Jo Van Eyck
@jovaneyck.bsky.social
I help software orgs get things done without shooting themselves in the foot. Technical coach, software crafter, legacy code wrestler.
Also, boardgames 🎲
Also, boardgames 🎲
Reposted by Jo Van Eyck
Key to efficient learning is realizing how we ACTUALLY learn, not just what FEELS like learning. I wrote a Claude Skill for some friends to help them think about this and they've liked it -- see Principles for some directions you could explore
github.com/DrCatHicks/l...
github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude Code skill for deliberate skill development during AI-assisted coding
A Claude Code skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
February 15, 2026 at 3:54 PM
Key to efficient learning is realizing how we ACTUALLY learn, not just what FEELS like learning. I wrote a Claude Skill for some friends to help them think about this and they've liked it -- see Principles for some directions you could explore
github.com/DrCatHicks/l...
github.com/DrCatHicks/l...
Reposted by Jo Van Eyck
Short musings on "cognitive debt" - I'm seeing this in my own work, where excessive unreviewed AI-generated code leads me to lose a firm mental model of what I've built, which then makes it harder to confidently make future decisions simonwillison.net/2026/Feb/15/...
How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt
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 …
simonwillison.net
February 15, 2026 at 5:22 AM
Short musings on "cognitive debt" - I'm seeing this in my own work, where excessive unreviewed AI-generated code leads me to lose a firm mental model of what I've built, which then makes it harder to confidently make future decisions simonwillison.net/2026/Feb/15/...
Buckle up. This year the way we write software will change.
In this video, I map out where software engineering is heading, introduce a practical maturity ladder and zoom in on essential skills if you want to stay effective in 2026 and beyond.
📺 youtu.be/6W_-YWHKwZ4
In this video, I map out where software engineering is heading, introduce a practical maturity ladder and zoom in on essential skills if you want to stay effective in 2026 and beyond.
📺 youtu.be/6W_-YWHKwZ4
You are Not Ready: Agentic coding in 2026
YouTube video by Jo Van Eyck
youtu.be
February 8, 2026 at 6:32 PM
Buckle up. This year the way we write software will change.
In this video, I map out where software engineering is heading, introduce a practical maturity ladder and zoom in on essential skills if you want to stay effective in 2026 and beyond.
📺 youtu.be/6W_-YWHKwZ4
In this video, I map out where software engineering is heading, introduce a practical maturity ladder and zoom in on essential skills if you want to stay effective in 2026 and beyond.
📺 youtu.be/6W_-YWHKwZ4
Reposted by Jo Van Eyck
I have Gas Town derangement syndrome and spent the last few weeks writing thousands of words on agent orchestration patterns; how they shift our bottlenecks and force us to ask whether and when we should stop looking at code
maggieappleton.com/gastown
maggieappleton.com/gastown
Gas Town’s Agent Patterns, Design Bottlenecks, and Vibecoding at Scale
On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code
maggieappleton.com
January 23, 2026 at 2:26 PM
I have Gas Town derangement syndrome and spent the last few weeks writing thousands of words on agent orchestration patterns; how they shift our bottlenecks and force us to ask whether and when we should stop looking at code
maggieappleton.com/gastown
maggieappleton.com/gastown
Reposted by Jo Van Eyck
Discord wants to know how you feel about AI.
Go tell them: discord.sjc1.qualtrics.com/jfe/form/SV_...
Go tell them: discord.sjc1.qualtrics.com/jfe/form/SV_...
Qualtrics Survey | Qualtrics Experience Management
The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.
discord.sjc1.qualtrics.com
January 10, 2026 at 12:53 AM
Discord wants to know how you feel about AI.
Go tell them: discord.sjc1.qualtrics.com/jfe/form/SV_...
Go tell them: discord.sjc1.qualtrics.com/jfe/form/SV_...
Reposted by Jo Van Eyck
Published: What is Continuous Delivery?
It takes nine principles, one heuristic, three foundations, one pattern and three practices to practice truly Continuous Delivery.
thinkinglabs.io/articles/202...
