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...
Running Agents in watsonx Orchestrate via APIs
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 ...
Invoking watsonx Orchestrate APIs locally
Watsonx Orchestrate is IBM’s platform to run agentic systems. To make developers productive, Orchestrate can be run locally via the watsonx Orchestrate Developer Edition. This post describes how to...
Accessing local Models in watsonx Orchestrate via Ollama
Watsonx Orchestrate is IBM’s platform to run agentic systems. While low-code developers can use the user interface to build agents, pro-code developers can use the Agent Development Kit to build so...
Introducing the watsonx Orchestrate Tool Builder
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...
Custom Inference Stacks in watsonx.ai
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...
Building agentic Applications with Langflow and MCP
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...
Connecting AI Agents to IBM watsonx Orchestrate
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...
Observability in watsonx Orchestrate via Langfuse
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...
AI Highlights from IBM Think 2025
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...