I want to share my experience in the cloud, AI, and agents development areas.
The post explains why traditional Retrieval-Augmented Generation (RAG) approaches no longer scale and how modern architectures, including GraphRAG, address these limitations. It highlights why data quality, metadata, and disciplined system design matter more than models or frameworks, and provides a practical foundation for building robust RAG systems, illustrated with IBM technologies but applicable far beyond them.
This blog post outlines a practical example of setting up a custom component in Langflow to connect with an external weather API and import it into the watsonx Orchestrate Development Edition. The process emphasizes learning through experimentation rather than achieving a flawless solution, highlighting the potential of Langflow and watsonx Orchestrate for AI development.
The post discusses integrating Knowledge Graphs with Retrieval-Augmented Generation (RAG), specifically using Neo4j and LangGraph. It outlines an example setup where extracted document data forms a structured graph for querying. The system enables natural question-and-answer interactions through AI, enhancing information retrieval with graph relationships and embeddings.
The post outlines using the Evaluation Framework in watsonx Orchestrate ADK to verify AI Agent behavior through a practical example: Galaxium Travels, a fictional booking system. It details setting up the environment, defining user Stories, generating synthetic Test Cases, and running evaluations, crucial for ensuring AI reliability and transparency.
This post outlines the process of setting up a local watsonx Orchestrate server and invoking a simple agent via REST API using Python. It covers environment setup, Bearer token retrieval, agent ID listing, and code execution.
This post guides users through building an AI agent locally using the watsonx Orchestrate Agent Development Kit (ADK), exporting it from their local setup, and importing it into a remote instance on IBM Cloud. The process enhances local development while ensuring efficient production deployment.
This post shows how to use Langflow with watsonx.ai and a custom component for a “Temperature Service” that fetches and ranks live city temperatures. It covers installation, flow setup, agent prompting, tool integration, and interactive testing. Langflow’s visual design, MCP support, and extensibility offer rapid prototyping; future focus includes DevOps and version control.
The blog post outlines the process of setting up the Agent Developer Kit (ADK) to build and run AI agents locally using WatsonX Orchestrate Developer Edition. It involves setting up prerequisites, installing the necessary software, and loading an example agent—optional integration with Langfuse for observability.
The post explores the integration of Large Language Models (LLMs) in applications, stressing the need for effective production testing. It introduces the AI Operational Complexity Cube concept, emphasizing new testing dimensions for LLMs, including prompt testing and user engagement. A structured testing approach is proposed to ensure reliability and robustness.
This blog post explains how to deploy a fine-tuned model to IBM watsonx on IBM Cloud. It highlights the advantages of using this platform, such as avoiding infrastructure management and ensuring enterprise security, as well as detailed steps for configuration, deployment, and accessing the model from IBM watsonx.
Thomas Suedbroecker's Blog 