Tag: architecture

  • Don’t forget what I told you yesterday – AI memory and the mind palace – Tanzu Catsup

    If you’ve spent any real time with Claude Code or Cursor, you know the feeling. The thing you told the agent five minutes ago is now optional as far as it’s concerned. The fix isn’t a smarter model. It’s architecture. This week David Zendzian and I dig into memory for AI agents – what it…

    Read more

  • Eight years of wanting, three months of building with AI lalitm.com/post/buil… When I was working on something where I didn’t even know what I wanted, AI was somewhere between unhelpful and harmful. The architecture of the project was the clearest case: I spent weeks in the early days following AI down dead ends, exploring designs…

    Read more

  • Agents Don’t Know What Good Looks Like – And That’s a Design Constraint, Not a Bug

    Summarized by AI on April 11th, 2026. Luca Mezzalira reacts to a fireside chat between Neal Ford and Sam Newman on agentic AI and software architecture. The core argument is that current AI agents are stuck between novice and advanced beginner on the Dreyfus Model of Knowledge Acquisition – they can follow and even adapt…

    Read more

  • Cognitive Surrender, Supply Chain Rats, and Cthulhu at Mount Fuji – Related to your interests, Saturday

    Cognitive Surrender, Supply Chain Rats, and Cthulhu at Mount Fuji – Related to your interests, Saturday

    Also: invisible AI bottlenecks, Amex coding stats, Copilot for entertainment only, and why not both Earth from Orion after translunar injection, April 2, 2026. Two auroras and zodiacal light visible as Earth eclipses the Sun. NASA/Reid Wiseman, Artemis II Related to your interests Invisible Work in the Age of AI: The New Bottleneck in Architecture…

    Read more

  • Tanzu Catsup: The Risk of Relying on AI for Platform Engineering

    Internal development teams and executives are increasingly looking at AI to automate the creation of internal developer platforms. However, cobbling together open-source components with AI is a far cry from building a scalable, secure, and “enterprise-grade” environment. In this conversation, we explore why betting your internal infrastructure on AI-generated platforms is a high-stakes risk and…

    Read more

  • To have full sovereign IT, you need to build the software from the ground up. 🔗 two questions on software “sovereignty”

    Read more

  • A project is what IBM delivered at e&. Custom integration, IBM Consulting on-site, bespoke architecture tailored to one customer’s requirements. It works, but it doesn’t scale. Every enterprise becomes its own implementation, with its own timeline, its own integration challenges, its own dependency on consulting availability. “A platform is repeatable. Channel partners can sell it.…

    Read more

  • Recursive Loops, Enterprise Nanny-states, Garbage Chairs, and Improv

    Recursive Loops, Enterprise Nanny-states, Garbage Chairs, and Improv

    Garbage Chairs of Amsterdam, Duivendrecht edition. Original Content From Platform Engineering to Stand-Up Comedian, with Lian Li, Software Defined Talk #117: “In this episode, Whitney and Coté talk with Lian, a “cloud-native human” with a 15-year career in tech. Lian discusses her transition from tech to performance art, her experiences in amateur musical theater, stand-up…

    Read more

  • Related to your interests for Sunday

    “Moody’s Analytics recently estimated that the top 10 percent of households were responsible for nearly half of all spending.” K-shaped. AI is used a lot for making software. Not sure about the survey demographics and methodology. Deciding on Obama v. McCain in 2008. Keep track of things you’ve done each day so you realize you’re…

    Read more

  • “The question that actually determines success is simpler—and almost never asked: Are we ready to operate a private cloud as a product for the next 3–5 years?” 🔗 Before You Build a Private Cloud, Ask This One Question

    Read more

  • How shit actually works versus how you wish it worked

    A discussion of messy dichotomies from the robot: Thus spoke 🤖 : Exploratory vs Normative — Quick Reference A compact reference for thinking about how a framework is operating: discovering reality vs prescribing order. Exploratory vs Normative (academic, but precise) Exploratory: investigates what exists in the real world; derives insight from practice Normative: asserts what…

    Read more

  • Make it so the robots can use your shit, or you might be irrelevant. At least, less so. Platforms, tools or frameworks that are hard for large language models (LLMs) and agents to use will start feeling less powerful and require more manual intervention. In contrast, tools that are simple for agents to integrate with…

    Read more

  • Today’s lock-in was yesterday’s promise to open architectures.

    Read more

  • Programmer aesthetics: “your engineering taste is composed of the set of engineering values you find most important.”

    Programmer aesthetics: “your engineering taste is composed of the set of engineering values you find most important.” // And: “most bad taste comes from inflexibility. I will always distrust engineers who justify decisions by saying ‘it’s best practice.’ No engineering decision is ‘best practice’ in all contexts! You have to make the right decision for…

    Read more

  • Untitled post 54169

    Brutalist(?) Glasgow.

    Read more

  • How To Build Agentic AI That Ships – The New Stack – “Ninety-five percent of AI initiatives should be expected to fail as long as we ignore these pitfalls: Models are generic. Enterprises are unique. Ideal use cases aren’t flashy. Coordination across teams is hard.” // Lots of other good executive think too, especially being…

    Read more

  • Is Your IT Organization A Ponzi Scheme? – “The only way out is to stop borrowing against the future and start paying down the past. Escaping requires sustained platform investment — enough to reach equilibrium where debt stops growing. This means: Refactoring to improve code structure and reduce the cost of future changes. Refreshing technologies…

    Read more

  • Code was the least interesting part of my multi-agent app, and here’s what that means to me – Less time coding means more time designing and product managing.

    Read more

  • Expert Generalists – ”Traditional interview loops still revolve around product trivia – “Explain Spark’s shuffle stages,” “How does Databricks Delta time-travel work?” A candidate who has never touched those tools can still be exactly the kind of person we need: someone who quickly grasps unfamiliar concepts, breaks complex systems into manageable parts, and collaborates across…

    Read more

  • Did we just make platform engineering much easier by shipping a cloud IDP?Architecture Musings – Google Cloud IDP.

    Read more