I want to share my experience in the cloud, AI, and agents development areas.
This post shows the importance of clear prompt structure when developing local AI agents with frameworks like LangGraph and Ollama. Smaller models are less tolerant of ambiguities, making it crucial to separate instructions, context, and output formats. This enhances reliability, debugging, and reduces risks from untrusted inputs.
This article explores why governance becomes more important as software engineering becomes increasingly automated. It describes the evolution from human-centric development to AI-assisted and agentic engineering, where AI systems no longer only generate code but increasingly participate in engineering decisions. The main argument is that faster software creation does not automatically lead to better software. As AI accelerates implementation, accountability, traceability, reviewability, and human approval become more important. Effective governance allows organizations to use AI capabilities without losing human responsibility. It helps make AI-assisted software engineering more transparent, more reviewable, and more trustworthy.
AI is transforming the software development lifecycle, shifting focus from coding to reviewing AI-generated systems. While AI tools simplify software generation, building trustworthy systems remains complex. Traditional review processes may no longer suffice. This raises a critical question: how can humans responsibly.
This blog post explores the paradox of AI's growth potential versus the increasing trend toward data protectionism. It highlights how AI tools are hindered by data access limitations, posing risks to innovation. The observation implies that as data becomes more valuable, organizations may withhold it, undermining the openness that has historically fueled AI development.
This blog post details the author's exploration of IBM Bob while building an MCP server for Astra DB. It emphasizes learning through experimentation in Code Mode, focusing on automation and iterative development. The author shares insights on prompt creation, workflow challenges, and the importance of documentation throughout the process, ultimately achieving a functional server setup.
The post discusses automating local testing of IBM watsonx Orchestrate with Ollama models using a Bash script. The script simplifies the setup process, ensuring proper connections and configurations. It initiates services, confirms model accessibility, reducing typical setup errors.
The this post describes a Bash automation script for setting up the IBM watsonx Orchestrate Development Edition. The script automates tasks like resetting the environment, starting the server, and configuring credentials, allowing for a more efficient workflow. It addresses common setup issues, ensuring a repeatable and successful process.
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 post explores how Generative AI and Agentic AI emphasize trustworthiness over absolute determinism. As AI's role in enterprises evolves, organizations must focus on building reliable systems that operate under risk, balancing innovation with accountability. A personal perspective.
This blog discusses the emergence of agentic AI, capable of planning and executing complex tasks autonomously, contrasting with traditional generative AI. The post emphasizes the importance of managing expectations, oversight, and ensuring transparency due to the unpredictability, including potential hallucinations associated with these systems. LangGraph is highlighted as a powerful tool for developing agentic workflows.
Thomas Suedbroecker's Blog 