CLARIPHY — AI agents and Large Language Models for Scientific Discovery

This hands-on tutorial introduces AI for scientific research, covering LLMs, multimodal data, RAG, and AI agents, using NRP resources. It culminates in JFC, a multi-agent framework demonstrating end-to-end HEP analysis workflows

Facilitators: Daniel Diaz and Andrzej Novak (MIT)

Schedule

StartLessonDuration
00:00Setup0 min
00:00Introduction — LLMs on NRP20 min
00:20Launch the Agent — JFC Physics Analysis on NRP15 min
00:35Chat with LLMs — Python, Multimodal, Embeddings & RAG50 min
01:25Agentic Workflows — opencode & IDE Integration45 min
02:10Build a Simple Agent — Tool Calling & the Agent Loop40 min
02:50Check In on the Agent — How JFC Ran, and What It Found10 min
03:00Finish

Times are cumulative and assume a prompt start.

Code and other resources used for this training session can be found in the materials/clariphy branch.