In his tech tutorial, Krishnendu guided participants through building a complete responsible AI pipeline using open-source large language models like LLaMA, Gemma, and GPT-OSS. He demonstrated how to create and orchestrate AI agents using frameworks such as Model Context Protocol (MCP), Agent-to-Agent (A2A), AutoGen, and Google ADK, while ensuring privacy and transparency. The session included live coding with tools like vLLM, Hugging Face Transformers, and Presidio, covering use case identification, agent building, orchestration, and privacy safeguards. By the end, attendees gained practical starter code, a minimal end-to-end implementation pipeline, and guidelines for developing decentralized, transparent, and privacy-preserving AI agents. This tutorial by Krishnendu Dasgupta was held on October 14th at DSC DACH 25 in Vienna.

Follow us on social media : LinkedIn: https://www.linkedin.com/company/11184830/admin/ Instagram: https://www.instagram.com/datasciconf/ Facebook page: https://www.facebook.com/DataSciConference Website: https://datasciconference.com/