Build the machinery around an agent loop.
Implement tool use, planning, reflection, memory, multi-agent coordination, evaluation, and guardrails around a deterministic model stand-in.
Implement and trace an agent loop
Design typed tools and validate calls
Add planning, reflection, and memory deliberately
Evaluate multi-step behavior and enforce guardrails
The Helpwell support agent, improved one capability at a time while its control flow remains inspectable.
Basic Python and familiarity with LLM prompts or APIs.
Open any module to review its exact sections. Progress and completion follow you through the course.
Topics include Chatbot vs agent, The agent loop, Model + Tools + Instructions, and more.
Topics include Function calling, Structured outputs, ReAct, and more.
Topics include Decomposition, Plan-and-Solve, Step dependencies, and more.
Topics include Self-Refine, Reflexion, CRITIC, and more.
Topics include Statelessness, Context window, Virtual memory (MemGPT), and more.
Topics include Handoffs, Supervisor / orchestrator-workers, Shared state, and more.
Topics include Outcome vs trajectory eval, Task success rate, pass^k reliability, and more.
Topics include Caps & sandboxing, Human-in-the-loop, Prompt injection, and more.
Engineers building tool-using AI systems
AI product teams reviewing agent architecture
Developers moving beyond chat interfaces
These are independent LDS courses that extend the closest skills. Choose the direction that matches what you want to build next.
Replace “it feels better” with evidence.
Engineer what the model sees and returns.
Turn one LLM call into a dependable service.
The first module establishes the language and example used throughout the rest of the course.
