𝗙𝗿𝗼𝗺 𝗖𝗮𝗹𝗹 𝗖𝗲𝗻𝘁𝗲𝗿 𝘁𝗼 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗛𝘂𝗯: 𝗧𝗵𝗲 𝗙𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗦𝘂𝗽𝗽𝗼𝗿𝘁 𝗜𝘀 𝗛𝗲𝗿𝗲

Just returning from an internal Amazon Connect deep[1] dive. I haven’t touched this particular product since maybe 5 years?! Dirk Fröhner — I’m sure you remember our joint large-scale workshop with one of your customers.

What stuck with me from that time was how fast you can actually set up a contact center in the cloud — less than 30 minutes from zero to the first call received — and how much AI was already improving both the customer and agent experience back then. That hasn’t changed.

Most comprehensive overview on RAG I have seen. We came a long way from vanilla RAG. Still remember the time of arguments that RAG is just a “hot fix” to be obsolete soon. Reality is it is not a fix but the backbone of the majority of enterprise applications.

Kudos to Jin for putting this togehter. Should go to every practitioner’s back pocket !

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After years of watching organizations struggle with outdated systems, I’ve written about a pattern we all know too well—the maintenance trap in IT.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

What Anthropic is describing is the weaker version of this technique: applied externally, without permission, at an adversarial scale. Yet 16 million exchanges suggest MiniMax found the weaker version worth the effort. That’s the structural problem: if meaningful capabilities can be extracted even from outputs alone, the model itself is a depreciating asset. The moat is the rate of improvement, not today’s benchmark score. The labs that can stay ahead of the distillation cycle have defensible positions. The ones that can’t are selling last quarter’s capability at this quarter’s price." - straight to the point. Thanks Julien for this insightful analysis and sharing it. TIL - a lot!

From my perspective balancing AI Agents Agency with Control is one of the most important themes for 2026. We need to get this right both as builders and users for AI Agentic systems.

Anthropic’s study “Measuring AI agent autonomy in practice”[1] nicely fits into this as the started to study autonomy of ai agents based of usage of Claude Code and tool invocations. Already this first iteration provides some nice insights. Obviously a high focus on Coding use cases, but also indicating a wide variety of other use cases which resonate with my experience from customers I’m working with.

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.