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 โฆ
SoftwareEngineering
30 posts tagged SoftwareEngineering ยท all tags
2026
Architecting Skills: How Code Makes AI Agents More Reliable Over Time
Context Engineering: The Skill That Replaced Prompt Engineering
TL;DR: Patrick Debois coined DevOps in 2009 by naming what practitioners were already doing. In 2026, heโs doing it again with โContext Engineeringโ and the CDLC (Context Development Lifecycle): Generโฆ
Cognitive Debt: The Hidden Cost of AI-Generated Code
The Code Nobody Understands Hereโs a pattern Iโve seen across multiple teams: a data pipeline ships, built almost entirely by an AI coding agent. Clean architecture. Full test coverage. Passes every rโฆ
The Post-Agile Operating Model: How AI Changes How Teams Ship
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 5โ15% productivity โฆ
Code Quality Is the New Infrastructure
Ten talks. Ten practitioners from different companies โ Anthropic, Google, HashiCorp, Thoughtworks, Answer.AI, Factory, and independent creators. None of them coordinated. All arrived at the same concโฆ
The Bottleneck Moved: What 10 Studies Say About AI Developer Productivity
The Pattern I Keep Seeing Every few weeks, a customer asks me the same question: โWe rolled out AI coding tools to 500 engineers. Why arenโt we shipping faster?โ I wrote about this a month ago. The daโฆ
Software Fundamentals Matter More Than Ever
The Talk That Confirmed What Iโve 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 codinโฆ
AI Coding Productivity: 10%, Not 10x
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 singlโฆ
On the Loop, Not In It โ But Code Quality Still Matters
On the Loop, Not In It โ But Code Quality Still Matters Yesterday one of my AI agents wasted 15 minutes chasing a bug that didnโt exist. The function was called transformPayload(), but it didnโt transโฆ
Technology Evolution Doesn't Move in a Straight LineโIt Spirals
Technology Evolution Doesnโt 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 tโฆ
IT System Maintenance in the age of AI
IT System Maintenance in the age of AI Introduction - The Maintenance Trap in IT You donโt need to be in the IT industry for long to have witnessed this firsthand. Even non-IT users do. Those systems โฆ
๐ง ๐ง๐ต๐ฒ ๐ ๐ฎ๐ถ๐ป๐๐ฒ๐ป๐ฎ๐ป๐ฐ๐ฒ ๐ง๐ฟ๐ฎ๐ฝ: ๐ช๐ต๐ ๐ฌ๐ผ๐๐ฟ ๐๐ง ๐ฆ๐๐๐๐ฒ๐บ๐ ๐๐ฟ๐ฒ ๐ ๐ผ๐ฟ๐ฒ ๐๐ถ๐ธ๐ฒ ๐ฃ๐น๐ฎ๐ป๐๐ ๐ง๐ต๐ฎ๐ป ๐ฆ๐๐ผ๐ป๐ฒ๐
๐ง ๐ง๐ต๐ฒ ๐ ๐ฎ๐ถ๐ป๐๐ฒ๐ป๐ฎ๐ป๐ฐ๐ฒ ๐ง๐ฟ๐ฎ๐ฝ: ๐ช๐ต๐ ๐ฌ๐ผ๐๐ฟ ๐๐ง ๐ฆ๐๐๐๐ฒ๐บ๐ ๐๐ฟ๐ฒ ๐ ๐ผ๐ฟ๐ฒ ๐๐ถ๐ธ๐ฒ ๐ฃ๐น๐ฎ๐ป๐๐ ๐ง๐ต๐ฎ๐ป ๐ฆ๐๐ผ๐ป๐ฒ๐ After years of watching organizations struggle with outdated systems, Iโve written about a pattern we all know too wellโtheโฆ
Passing on control to your AI coding agent team entirely?
