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/Week 2 — Agentic Systems/REACT Loops & Harnesses
OverviewESDS CourseAll Programs

Up next

Building Good Skills

Day 3: what separates a reliable, reusable skill from a brittle one, and how to build them.

On this page

    REACT Loops & Harnesses

    Days 1–2

    The first two days of Week 2 introduce agentic systems from the inside, by building one.

    Anatomy of an agentic system

    • The core loop: reason, act, observe, repeat.
    • Tools and actions: how an agent affects the world and reads back results.
    • Stopping conditions and control flow.

    Building a REACT loop

    • Implement a basic REACT (reason + act) loop from scratch.
    • Wire in a small set of tools and watch the loop use them.
    • Inspect each step so the system's behavior stays legible to you.

    Building a simple harness

    • Wrap the loop in a harness that manages prompts, tools, and state.
    • Add basic logging so you can see what the agent did and why.
    • Establish a clean seam between the agent and the rest of your code.

    Outcomes

    You'll finish these two days with a working REACT loop and a simple harness you understand end to end — the substrate for the more capable systems built later in the week.