schristoph.online

Architecting Skills: How Code Makes AI Agents More Reliable Over Time

Fri, 05 Jun 2026 00:00:00 +0000

TL;DR: An agent skill starts life as a markdown file full of instructions. It works, sometimes. Then you watch it fail in ways that are hard to predict, and you notice a pattern: the steps that break are always the mechanical ones, not the judgment calls. So you push those steps into scripts. Each migration from prose instruction to deterministic code removes an entire class of failures. Reliability was one of the hardest problems I covered in my AWS Summit Hamburg talk on moving agents from demo to deployment, and this is the same idea applied one level down: code is reliable because it removes ambiguity, and prose is flexible because it preserves it. A mature skill knows which is which.

The Skill That Worked, Sometimes

The first version of almost every skill I build is a markdown file. It reads like a runbook: “search my inbox for links I sent myself, summarise each one, append them to the reading list, then move the processed mails out of the inbox so they do not get picked up again.”

Context Engineering: The Skill That Replaced Prompt Engineering

Fri, 29 May 2026 00:00:00 +0000

TL;DR: Patrick Debois coined DevOps in 2009 by naming what practitioners were already doing. In 2026, he’s doing it again with “Context Engineering” and the CDLC (Context Development Lifecycle): Generate, Evaluate, Distribute, Observe. The core insight: as coding agents get more capable, the bottleneck shifts from writing code to assembling the right context. More context isn’t better — more precise context is. Teams that treat context as a versioned, tested, governed engineering artifact will compound an advantage that’s hard to replicate.

The Same Person, Seventeen Years Apart

In 2009, Patrick Debois organized a small conference in Ghent, Belgium. He needed a name, took the first three letters of “development” and “operations,” added “days,” and called it DevOpsDays [1]. The term stuck. It named a discipline that practitioners had been doing without a shared vocabulary. Within a few years, DevOps went from a conference hashtag to a job title, a team structure, and an industry worth billions.

Cognitive Debt: The Hidden Cost of AI-Generated Code

Thu, 21 May 2026 00:00:00 +0000

The Code Nobody Understands

Here’s a pattern I’ve seen across multiple teams: a data pipeline ships, built almost entirely by an AI coding agent. Clean architecture. Full test coverage. Passes every review gate. Two weeks later, a downstream service starts returning stale results. The on-call engineer opens the pipeline code and realizes she can’t explain why it had worked in the first place.

The logic is correct. The tests are green. But the mental model, the shared understanding of why this code makes these decisions, doesn’t exist. The agent wrote it. The team approved it. Nobody internalized it.

The Post-Agile Operating Model: How AI Changes How Teams Ship

Wed, 13 May 2026 00:00:00 +0000

The 7x Gap

Last month at the AI Engineer Summit, McKinsey presented findings from a survey of roughly 300 enterprises. The headline number was sobering: most organizations see only 5–15% productivity gains from AI coding tools. That’s it. After the licenses, the hackathons, the executive memos about “AI transformation.” A rounding error.

But buried in the same data was a different story. Top performers weren’t just doing slightly better. They were 7x more likely to have AI-native workflows spanning the entire development lifecycle, and 6x more likely to have restructured their teams around new roles. Their time to market improved 5–6x. One bank case study showed a 51% increase in code merges and a 60x increase in agent consumption after restructuring.

Code Quality Is the New Infrastructure

Fri, 08 May 2026 00:00:00 +0000

Ten talks. Ten practitioners from different companies — Anthropic, Google, HashiCorp, Thoughtworks, Answer.AI, Factory, and independent creators. None of them coordinated. All arrived at the same conclusion.

Clean code isn’t a nice-to-have in the age of agents. It’s infrastructure.

I spent the last few weeks watching the Pragmatic Engineer podcast series on AI-assisted software engineering, plus Jeremy Howard’s deep dive on Machine Learning Street Talk and Eno Reyes’s talk at the AI Engineer Summit. These aren’t pundits speculating about the future. They’re builders shipping production software with AI agents every day. And the pattern that emerges across all of them is striking: the bottleneck for agent productivity isn’t model capability. It’s the codebase the model has to work with.

The Bottleneck Moved: What 10 Studies Say About AI Developer Productivity

Mon, 04 May 2026 00:00:00 +0000

The Pattern I Keep Seeing

Every few weeks, a customer asks me the same question: “We rolled out AI coding tools to 500 engineers. Why aren’t we shipping faster?”

