iiinova — where your digital self keeps evolving

Antony Marcano @antonymarcano.bsky.social · 12/05/2026

If what you mean is draw a diagram and a machine executes it... I'm not sure that applies here. This is more about "code" that is "executed" by a machine, from which a diagram is generated... So, perhaps not what you imagined? (Terms in "quotes" used VERY loosely)

000

Antony Marcano @antonymarcano.bsky.social · 10/05/2026

Yes, observability will be key. Also, agents monitoring other agent behaviours and alerting on 'misbehaviours'.

000

Antony Marcano @antonymarcano.bsky.social · 10/05/2026

Could your next Claude Code skill be a diagram? Not a diagram just describing the skill — a diagram that is the skill, executed like code. The answer is YES. Once you've tried it, you may not want to go back. antonymarcano.substack.com/p/claude-cod... #claudecode #ai #aiaugmented #claudeskills

antonymarcano.substack.com

Claude Code Skills as Executable UML

Could your next Claude Code skill be a diagram?

220

Antony Marcano @antonymarcano.bsky.social · 30/04/2026

Your Coding Agents Just Broke – Yet Nothing in Your Repo Changed?! This has just made another compelling case for a test-driven approach to your CLAUDE/SKILL.md changes when using coding agents at scale... Read on → open.substack.com/pub/antonyma... #aicoding #aiaugmented #claudecode

open.substack.com

Your Coding Agents Just Broke – Yet Nothing In Your Repo Changed

And there was nothing obvious that told you why

110

Antony Marcano @antonymarcano.bsky.social · 30/04/2026

There was a problem hiding in plain sight in that demo... did you spot it? My tests did... open.substack.com/pub/antonyma...

open.substack.com

Your Coding Agents Just Broke – Yet Nothing In Your Repo Changed

And there was nothing obvious that told you why

000

Antony Marcano @antonymarcano.bsky.social · 29/04/2026

Here’s the latest on the evolution of Stagentic-AI’s genesis project… Enabling Test-Driven Development of Claude Skills… open.substack.com/pub/antonyma... Now, every test-step is carried out by a separate sub-agent. Given – Haiku When – Opus (agent under test) Then – Sonnet Finally – Haiku Enjoy…

open.substack.com

Test-Driven Claude Skill Development Updated

Every test step is carried out by an independent subagent.

100

Antony Marcano @antonymarcano.bsky.social · 29/04/2026

Just for fun, I pointed NotebookLM's AI Podcast Hosts at my latest article "Taming Claude Code, One Agentic-Test at a Time"... It's metaphors, and insights – especially at the end – were a genuine surprise! Listen here (article linked in shownotes) open.substack.com/pub/antonyma...

open.substack.com

AI Debates... NotebookLM hosts discuss Test-Driven Agentic Behaviours

Another NotebookLM powered podcast debate, this time about my article “Taming Claude Code, One Agentic Test at a Time”.

000

Antony Marcano @antonymarcano.bsky.social · 28/04/2026

I was stuck in a “prompt and pray” loop, changing CLAUDE-md and SKILL-md files. Fix one behaviour, break another without even knowing. Until I realised this new problem… has an old solution. "Taming Claude Code,—One Agentic Test at a Time" open.substack.com/pub/antonyma... #claudecode #vibecoding

open.substack.com

Taming Claude Code, One Agentic-Test at a Time

Is This The Future of Prompt and Agent Engineering?

030

Antony Marcano @antonymarcano.bsky.social · 27/04/2026

When people say "guardrails", they really mean "guidance"... But there are true guardrails available. Combine both with gateways and not only do you have greater control over your coding agent, you improve token efficiency... → ideas.riverglide.com/what-people-... #AIcoding #agenticcoding

ideas.riverglide.com

What We All Got Wrong About Guardrails

When a coding agent does something it shouldn’t, people often say we need better guardrails. But what do they mean? What I often see…

011

Antony Marcano @antonymarcano.bsky.social · 09/04/2026

There were some audio issues in the previous video, so I've re-uploaded it here: bsky.app/profile/anto... I plan to take the previous post down in the next 24 hours.

000

Antony Marcano @antonymarcano.bsky.social · 09/04/2026

After discovering some audio issues, I've reuploaded this... new link here: bsky.app/profile/anto...

010

Antony Marcano @antonymarcano.bsky.social · 09/04/2026

What if you could develop your SKILL . md files in a test-driven way, just like your code? That was the question I asked myself, and the result was Test-Driven Agentic Behaviours (TDAB)... Let me show you → youtu.be/i3g9ZXiaqh0 (Re-uploaded) #ai #aiaugmentedcoding #aiassistedcoding #claudecode

youtu.be

Test-Driven Development of Claude Code Skills | Test-Driven Agentic Behaviours #TDAB

YouTube video by RiverGlide TV

011

Antony Marcano @antonymarcano.bsky.social · 08/04/2026

He didn't mean funny "haha". He meant "so coincidental that it's made me happy" funny.

