three. Possibly less. If t...

This one goes out to all the testing neophytes who only recently realized (https://simonwillison.net/guides/agentic-engineering-patterns/red-green-tdd/) that it's useful to have an automated means of verifying their code does what it claims to do. For the last month, I've been working on prove_it (https://github.com/searls/prove_it), a framework for building quality harnesses for Claude Code (https://claude.com/product/claude-code)—primarily via its hooks system (https://code.claude.com/docs/en/hooks). In a recent release, I added TDD enforcement to its default configuration. First, it injects a test-first development approach into every plan Claude generates. Then, a PreToolUse hook follows up with permissionDecisionReason reminders whenever the agent deviates from the one true path (e.g., repeatedly edits source files without touching any tests, never runs a test to see it fail, etc.).

Breaking API migrations, hidden coupling, and large-scale rewrites — done safely with AST-backed AI workflows.

AI should help us produce better code - Agentic Engineering Patterns

Twitter's latest consensus on inevitability: now that large language models can write code, everyone will become a software developer. People, you see, have problems, and software solves problems, and AI removes the barrier between people and software, therefore everyone will build their own software. It's a syllogism, after a fashion,

YouTube video by Jo Van Eyck

Anti-patterns: things to avoid - Agentic Engineering Patterns

YouTube video by Jo Van Eyck

A Claude Code skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities

This piece by Margaret-Anne Storey is the best explanation of the term cognitive debt I've seen so far. Cognitive debt, a term gaining traction recently, instead communicates the notion that …

YouTube video by Jo Van Eyck

On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.