I wrote about this a month ago. The data says AI coding productivity is around 10%, not 10x [1]. The post hit a nerve. But the responses split into two camps. One said: “Yes, that matches what we see.” The other: “So AI is useless for engineering?” Neither is right. The 10% number is real, but it’s a symptom, not the diagnosis. The diagnosis is more interesting, and more actionable.

Software Fundamentals Matter More Than Ever

Thu, 30 Apr 2026 00:00:00 +0000

The Talk That Confirmed What I’ve Been Seeing

Matt Pocock stood on stage at the AI Engineer Summit and said something that most of the audience needed to hear: the developers who succeed with AI coding agents aren’t the ones who delegate everything. They’re the ones who fall back on engineering fundamentals [1].

After 18 months of teaching developers to build with AI agents through his “Claude Code for Real Engineers” course, Pocock has watched the same patterns emerge. The skills that matter aren’t new. They’re decades old. And they didn’t break when AI arrived. They got more important.

AI Coding Productivity: 10%, Not 10x

Wed, 01 Apr 2026 00:00:00 +0000

The Number Nobody Wants to Hear

A few weeks ago, I wrote about running my entire workday through an AI agent [1], meetings, research, CRM, content creation. Eight hours of productive work, not a single line of code. The response was overwhelmingly positive. But one comment stuck with me: “If AI agents are this good, why isn’t my team shipping 10x more?”

The answer is now backed by data from multiple independent studies, and it’s not what the vendor pitches suggest.

On the Loop, Not In It — But Code Quality Still Matters

Thu, 12 Mar 2026 00:00:00 +0000

On the Loop, Not In It — But Code Quality Still Matters

Yesterday one of my AI agents wasted 15 minutes chasing a bug that didn’t exist. The function was called transformPayload(), but it didn’t transform anything. It validated. The agent built three layers of transformation logic on top of it before realizing the name was a lie. I’ve seen this pattern dozens of times now. And it’s exactly why I think Kief Morris’s latest piece gets the big picture right but undersells one critical detail.

Technology Evolution Doesn't Move in a Straight Line—It Spirals

Tue, 10 Mar 2026 00:00:00 +0000

Technology Evolution Doesn’t Move in a Straight Line. It Spirals

The Proud Ops Colleague

Years ago, an Ops colleague proudly showed me something new. ClusterSSH, cssh [1]. A tool that opens multiple terminals to multiple machines, at the same time. You type once, it executes everywhere.

Back then, machines still had names. Ops folks knew their history, their specs, their quirks. They could tell you which server had been acting up last Thursday and what firmware it was running. And cssh? It let them follow the runbook consistently across every node. No more SSH-ing into machines one by one, hoping you didn’t forget a step on node 7.

🔧 𝗧𝗵𝗲 𝗠𝗮𝗶𝗻𝘁𝗲𝗻𝗮𝗻𝗰𝗲 𝗧𝗿𝗮𝗽: 𝗪𝗵𝘆 𝗬𝗼𝘂𝗿 𝗜𝗧 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗔𝗿𝗲 𝗠𝗼𝗿𝗲 𝗟𝗶𝗸𝗲 𝗣𝗹𝗮𝗻𝘁𝘀 𝗧𝗵𝗮𝗻 𝗦𝘁𝗼𝗻𝗲𝘀

Wed, 25 Feb 2026 00:00:00 +0000

🔧 𝗧𝗵𝗲 𝗠𝗮𝗶𝗻𝘁𝗲𝗻𝗮𝗻𝗰𝗲 𝗧𝗿𝗮𝗽: 𝗪𝗵𝘆 𝗬𝗼𝘂𝗿 𝗜𝗧 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗔𝗿𝗲 𝗠𝗼𝗿𝗲 𝗟𝗶𝗸𝗲 𝗣𝗹𝗮𝗻𝘁𝘀 𝗧𝗵𝗮𝗻 𝗦𝘁𝗼𝗻𝗲𝘀

After years of watching organizations struggle with outdated systems, I’ve written about a pattern we all know too well—the maintenance trap in IT.

Here’s the uncomfortable truth: We’ve all seen those systems that haven’t been updated in years. Aging interfaces, accumulating bugs, mounting security risks. We assess the cost of updates, weigh the business value, and often decide to “just skip this one.”

