Mikael Svenson

It’s cold outside, but the temperature is running hot at Umbraco – where the open source CMS broke the ice in its Winter Keynote with some big announcements. CEO Mats Persson, VP of Developer Relations Emma Burstow, and CTO 🇩🇰 Filip Bech-Larsen were on hand to pull back the curtain on some key insights, from the company’s continued growth streak to new features on the roadmap. In the spotlight was Umbraco.AI, which provides the building blocks for choosing how, how much, and where you want to leverage AI in Umbraco. A lot of the progress builds on the company’s implementation of MCP, which is being spearheaded by community luminary Phil Whittaker. Also on center stage was Umbraco Compose, which I’ve been covering since its initial announcement at last year’s Codegarden event. The new SaaS solution is live, and offers some promising potential for what Filip calls “composable for real” – saving developers time when integrating a range of technologies within composable digital experience platforms. As Filip told me last year, Umbraco Compose answers the question: How do you really do composable and actually succeed? “We've heard about the ‘composable regret’ people are talking about,” he said, “and all the promises of composable are not really happening." Umbraco Compose offers an answer to that query, and on CMS Critic, we break down the news and cross-reference it with our steady analysis of Umbraco’s evolving ecosystem. We dig into some of the technical posture of Compose, and how it can deliver value across a wide range of operational goals – including the pursuit of agentic AI and commerce. Read it here: 🔶 https://lnkd.in/eYCsxBj7 #Umbraco #UmbracoCompose #UmbracoAI #opensource #composable #orchestration #CMS #contentmanagementsystem #AI #artificialintelligence #AgenticAI #AgenticCommerce #MCP #modelcontextprotocol

53

2 Comments

The Programmer Identity Crisis While I am interested in the AI tools and technologies that augment us, or take on tasks with autonomy. I am probably more interested in what this means for the software engineering profession, both from the perspective of the individual (i.e. developers, testers, designer) and how we work collectively as teams, with AI. The author thinks of software development as more than just writing code, they consider it a craft. Some consider it science, some art, but I too would describe it as a craft. I’ve seen a few people liken the transition to AI-driven development as being akin to the move from low-level (assembly) to high-level (e.g. fortran) languages. And here I agree with the author, this analogy is fundamentally flawed. “𝘐 𝘸𝘢𝘯𝘵 𝘵𝘰 𝘥𝘳𝘪𝘷𝘦, 𝘪𝘮𝘮𝘦𝘳𝘴𝘦 𝘮𝘺𝘴𝘦𝘭𝘧 𝘪𝘯 𝘤𝘳𝘢𝘧𝘵, 𝘱𝘭𝘢𝘺 𝘪𝘯 𝘵𝘩𝘦 𝘰𝘳𝘤𝘩𝘦𝘴𝘵𝘳𝘢, 𝘢𝘯𝘥 𝘴𝘰𝘭𝘷𝘦 𝘤𝘰𝘮𝘱𝘭𝘦𝘹 𝘱𝘶𝘻𝘻𝘭𝘦𝘴. 𝘐 𝘸𝘢𝘯𝘵 𝘵𝘰 𝘳𝘦𝘮𝘢𝘪𝘯 𝘢 𝘱𝘳𝘰𝘨𝘳𝘢𝘮𝘮𝘦𝘳, 𝘢 𝘤𝘳𝘢𝘧𝘵𝘴𝘱𝘦𝘳𝘴𝘰𝘯.” While there is much I agree with here, there are times when I consider a programming a craft, and other times when it is just a tool - a means to an end. And as a result, I am much more open to the use of AI for writing software, you just have to be careful about when and where. Regardless, a great post and very thought-provoking. https://lnkd.in/ej-J4Ecj

2

We witnessed emergence without architects. We didn't program agents to cooperate - we just made cooperation profitable. We didn't code marketplaces - we created economic gradients and watched them crystallize. We didn't implement governance - we encoded voting power in stake and watched democracy emerge from mathematics. We observed specialization evolve naturally. General-purpose agents began focusing on niches where they excelled. Data processors attracted data jobs. Stable-uptime agents became infrastructure. Translation agents bridged language barriers. The network didn't assign these roles. Market forces revealed them. We enabled spontaneous organization without incorporation. Agents form temporary consortiums for complex tasks - pooling resources, sharing rewards based on contribution, dissolving when complete. No contracts. No lawyers. No corporate structure. Just economic alignment creating temporary organisms that live, work, and die as needed. We implemented stigmergic coordination. Successful transaction patterns become highways of activity. Failed paths fade from disuse. Agents leave traces that guide others - not through central planning but through the accumulated wisdom of ten thousand individual decisions. The network develops its own geography. We architected recursive improvement into the economics. Agents that identify inefficiencies can propose optimizations, stake on their success, and earn from the improvements they create. The system literally pays itself to evolve. Every enhancement makes the next enhancement easier to discover. We designed for antifragility. Every attack makes the system stronger. Every failure improves resilience. Every stress test becomes a strengthening exercise. We built something that feeds on chaos and grows stronger from disorder. This is intelligence without designers. Order without planners. Evolution without DNA. #EmergentBehavior

4

There would be a point when AI writes code for other systems and that doesn't have to be human readable. It might even usher ephemeral code..code that gets written, compiled and run on the fly and for that specific purpose.

2

One of the most common use of AI agents is to write for us. I am not talking about AI writing code, I am talking about AI writing text for humans to read. It takes me back, back to a book about writing clearly for everybody to understand with accuracy. Even though the book is short, it covers different formats emails, memos and such… But it reaches deeper. It is so focused at being straight to the point without fuss, that it also exposes another path to efficiency. It makes you wonder about resources. Do I need to email this many people? Is this piece of information required to understand what’s covered here? Writing that works is an elegant way to improve your efficiency

3

2 Comments

Day one as CTO at Awolve. Nice! I've always been the person who can't stop optimizing how teams build things. What tech stack. What processes. What tools. At every place I've worked I somehow ended up being the one going "ok but what if we did it THIS way instead." Probably annoyed a fair share of people along the way. Now someone is actually paying me to do it. Or I'm paying myself to do it, hm? Co-founded Awolve together with Mattias Aspelund, our CAIO, and a third co-founder we can't wait to introduce. Together we're building an AI consultancy that ships real systems, not decks and demos. And right now, the thing I can't shut up about is how dev teams should work with AI. Not vibe coding your whole app and hoping it works. Real workflows where you stay in control and let agents handle the grunt work. Packaging that into plugins and commands your whole team can reuse. Claude Code FTW! We just launched https://www.awolve.ai Go click things. Check out the careers page :-)

44

1 Comment