Podcast - my new medium? 🎙️

Another highlight from my last day at IBC! 📺

The #AWS booth was packed throughout the entire event. It was challenging for me to explore beyond “just” captivation & monetization - there was so much to discover! 🚀

The final day allowed for a little more flexibility, and Olivier Boder and I ended up recording a podcast covering all the new trends in Media & Entertainment, Multi-Channel Monetization, and how customers can start implementing AI Agents as extensions of their existing teams. 🤖

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 …

The current state of the AI Agents ecosystem reminds me of the early days of technologies like Big Data/Hadoop or Containers/Kubernetes: many different tools, frameworks, and open source projects to choose from.

While flexibility is beneficial, it makes getting started quite challenging. Which direction should I go?

One either needs unlimited time and resources to explore options and make decisions, or requires solid, prescriptive guidance.

And here we go: If you’re looking at building AI Agents on AWS, the AWS Prescriptive Guidance - Agentic AI [1] serves as an excellent starting point. It provides guidance on the foundations of Agentic AI, patterns and workflows on AWS, and also covers the growing selection of Agentic AI frameworks, protocols, and tools available on AWS [2]. Note that the scope extends beyond AWS/Amazon frameworks and tools to include discussions of open source frameworks like LangChain and LangGraph, as well as protocols like MCP and A2A. Many more topics are covered, so I highly recommend reading it when getting started with your Agentic AI projects on AWS or when you want to re-evaluate earlier decisions.

Today I had a brief coding session with the newly launched Kiro [1]: a new agentic IDE that works alongside you from prototype to production.

I selected a use case I had previously coded myself, which helped me guide the coding agent through some challenging areas. It was impressive how quickly we achieved results, and the experience was genuinely enjoyable.

The use case involves generating a short advertising video from a high-level description. While the advertising video is the final output, the process also creates supporting assets like campaign descriptions, ad copy, and image assets. I requested a multi-agent implementation.

😋 What a fantastic recipe - Ingredients: Retail, Agentic AI, Cape Town Result: A unique South African curry. A little spicy, very tasteful and energising!

📈 Spent valuable time here in our office in Cape Town to discuss all things retail with customers and colleagues during the AWS Executive Retail Day. Together with Louise Liddell I presented “Retail Transformation in the Age of Agentic AI: From Data Strategy to Business Value”.

Diving into designing multi-agent systems and got lost with all the different implementation options? MCP (x)or A2A?! - Heiko’s and Dr. Sokratis Kartakis (any way to mention you in here just by your first name, mate?) nice article got your back. Highly recommended read! Congrats to both for being published there!

AlphaEvolve - takes me back into - my - history and into a bright future …

This month Google DeepMind released AlphaEvolve a new AI Agent which evolves algorithms for math and practical applications. In its core it’s combining evolutionary algorithms(SA) with the power of LLM.

Back in university, ouch we talk like 25y back, I studied evolutionary algorithms. EAs are in short an optimization techniques inspired by natural evolution . I tried to prove upper and lower bounds and the positive impact of providing and maintaining diversity in the populations. Hard work, with very limited success on my end. Since then I really looked back into EAs, but they are more relevant than ever.