IT System Maintenance in the age of AI

Wed, 25 Feb 2026 00:00:00 +0000

IT System Maintenance in the age of AI

Introduction - The Maintenance Trap in IT

You don’t need to be in the IT industry for long to have witnessed this firsthand. Even non-IT users do. Those systems that haven’t been maintained for ages. From a user perspective, you “just” see a maybe aged user interface, non-evolving features, and old bugs or quirks become accepted by, possibly generations of, users. From a user perspective, you should have an eye on this. Often, this not only means that the system becomes cumbersome to use, but it also means that there are possibly no security updates being made. We will see just in a bit that it might even not be possible anymore. So think about which kind of data you want to put in there.

Passing on control to your AI coding agent team entirely?

Tue, 10 Feb 2026 00:00:00 +0000

Passing on control to your AI coding agent team entirely?

Anthropic researcher Nicholas Carlini conducted a stress test of their Claude Opus 4.6 model by deploying 16 parallel AI agents to build a complete C compiler in Rust from scratch(https://lnkd.in/eGMp4b2K). Over approximately two weeks and nearly 2,000 Claude Code sessions, the agents autonomously produced a 100,000-line compiler capable of compiling the Linux 6.9 kernel across multiple architectures (x86, ARM, and RISC-V). The experiment cost around $20,000 in API fees and demonstrated that coordinated AI agent teams can tackle complex systems programming challenges traditionally requiring significant human expertise and architectural oversight.

Kiro Subagents: Scaling Development with Specialized AI Agents

Mon, 09 Feb 2026 00:00:00 +0000

Kiro Subagents: Scaling Development with Specialized AI Agents

When you’re building complex software, context management becomes your bottleneck. Your AI agent is juggling frontend components, backend APIs, database schemas, testing frameworks, and documentation—all competing for limited context window space. The result? Diluted focus and suboptimal outputs.

Kiro Subagents solve this architectural challenge by enabling parallel task execution through specialized, autonomous agents that maintain independent context windows.

🏗️ The Architecture: Parallel Contexts, Focused Execution

Subagents operate as independent processes with their own context management. This architectural pattern delivers several technical advantages:

🎯 From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time

Fri, 30 Jan 2026 00:00:00 +0000

🎯 From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time

⚖️ We need to balance Agency versus Control. We want AI systems to be super easy to use, read our minds, and just provide the answer we need. But we also need to make sure that nothing goes wrong. The more we control, the less agency we get. This is a balancing act.

Let’s focus on the control part. There are many different mechanisms to increase and guarantee control. Things like policies and guardrails come to mind. Those are obvious and powerful. I will cover them in a dedicated post.

🎯 From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time

Thu, 29 Jan 2026 00:00:00 +0000

🎯 From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time

Agentic systems are incredibly flexible, but ad-hoc code generation means unpredictable results and wasted resources. How do we fix this without losing the magic? The answer lies in tools—prebuilt, tested, reusable components that make your AI agents more capable, reliable, and cost-efficient with every interaction.

With the right approach, your agents can become smarter and more efficient over time. Dive deep in the article below.

When a 'Model' Isn't Just a Model: Redefining AI Systems for the Builder's Era

Wed, 07 Jan 2026 00:00:00 +0000

When a ‘Model’ Isn’t Just a Model: Redefining AI Systems for the Builder’s Era

🎬 Great keynote by Jensen Huang at CES 2026 [1]! Great content and also love the ease of his presentation style. Miguel: We are not the only ones presenting in front of a black screen once in a while ;)

🔓 I agree with Jensen, it’s super exciting to see more and 𝗺𝗼𝗿𝗲 𝗼𝗽𝗲𝗻-𝗶𝘀𝗵 𝗳𝗿𝗼𝗻𝘁𝗶𝗲𝗿 𝗺𝗼𝗱𝗲𝗹𝘀 𝗯𝗲𝗶𝗻𝗴 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 by different providers. Sounds like NVIDIA is taking a big stake in this. Really key for me is that providers not “just” release open-weight models but also the data they trained on and the process used to train them. Jensen mentions the obvious responsible AI argument which is super important. This is the only way 3rd parties can verify the models and understand things like bias being introduced by the training data, copyright infringements, and alike. From my perspective, equally important: 𝗢𝗽𝗲𝗻 𝗶𝘀 𝗼𝗻𝗹𝘆 𝘁𝗿𝘂𝗹𝘆 𝗼𝗽𝗲𝗻 𝘁𝗼 𝗺𝗲 𝗶𝗳 𝗜 𝗰𝗮𝗻 𝗯𝘂𝗶𝗹𝗱 𝗶𝘁, 𝗺𝗼𝗱𝗶𝗳𝘆 𝗶𝘁 𝘁𝗼 𝗺𝗮𝗸𝗲 𝗺𝘆 𝗼𝘄𝗻 𝘃𝗮𝗿𝗶𝗮𝗻𝘁, 𝗮𝗻𝗱 𝗜’𝗺 𝗮𝗹𝗹𝗼𝘄𝗲𝗱 𝘁𝗼 𝗱𝗼 𝘀𝗼.

