Building Deep Research Agents (SciPy Practice Session)

Something a little different! Eric and I will be presenting an abridged version of our workshop for SciPy to a small group. Here is the session description from SciPy: Through the construction of a Deep Research Agent, tutorial participants will learn the fundamental building blocks of LLM-driven applications. Starting with in-context learning and prompt design, we will progress through memory management, tool integration via the Model Context Protocol (MCP), and planning workflows. Participants will build a working agent that can query a Zotero citation library, synthesize literature summaries, and engage in multi-turn research conversations. We will also discuss failure modes, limitations, and the role of such agents in an age of coding assistants. This will be a hands-on workshop so please come with your laptop and follow the installation instructions on the repo: https://github.com/ericmjl/build-deep-research-agent Since this is a small venue and very hands-on, we are limiting RSVPs. PLEASE do not RSVP unless you are sure you will be able to attend.