I want to share my experience in the cloud, AI, and agents development areas.
A structured experiment using ChatGPT and Codex in VS Code to generate a reproducible open-source Docling preprocessing pipeline with strict engineering constraints.
This post outlines the process of creating a deployable function in Jupyter Notebook using watsonx.ai, which is then exposed via a REST API. It emphasizes the separation of development in projects and runtime in deployment spaces, detailing steps from environment setup to function deployment and usage of the API endpoint.
The post discusses how the current focus on fast, outcome-driven innovation in the GenAI landscape risks sidelining invention, which nurtures genuine new possibilities. It emphasizes that while innovation thrives in KPI-oriented settings, invention often struggles for justification. The author calls for a deliberate balance to preserve the space for invention in future developments.
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.
Thomas Suedbroecker's Blog 