🌅 The Dawn of the Renaissance Developer

Mon, 15 Dec 2025 00:00:00 +0000

🌅 The Dawn of the Renaissance Developer

It’s that time of the year. AWS Community gets ready for the event of the year: re:Invent. And Werner publishes his tech predictions [1]. Like every year, a densely packed piece with loads of gems in it. This year Werner came up with 5 major themes, if I didn’t miscount. I covered the first one in my initial post [2].

The second one is about:

🤔 '𝗪𝗿𝗶𝘁𝗲 𝗙𝗶𝗿𝘀𝘁 𝗼𝗿 𝗕𝘂𝗶𝗹𝗱 𝗙𝗶𝗿𝘀𝘁? 𝗪𝗵𝘆 𝗔𝗜 𝗶𝘀 𝗥𝗲𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝘂𝗹𝗲𝘀 𝗼𝗳 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺

Mon, 01 Dec 2025 00:00:00 +0000

🤔 “𝗪𝗿𝗶𝘁𝗲 𝗙𝗶𝗿𝘀𝘁 𝗼𝗿 𝗕𝘂𝗶𝗹𝗱 𝗙𝗶𝗿𝘀𝘁? 𝗪𝗵𝘆 𝗔𝗜 𝗶𝘀 𝗥𝗲𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗥𝘂𝗹𝗲𝘀 𝗼𝗳 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁

This week I had the pleasure of listening to a presentation by Brent Smith, who highlighted the value of prototyping and empowering builders in the age of AI.

🔧 Why Prototyping Matters

Prototyping isn’t new—it’s a smart investment in any product development process. It enables early detection of design flaws, improves usability through real user feedback, and reduces costly mistakes before full-scale production. Prototyping aligns designs with manufacturing constraints, accelerates time to market, and builds stakeholder confidence by turning ideas into tangible, testable solutions.

🎙️ In a fantastic interview 'How AI will change software engineering – with Mart

Tue, 25 Nov 2025 00:00:00 +0000

🎙️ In a fantastic interview “How AI will change software engineering – with Martin Fowler” at the Pragmatic Engineer Podcast [1], Martin Fowler highlights the non-determinism introduced by Agentic AI as the big challenge for adoption. So big of a challenge that he compares it to the evolution from assembler code to higher-level programming languages.

🤔 Indeed, I see a lot of customers struggling with this non-determinism. What is correct? How do I evaluate a system? What about cascading effects in multi-agent systems?

𝗧𝗵𝗲 𝗔𝗜 𝗗𝗶𝘀𝗮𝗽𝗽𝗼𝗶𝗻𝘁𝗺𝗲𝗻𝘁 𝗚𝗮𝗽: 𝗔𝗿𝗲 𝗪𝗲 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗣𝗿𝗼𝗴𝗿𝗲𝘀𝘀 𝗼𝗿 𝗝𝘂𝘀𝘁 𝗖𝗵𝗮𝘀𝗶𝗻𝗴 𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲𝘀?

Tue, 30 Sep 2025 00:00:00 +0000

𝗧𝗵𝗲 𝗔𝗜 𝗗𝗶𝘀𝗮𝗽𝗽𝗼𝗶𝗻𝘁𝗺𝗲𝗻𝘁 𝗚𝗮𝗽: 𝗔𝗿𝗲 𝗪𝗲 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗣𝗿𝗼𝗴𝗿𝗲𝘀𝘀 𝗼𝗿 𝗝𝘂𝘀𝘁 𝗖𝗵𝗮𝘀𝗶𝗻𝗴 𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲𝘀?

There’s been incredible progress in #AI tools for software engineers—new agents, coding assistants, and integrated workflows are launching every week. Yet, when talking to customers, a common question keeps surfacing: are these AI investments really delivering value, or are they still more hype than help?

That’s why I found the latest Tech Lead Journal podcast with Laura Tacho (CTO at DX ) so insightful [1]. The episode dives into real-world research on AI adoption—and tackles the tough questions leaders are facing: • Why “acceptance rates” often mislead organizations • How to move past buzzwords and measure true AI impact (e.g. with DX’s practical AI Measurement Framework) • Which use cases save time today (surprisingly, stack trace analysis outranks code generation!) • Why AI should be treated as a strategic team extension, not a “magic bullet” or a replacement for developers.