It takes nine principles, one heuristic, three foundations, one pattern and three practices to practice truly Continuous Delivery.
thinkinglabs.io/articles/202...
What is Continuous Delivery?
thinkinglabs.io
January 9, 2026 at 2:30 PM
Published: What is Continuous Delivery?
It takes nine principles, one heuristic, three foundations, one pattern and three practices to practice truly Continuous Delivery.
thinkinglabs.io/articles/202...
It takes nine principles, one heuristic, three foundations, one pattern and three practices to practice truly Continuous Delivery.
thinkinglabs.io/articles/202...
In this video we'll quickly go over the awesome "AI augmented coding patterns" by @lexler.bsky.social and others.
Are you a cyborg or a centaur? Watch the video and find out!
youtu.be/54I-mOMwdtM
#aiaugmentedcoding #claudecode #githubcopilot #cursorcode
Are you a cyborg or a centaur? Watch the video and find out!
youtu.be/54I-mOMwdtM
#aiaugmentedcoding #claudecode #githubcopilot #cursorcode
AI coding patterns (that actually work)
YouTube video by Jo Van Eyck
youtu.be
December 23, 2025 at 11:02 AM
In this video we'll quickly go over the awesome "AI augmented coding patterns" by @lexler.bsky.social and others.
Are you a cyborg or a centaur? Watch the video and find out!
youtu.be/54I-mOMwdtM
#aiaugmentedcoding #claudecode #githubcopilot #cursorcode
Are you a cyborg or a centaur? Watch the video and find out!
youtu.be/54I-mOMwdtM
#aiaugmentedcoding #claudecode #githubcopilot #cursorcode
Reposted by Jo Van Eyck
Visualization of Day 3 (Lobby), written in Elm #AdventOfCode einarwh.no/aoc/2025/day...
Lobby
einarwh.no
December 4, 2025 at 10:31 AM
Visualization of Day 3 (Lobby), written in Elm #AdventOfCode einarwh.no/aoc/2025/day...
Advent of code in F# - day 4
After modular arithmetic and dynamic programming, today felt like a breath of fresh air 😅
youtu.be/RF-YIFsPe7A
#adventofcode #fsharp
After modular arithmetic and dynamic programming, today felt like a breath of fresh air 😅
youtu.be/RF-YIFsPe7A
#adventofcode #fsharp
🎄 Advent of code 2025 in F# - day 04
YouTube video by Jo Van Eyck
youtu.be
December 4, 2025 at 6:36 AM
Advent of code in F# - day 4
After modular arithmetic and dynamic programming, today felt like a breath of fresh air 😅
youtu.be/RF-YIFsPe7A
#adventofcode #fsharp
After modular arithmetic and dynamic programming, today felt like a breath of fresh air 😅
youtu.be/RF-YIFsPe7A
#adventofcode #fsharp
🎄 Advent of code 2025 in F# - day 02
YouTube video by Jo Van Eyck
youtu.be
December 2, 2025 at 6:39 AM
Reposted by Jo Van Eyck
That’s a wrap for day one of #SocratesBE
Here’s a FOMO inducing photo of today’s marketplace.
What you don’t see is Vincent’s legendary lightning talk on Limburgse Vlaai. That happened Thursday evening already.
Here’s a FOMO inducing photo of today’s marketplace.
What you don’t see is Vincent’s legendary lightning talk on Limburgse Vlaai. That happened Thursday evening already.
October 10, 2025 at 10:38 PM
That’s a wrap for day one of #SocratesBE
Here’s a FOMO inducing photo of today’s marketplace.
What you don’t see is Vincent’s legendary lightning talk on Limburgse Vlaai. That happened Thursday evening already.
Here’s a FOMO inducing photo of today’s marketplace.
What you don’t see is Vincent’s legendary lightning talk on Limburgse Vlaai. That happened Thursday evening already.
