Costs for AI-based applications depend primarily on inferencing, not on pre-training or fine-tuning. Inference costs depend highly on required memory usage. The new Granite 4 family of IBM’s open-s...

When building applications, developers often utilize standard tooling - Docker or Podman for containers, Ollama for local models. Context Forge aims to become the standard tool to manage agentic MC...

gpt-oss-120b is a powerful Large Language Model from OpenAI available as open-source. This post describes how to utilize gpt-oss-120b in watsonx Orchestrate agents. Watsonx Orchestrate is IBM’s pl...

The Agent to Agent Protocol (A2A) is an open standard designed to enable communication and interoperability between multiple agentic systems. Watsonx Orchestrate is IBM’s AI-powered platform used t...

The Agent2Agent (A2A) protocol is an open standard designed to enable seamless communication and collaboration between AI agents. This post explains how LangGraph agents can be extended to provide ...

LangGraph is one of the most popular frameworks to build agents. Watsonx.ai is IBM’s end-to-end AI development studio including various Large Language Models that can be utilized to build and host ...

This week at TechXchange 2025 IBM introduced project Bob, a tool for AI-based development of enterprise software. Below are two of my favorite features. Project Bob helps shipping quality software...

This week at TechXchange 2025 IBM introduced project Bob, a tool for AI-based development of software for enterprises. Below are some screenshots from the demo in the keynote. The landing page des...

Docling is an open-source framework to extract information from PDFs, DOCX, tables, images and other document types into structured data for scenarios like Generative AI and agentic applications. T...

Docling and Langflow are two popular open-source frameworks to extract information from documents and to build agentic applications. This post describes how to leverage Docling within Langflow. La...