Absolutely brilliant. Made my start of the week. And in all seriousness - a good reminder to not jus

Mon, 01 Sep 2025 00:00:00 +0000

Absolutely brilliant. Made my start of the week. And in all seriousness - a good reminder to not just blindly rushing with the innovation train into production, but e.g. apply good standard practices like testing. Still possible - and nicely supported - in those Agentic AI systems …

Being in the industry for many years in different roles, this resonates deeply with me. Expert versu

Tue, 29 Jul 2025 00:00:00 +0000

Being in the industry for many years in different roles, this resonates deeply with me. Expert versus Generalist. Highly recommend to have a read of Constantin’s article and a deep dive on the blog post by Martin Fowler, @gitanjalivenkatram and Unmesh Joshi. Super valuable. What are your thoughts on this? Join the discussion in the comments of Constantin’s article!

Yesterday I turned torture - a long 3-country car ride - into an entertaining learning opportunity.

Tue, 15 Jul 2025 00:00:00 +0000

I like Adrian's 2nd thought. Amazing to see how technology advancement keeps lifting the level of ab

Tue, 08 Jul 2025 00:00:00 +0000

I like Adrian’s 2nd thought. Amazing to see how technology advancement keeps lifting the level of abstraction.

While I learned some assembler back in the old days, pretty soon it wasn’t anything I was spending time on. Back at Siemens Mobile I was an App guy, purely writing application code in good old plain C, while our device driver guys were still coding in assembler. Clash of worlds when we had a production line standing still due to non-booting phones. Me and the device driver guy staring at the hardware debugger screen. He was wondering about those bloated C-structures the application stack created, then quickly pointed out an issue in the assembly code being shown right next to the C code. I never looked at it when I was debugging app issues. I would have never been able to spot the issue.

Heading home for weekend I spent some valuable time with a large AWS customer talking us through the

Fri, 23 May 2025 00:00:00 +0000

Heading home for weekend I spent some valuable time with a large AWS customer talking us through their experience with Generative AI in their software engineering. Characterising themselves as a traditional software development company they find a lot of value beyond the hype. Talking about efficiency gains well beyond “just” creating code and the hype cycle.

Generative AI is transforming software development in ways that go beyond writing code. Its most immediate and surprising impact is on automating routine, non-core engineering tasks, improving overall productivity and job satisfaction. Adoption is being led by junior staff, and the technology is democratizing who can contribute to building software. Leaders should encourage experimentation, be patient with evolving capabilities, and support their teams through the transition.

Can I escape the never-ending cycle of “just” toying with new models to production?

Mon, 16 Dec 2024 00:00:00 +0000

Can I escape the never-ending cycle of “just” toying with new models to production?

Most of us have been there. Trying out a new thing is super interesting to many of us. We are curious to understand what we could do, how it works. But then applying to reach a goal, while interesting at first, often entails a lot of efforts, which are not particularly exciting. While applicable to pretty much any aspect of our lifes, this is particular true in IT. Taking a proven concept into production is hard.

RAG - just a poor engineering workaround?

Wed, 25 Sep 2024 00:00:00 +0000

💡On my way back from a customer workshop on “Prompt Engineering” in Den Haag in the Netherlands. Goo

Wed, 22 May 2024 00:00:00 +0000

💡On my way back from a customer workshop on “Prompt Engineering” in Den Haag in the Netherlands. Good to connect with nature and an upcoming storm and very interesting to learn from customers about their experiences with GenAI. Still on the mission of turning authoring a prompt from a pure art form to more of an engineering approach. A Test driven, automated engineering approach for creating prompts has well resonated with the participants of the workshop - can’t wait to see that implemented. Big kudos to the participants who turned a potential boring presentation in an interactive exchange of ideas. Loved it!

Today is re:Purpose day, a great organisational initiative in Tanuja Randery's organization. Many di

Fri, 11 Mar 2022 00:00:00 +0000

Today is re:Purpose day, a great organisational initiative in Tanuja Randery’s organization. Many different activities by different team members. Beside toeing the swimming pool for a first time since a long pandemic break, I also spent some quality coding time in a cafe. While I have flexibility every day, the re:Purpose day really help me to actually get better in using it. And yes, we are hiring. Just ping me or Nahia Orduña :). #coding #hereataws #team #repurpose #passion