Reposted by Jo Van Eyck
F# folk - I've started a PR to add F# support to the Serena MCP server, that effectively allows the use of the F# language server from coding agents.
github.com/oraios/seren...
Please be welcome to contribute to get this over the line.
cc @chethusk.bsky.social
Thanks
Don
github.com/oraios/seren...
Please be welcome to contribute to get this over the line.
cc @chethusk.bsky.social
Thanks
Don
Add F# support using FsAutoComplete LSP by dsyme · Pull Request #662 · oraios/serena
This adds F# support by the usual path, using the standard F# LSP
Using Serena with F# Projects
This guide demonstrates how to use Serena's tools with F# projects through both the MCP protocol...
github.com
October 10, 2025 at 11:11 AM
F# folk - I've started a PR to add F# support to the Serena MCP server, that effectively allows the use of the F# language server from coding agents.
github.com/oraios/seren...
Please be welcome to contribute to get this over the line.
cc @chethusk.bsky.social
Thanks
Don
github.com/oraios/seren...
Please be welcome to contribute to get this over the line.
cc @chethusk.bsky.social
Thanks
Don
Reposted by Jo Van Eyck
I've become one of those people who run multiple coding agents at once - here are my notes on embracing the parallel coding agent lifestyle simonwillison.net/2025/Oct/5/p...
Embracing the parallel coding agent lifestyle
For a while now I’ve been hearing from engineers who run multiple coding agents at once—firing up several Claude Code or Codex CLI instances at the same time, sometimes in …
simonwillison.net
October 5, 2025 at 1:56 PM
I've become one of those people who run multiple coding agents at once - here are my notes on embracing the parallel coding agent lifestyle simonwillison.net/2025/Oct/5/p...
Reposted by Jo Van Eyck
AI agents being able to run unit tests is SUCH a massive unlock.
If you're a dev who has utilized unit tests heavily: using a tool like Claude Code makes so much sense.
And if you don't yet use tests: with AI agents, don't see how you would not do it sooner or later...
If you're a dev who has utilized unit tests heavily: using a tool like Claude Code makes so much sense.
And if you don't yet use tests: with AI agents, don't see how you would not do it sooner or later...
September 30, 2025 at 9:58 PM
AI agents being able to run unit tests is SUCH a massive unlock.
If you're a dev who has utilized unit tests heavily: using a tool like Claude Code makes so much sense.
And if you don't yet use tests: with AI agents, don't see how you would not do it sooner or later...
If you're a dev who has utilized unit tests heavily: using a tool like Claude Code makes so much sense.
And if you don't yet use tests: with AI agents, don't see how you would not do it sooner or later...
Reposted by Jo Van Eyck
I'm ready to accept a definition of "agent" that I think is widely-enough agreed upon to be useful, at least in the AI engineering space:
An LLM agent runs tools in a loop to achieve a goal
(I've been dismissing the term as hopelessly ambiguous for years) simonwillison.net/2025/Sep/18/...
An LLM agent runs tools in a loop to achieve a goal
(I've been dismissing the term as hopelessly ambiguous for years) simonwillison.net/2025/Sep/18/...
I think “agent” may finally have a widely enough agreed upon definition to be useful jargon now
I’ve noticed something interesting over the past few weeks: I’ve started using the term “agent” in conversations where I don’t feel the need to then define it, roll my eyes …
simonwillison.net
September 18, 2025 at 7:15 PM
I'm ready to accept a definition of "agent" that I think is widely-enough agreed upon to be useful, at least in the AI engineering space:
An LLM agent runs tools in a loop to achieve a goal
(I've been dismissing the term as hopelessly ambiguous for years) simonwillison.net/2025/Sep/18/...
An LLM agent runs tools in a loop to achieve a goal
(I've been dismissing the term as hopelessly ambiguous for years) simonwillison.net/2025/Sep/18/...
Reposted by Jo Van Eyck
I don’t think people yet fully appreciate how the “lethal trifecta” restricts agentic AI use cases. When private data access, untrusted inputs, and external actions converge, you create a structural vulnerability we don’t yet know how to contain.
simonwillison.net/2025/Jun/16/...
simonwillison.net/2025/Jun/16/...