110

Antony Marcano @antonymarcano.bsky.social · 08/04/2026

I swiped away as soon as I saw the waterfall diagram that said "Test & Debug" after coding 😬

210

Antony Marcano @antonymarcano.bsky.social · 08/04/2026

I've looked at it previously. But, that's not really the point of the video... It's more about test-driving the agent files themselves. Still, I've yet to see any skill execute TDD with the discipline I seek. However, it would be interesting to see if superpowers passes my agent test suite 🤔

400

Antony Marcano @antonymarcano.bsky.social · 07/04/2026

What if you could develop your SKILL . md files in a test-driven way, just like your code? That was the question I asked myself, and the result was Test-Driven Agentic Behaviours (TDAB)... Let me show you → youtu.be/uisjVdEvrCY #ai #aiaugmentedcoding #aiassistedcoding #claudecode

youtu.be

Test-Driven Development of Claude Code Skills | Test-Driven Agentic Behaviours #TDAB

YouTube video by RiverGlide TV

301

Antony Marcano @antonymarcano.bsky.social · 04/03/2026

If the collective comprehension and articulation of a concept is flawed, and our individual comprehension is flawed, then we cannot expect AI to be any less flawed than the material it has to work with. This seems to be at the heart of much of the debate in AI augmented coding.

031

Antony Marcano @antonymarcano.bsky.social · 26/02/2026

Mutation testing is a method that's becoming increasingly important with AI-augmented coding. Without it, we could risk future bugs in our agent-written code, even if what we release today seems to work. Read on: ideas.riverglide.com/mutants-in-t...

ideas.riverglide.com

Mutants in the Machine: The AI Illusion of Test-Driven Code

Mutation testing is a method that’s becoming increasingly important with AI-augmented coding. Without it, we could risk future bugs in our…

010

Reposted by Antony Marcano

Edward Wong @arkangelofkaos.bsky.social · 19/02/2026

Thanks to everyone that joined us for @xtclondon.bsky.social on Tuesday! Loved all the discussion sessions on enjoying programming, effectiveness of AI, security and "best vibe engineering practices" 💪 Looking forward to future meetups: www.meetup.com/extreme-tues...

132

Antony Marcano @antonymarcano.bsky.social · 19/02/2026

I recently joined Jack Hannah for a chat on @tuple's "Distributed" podcast. We talk about what distinguishes teams at the 'Elite' benchmark of DORA's Software Delivery Performance metrics, how AI is reshaping software delivery and more. Watch here: youtu.be/y7KZd6x7-lo (55mins)

youtu.be

Why faster coding doesn’t mean faster delivery

YouTube video by Tuple

012

Antony Marcano @antonymarcano.bsky.social · 18/02/2026

Is Your AI-assisted Coding Strategy Quietly Backfiring In 2026? Most AI-assisted coding strategies lean on one simple assumption: If developers can write code faster, delivery will be faster too. The latest DORA research suggests that assumption is wrong, more often than not. youtu.be/dQ1apxgvOa0

youtu.be

Is Your AI assisted Coding Strategy Quietly Backfiring?

YouTube video by RiverGlide TV

010

Antony Marcano @antonymarcano.bsky.social · 18/02/2026

"Product managers were frustrated by how long even small features took to release". By making it possible to slice their backlog differently an additional £2.6M in revenue was found, representing "repeated revenue they were likely missing out on for some time". ideas.riverglide.com/your-product...

ideas.riverglide.com

The Hidden Costs in Your Product Backlog

Your product backlog could be encouraging teams to structure their work in ways that carry measurable costs. For one company, this would…

000

Antony Marcano @antonymarcano.bsky.social · 11/02/2026

I need to be more active here 🤔

110

Reposted by Antony Marcano

Jason Gorman @jasongorman.bsky.social · 11/02/2026

Great catching up with @antonymarcano.bsky.social at The Rake in Borough Market tonight. Great conversation and some spiffy guest ales. Opinion was divided on the lemony one.

011

Antony Marcano @antonymarcano.bsky.social · 31/01/2026

Yes, that's the obvious part. The issues are: 1. Most teams don't do that well without AI, so more lower quality code is made faster. 2. And it only benefits an org if, once you commit/push your code, it flows with ease to production. If there's bottlenecks, it harms the org.

200

Antony Marcano @antonymarcano.bsky.social · 31/01/2026

Haha! Well, it doesn't come across like that to me. It seems he's very passionate about people getting the benefits of AI assisted coding, understands the pitfalls and limitations and is trying to help people understand them too.

000

Antony Marcano @antonymarcano.bsky.social · 30/01/2026

It's not stopping me... There's no reason why it can't be the way you described your others too, but while using AI is treated as more important than maintainable code and throughput of real value (which seems to be the case for many) - what's the most likely outcome?

200

Antony Marcano @antonymarcano.bsky.social · 30/01/2026

Yes, this is very true. I think a big problem is people communicate their needs in terms of a solution they have in mind. Behind that is at least an instinct of the problem to solve. If we ask what that problem is, we can help people find that path.

000

Antony Marcano @antonymarcano.bsky.social · 30/01/2026

Why the story of the viral skateboard-to-car, agile in a nutshell, image needs an unhappy ending... You’ve probably seen Henrik Kniberg's skateboard-to-car sketch a thousand times. But, not with this version of the story behind it... youtu.be/UR4Cq42BtbU #agile #agilesoftwaredevelopment

youtu.be

What Did This Viral Agile Diagram’s Story Miss Out?

YouTube video by RiverGlide TV

112

Antony Marcano @antonymarcano.bsky.social · 30/01/2026

I've been living over on LinkedIn all this time and forgot that BlueSky was a thing... Going to see what it's like here... And if anyone is listening.

130

Antony Marcano @antonymarcano.bsky.social · 07/02/2025

It feels odd to me when people say they code solo by default, and only pair when it makes sense. My default is to pair, and only code solo when that makes sense... which is generally exploring, when it's about discovery of new ways rather than executing on one of them. But only for short periods.

030

Antony Marcano @antonymarcano.bsky.social · 23/11/2024

Hello! Late to the party... But better late than never.

120