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...

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...

Watsonx Orchestrate is IBM’s platform to build and run agentic systems, from structured flows to autonomous systems. You can start simple via the Orchestrate user interfaces, but as a developer you...

Agentic applications can fail for multiple reasons. For developers it’s important to understand why they fail to improve the quality. To run evaluations, ground truth information is required which ...

There is a lot of buzz around autonomous agents. However, agents can fail. In these cases, it’s important for developers and AI engineers to understand why they fail to improve prompts, models and ...

The Model Context Protocol (MCP) has quickly become the standard how tools can be invoked from agents. There are different transport mechanisms, but some clients only support STDIO at this point. T...

The Model Context Protocol (MCP) has quickly become the standard how tools can be invoked from agents. This post contains a simple example how to invoke GitHub tools including authentication from w...

When building agentic systems, observability is key. While several demos seem to indicate that fully autonomous agents can already do everything, in reality often multi-agent systems fail. This pos...

Watsonx Orchestrate is IBM’s platform to run agentic systems. Agents can orchestrate work by delegating to multiple agents and tools. This post describes how external collaborator agents can get co...

Watsonx Orchestrate is IBM’s platform to run agentic systems. Developers can run Orchestrate locally via containers. This post describes how to run agents and models via APIs. Watsonx Orchestrate ...