Getting Started

  • Welcome & Overview
  • Logistics & Format
  • Prerequisites
  • Project Component

Week 1 — Agentic Cowork Tools

  • Overview & Objectives
  • How LLMs & Agents Work
  • Working with Claude & Claude Cowork
  • Claude Code at Scale

Week 2 — Agentic Systems

  • Overview & Objectives
  • REACT Loops & Harnesses
  • Building Good Skills
  • Agentic Workflow Systems

Week 3 — Deep Learning

  • Overview & Objectives
  • DL Architectures & Training
  • Open-Source Models & Evaluation
ESDS Advanced/Getting Started/Project Component
OverviewESDS CourseAll Programs

Up next

Overview & Objectives

The week at a glance: from the fundamentals of LLMs and agents to running parallel Claude Code instances with remote MCP.

On this page

    Project Component

    Alongside the lectures and practice, ESDS Advanced is organized around team projects that build out real NOAA/NCICS-related tools during the course.

    The goal

    Teams work on a project across all three weeks, finding an aspect of each module to fold into a single final product. By the end, a project should ideally bring together:

    • Agentic cowork tools — for research, synthesis, reporting, and communication.
    • Agentic systems — a workflow that automates or augments part of the work.
    • Deep learning — a model that adds capability or insight.

    Cadence

    • Afternoons: dedicated project time.
    • Weekly presentations: each team shares progress at the end of the week.
    • Final presentation: teams present their completed product at the end of the course.

    What makes a good project

    Strong projects tend to:

    • Solve a real NOAA/NCICS problem, not a toy example.
    • Keep a human in the loop where scientific quality matters.
    • Validate results rather than trusting agent or model output blindly.
    • Produce something a non-technical stakeholder can actually use.

    Throughout the course, keep asking how the day's material could become a piece of your team's final product.