The lethal trifecta for AI agents: private data, untrusted content, and external communication
If you are a user of LLM systems that use tools (you can call them “AI agents” if you like) it is critically important that you understand the risk of …
simonwillison.net
September 8, 2025 at 8:29 AM
I don’t think people yet fully appreciate how the “lethal trifecta” restricts agentic AI use cases. When private data access, untrusted inputs, and external actions converge, you create a structural vulnerability we don’t yet know how to contain.
simonwillison.net/2025/Jun/16/...
simonwillison.net/2025/Jun/16/...
Ever wondered how AI coding agents like Claude Code, Github Copilot and Codex work? So did I! So of course I had to go and build one myself 😅
youtu.be/7oTPNr9APGE
#claudecode #codex #cursor #copilot #anthropic #openai #llm #agenticai #ai
youtu.be/7oTPNr9APGE
#claudecode #codex #cursor #copilot #anthropic #openai #llm #agenticai #ai
I Built an AI Coding Agent in 200 Lines of Code.
YouTube video by Jo Van Eyck
youtu.be
August 31, 2025 at 5:20 PM
Ever wondered how AI coding agents like Claude Code, Github Copilot and Codex work? So did I! So of course I had to go and build one myself 😅
youtu.be/7oTPNr9APGE
#claudecode #codex #cursor #copilot #anthropic #openai #llm #agenticai #ai
youtu.be/7oTPNr9APGE
#claudecode #codex #cursor #copilot #anthropic #openai #llm #agenticai #ai
Can AI coding agents do Test-Driven Development (TDD) properly? They sure can!
In this week's video I take a look at two approaches: prompt engineering & using the tdd-guard library
📺 youtu.be/IVdYaVKuekk
#ai #aiassistedcoding #claudecode #tdd #testdrivendevelopment #tddguard
In this week's video I take a look at two approaches: prompt engineering & using the tdd-guard library
📺 youtu.be/IVdYaVKuekk
#ai #aiassistedcoding #claudecode #tdd #testdrivendevelopment #tddguard
Can AI coding agents do Test-Driven Development (TDD)?
YouTube video by Jo Van Eyck
youtu.be
August 24, 2025 at 12:06 PM
Can AI coding agents do Test-Driven Development (TDD) properly? They sure can!
In this week's video I take a look at two approaches: prompt engineering & using the tdd-guard library
📺 youtu.be/IVdYaVKuekk
#ai #aiassistedcoding #claudecode #tdd #testdrivendevelopment #tddguard
In this week's video I take a look at two approaches: prompt engineering & using the tdd-guard library
📺 youtu.be/IVdYaVKuekk
#ai #aiassistedcoding #claudecode #tdd #testdrivendevelopment #tddguard
Reposted by Jo Van Eyck
LLMs and coding agents are a security nightmare
garymarcus.substack.com/p/llms-codin...
#ai #genai #llm #programming
garymarcus.substack.com/p/llms-codin...
#ai #genai #llm #programming
LLMs + Coding Agents = Security Nightmare
Things are about to get wild
garymarcus.substack.com
August 18, 2025 at 2:28 PM
LLMs and coding agents are a security nightmare
garymarcus.substack.com/p/llms-codin...
#ai #genai #llm #programming
garymarcus.substack.com/p/llms-codin...
#ai #genai #llm #programming
AI coding assistants promise 10x productivity gains. The research tells a different story.
Full breakdown here: youtu.be/MLSs8Asmthk
#aiassistedcoding #claudecode #githubcopilot #dora
Full breakdown here: youtu.be/MLSs8Asmthk
#aiassistedcoding #claudecode #githubcopilot #dora
Busting the AI coding productivity myth
YouTube video by Jo Van Eyck
youtu.be
August 17, 2025 at 7:18 PM
AI coding assistants promise 10x productivity gains. The research tells a different story.