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 comโฆ
Kiro Subagents: Scaling Development with Specialized AI Agents
Kiro Subagents: Scaling Development with Specialized AI Agents When youโre building complex software, context management becomes your bottleneck. Your AI agent is juggling frontend components, backendโฆ
๐ฏ From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time
๐ฏ From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time โ๏ธ We need to balance Agency versus Control. We want AI systems to be super easy to use, read our minds, and just proโฆ
๐ฏ From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time
๐ฏ 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.โฆ
When a 'Model' Isn't Just a Model: Redefining AI Systems for the Builder's Era
When a โModelโ Isnโt Just a Model: Redefining AI Systems for the Builderโs Era ๐ฌ Great keynote by Jensen Huang at CES 2026 [1]! Great content and also love the ease of his presentation style. Miguel: โฆ
2025
๐
The Dawn of the Renaissance Developer
๐ The Dawn of the Renaissance Developer Itโs 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 denโฆ
๐ค '๐ช๐ฟ๐ถ๐๐ฒ ๐๐ถ๐ฟ๐๐ ๐ผ๐ฟ ๐๐๐ถ๐น๐ฑ ๐๐ถ๐ฟ๐๐? ๐ช๐ต๐ ๐๐ ๐ถ๐ ๐ฅ๐ฒ๐๐ฟ๐ถ๐๐ถ๐ป๐ด ๐๐ต๐ฒ ๐ฅ๐๐น๐ฒ๐ ๐ผ๐ณ ๐ฃ๐ฟ๐ผ๐ฑ๐๐ฐ๐ ๐๐ฒ๐๐ฒ๐น๐ผ๐ฝ๐บ
๐ค โ๐ช๐ฟ๐ถ๐๐ฒ ๐๐ถ๐ฟ๐๐ ๐ผ๐ฟ ๐๐๐ถ๐น๐ฑ ๐๐ถ๐ฟ๐๐? ๐ช๐ต๐ ๐๐ ๐ถ๐ ๐ฅ๐ฒ๐๐ฟ๐ถ๐๐ถ๐ป๐ด ๐๐ต๐ฒ ๐ฅ๐๐น๐ฒ๐ ๐ผ๐ณ ๐ฃ๐ฟ๐ผ๐ฑ๐๐ฐ๐ ๐๐ฒ๐๐ฒ๐น๐ผ๐ฝ๐บ๐ฒ๐ป๐ This week I had the pleasure of listening to a presentation by Brent Smith, who highlighted the value of prototypingโฆ
๐๏ธ In a fantastic interview 'How AI will change software engineering โ with Mart
๐๏ธ In a fantastic interview โHow AI will change software engineering โ with Martin Fowlerโ at the Pragmatic Engineer Podcast [1], Martin Fowler highlights the non-determinism introduced by Agentic AI โฆ
๐ง๐ต๐ฒ ๐๐ ๐๐ถ๐๐ฎ๐ฝ๐ฝ๐ผ๐ถ๐ป๐๐บ๐ฒ๐ป๐ ๐๐ฎ๐ฝ: ๐๐ฟ๐ฒ ๐ช๐ฒ ๐ ๐ฒ๐ฎ๐๐๐ฟ๐ถ๐ป๐ด ๐ฃ๐ฟ๐ผ๐ด๐ฟ๐ฒ๐๐ ๐ผ๐ฟ ๐๐๐๐ ๐๐ต๐ฎ๐๐ถ๐ป๐ด ๐๐ฒ๐ฎ๐ฑ๐น๐ถ๐ป๐ฒ๐?
๐ง๐ต๐ฒ ๐๐ ๐๐ถ๐๐ฎ๐ฝ๐ฝ๐ผ๐ถ๐ป๐๐บ๐ฒ๐ป๐ ๐๐ฎ๐ฝ: ๐๐ฟ๐ฒ ๐ช๐ฒ ๐ ๐ฒ๐ฎ๐๐๐ฟ๐ถ๐ป๐ด ๐ฃ๐ฟ๐ผ๐ด๐ฟ๐ฒ๐๐ ๐ผ๐ฟ ๐๐๐๐ ๐๐ต๐ฎ๐๐ถ๐ป๐ด ๐๐ฒ๐ฎ๐ฑ๐น๐ถ๐ป๐ฒ๐? Thereโs been incredible progress in #AI tools for software engineersโnew agents, coding assistants, and integrated workfโฆ
Absolutely brilliant. Made my start of the week. And in all seriousness - a good reminder to not jus
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 โฆ
Being in the industry for many years in different roles, this resonates deeply with me. Expert versu
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 Constantinโs article and a deep dive on the blog poโฆ
I like Adrian's 2nd thought. Amazing to see how technology advancement keeps lifting the level of ab
I like Adrianโs 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 wasnโt anything I wasโฆ
Heading home for weekend I spent some valuable time with a large AWS customer talking us through the
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 tradiโฆ
2024
Can I escape the never-ending cycle of โjustโ toying with new models to production?
Can I escape the never-ending cycle of โjustโ 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 โฆ
๐กOn my way back from a customer workshop on โPrompt Engineeringโ in Den Haag in the Netherlands. Goo
๐กOn my way back from a customer workshop on โPrompt Engineeringโ in Den Haag in the Netherlands. Good to connect with nature and an upcoming storm and very interesting to learn from customers about thโฆ
2022
Today is re:Purpose day, a great organisational initiative inย Tanuja Randery's organization. Many di
Today is re:Purpose day, a great organisational initiative inย Tanuja Randeryโs organization. Many different activities by different team members. Beside toeing the swimming pool for a first time sinceโฆ