At the ChatBot Summit in Berlin I gave a talk ‘How to understand why Agents fail’. Below is a transcript and the slides. As you all know there is a lot of innovation and buzz around agents and age...

Fine-tuning of Large Language Models allows customizations of AI models for specific tasks and data. While Fine-tuning used to require a lot of compute, technologies like InstructLab, QLoRA and lam...

AI agents can work autonomously by delegating tasks to different agents, models and tools. Various protocols are evolving to standardize the communication between agents. This post describes some p...

watsonx Orchestrate is a low code tool to build AI agents for business. It comes with a new component, called ‘Tool Builder’ to create flows via a graphical user interface or for developers via Pyt...

Watsonx.ai comes with the popular inference stack vLLM out of the box. With the latest version it’s also possible to deploy custom inference servers. Not every Generative AI Model can be run on vL...

Langflow is an open-source tool to build agentic applications via re-usable UI controls and Python code. This post demonstrates a simple example that introduces Langflow, its capability to invoke M...

IBM watsonx Agent Connect is a new technology to connect AI agents from any framework to IBM watsonx Orchestrate. This post explains how to build external agents and how to access them from watsonx...

watsonx Orchestrate provides observability through a native integration with an open-source project known as Langfuse, an LLM engineering platform supporting traces and observations. This post show...

This week IBM Think 2025 took place in Boston. Below are some of my highlights related to AI. Note that not all capabilities below are already generally available. For some features there are publ...

The IBM watsonx Orchestrate Agent Development Kit is a set of tools designed to make it easy to build and deploy agents using IBM watsonx Orchestrate. It supports integrating agents and tools built...