Full breakdown here: youtu.be/MLSs8Asmthk
#aiassistedcoding #claudecode #githubcopilot #dora
Full breakdown here: youtu.be/MLSs8Asmthk
#aiassistedcoding #claudecode #githubcopilot #dora
Reposted by Jo Van Eyck
AI may not make you a 10x engineer, but understanding how to use AI assisted coding frameworks can cost 20x less.
Diagram shows an experiment by @jovaneyck.bsky.social using MCPs with Claude Code vs without MCPs
Diagram shows an experiment by @jovaneyck.bsky.social using MCPs with Claude Code vs without MCPs
August 15, 2025 at 9:10 PM
AI may not make you a 10x engineer, but understanding how to use AI assisted coding frameworks can cost 20x less.
Diagram shows an experiment by @jovaneyck.bsky.social using MCPs with Claude Code vs without MCPs
Diagram shows an experiment by @jovaneyck.bsky.social using MCPs with Claude Code vs without MCPs
Reposted by Jo Van Eyck
It's the 10th anniversary of this joke. I originally posted it on Twitter, and I felt it deserved a new home. It has been quoted in books, presentations, academic lectures, and t-shirts, and it's probably the only thing I'll be remembered for 🤣
August 15, 2025 at 2:50 PM
It's the 10th anniversary of this joke. I originally posted it on Twitter, and I felt it deserved a new home. It has been quoted in books, presentations, academic lectures, and t-shirts, and it's probably the only thing I'll be remembered for 🤣
Everyone’s chasing 10x boost from coding assistants. In my coding I get nowhere near that promised 10x. But in other areas it comes close!
Inside my Obsidian vault, I built:
* Semantic search
* Interactive quizmaster
* slide decks to text
Watch here: youtu.be/nSh2BYJ29kY
#claudecode #obsidian
Inside my Obsidian vault, I built:
* Semantic search
* Interactive quizmaster
* slide decks to text
Watch here: youtu.be/nSh2BYJ29kY
#claudecode #obsidian
This combo makes smart note systems magical.
YouTube video by Jo Van Eyck
youtu.be
August 10, 2025 at 9:59 PM
Everyone’s chasing 10x boost from coding assistants. In my coding I get nowhere near that promised 10x. But in other areas it comes close!
Inside my Obsidian vault, I built:
* Semantic search
* Interactive quizmaster
* slide decks to text
Watch here: youtu.be/nSh2BYJ29kY
#claudecode #obsidian
Inside my Obsidian vault, I built:
* Semantic search
* Interactive quizmaster
* slide decks to text
Watch here: youtu.be/nSh2BYJ29kY
#claudecode #obsidian
Reposted by Jo Van Eyck
"PhD-level experts in your back pocket" is a completely nonsensical description of AI but a pretty good description of social media if you follow the right people
August 9, 2025 at 11:07 PM
"PhD-level experts in your back pocket" is a completely nonsensical description of AI but a pretty good description of social media if you follow the right people
AI coding assistants not working for you because your legacy codebase is too big? There's a solution!
In this video I share one-click and FREE solutions that give Claude Code a staggering 30x performance boost when working in large codebases.
youtu.be/UqfxuQKuMo8
#aiassistedcoding #claudecode
In this video I share one-click and FREE solutions that give Claude Code a staggering 30x performance boost when working in large codebases.
youtu.be/UqfxuQKuMo8
#aiassistedcoding #claudecode
AI coding agents are useless on large codebases. Unless you do THIS.
YouTube video by Jo Van Eyck
youtu.be
August 2, 2025 at 3:14 PM
AI coding assistants not working for you because your legacy codebase is too big? There's a solution!
In this video I share one-click and FREE solutions that give Claude Code a staggering 30x performance boost when working in large codebases.
youtu.be/UqfxuQKuMo8
#aiassistedcoding #claudecode
In this video I share one-click and FREE solutions that give Claude Code a staggering 30x performance boost when working in large codebases.
youtu.be/UqfxuQKuMo8
#aiassistedcoding #claudecode