Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
Building AI Teaching Agents
·
Module 1
Foundations of LLM Agents
1
Beyond Simple LLM Calls: Understanding Agent Architectures
Distinguish agent architectures (e.g., controller-based) from simple LLM calls, deterministic workflows, and traditional RL agents.
2
Classifying AI Agents
Classify agents along axes of autonomy, tool access, planning horizon, and number of actors (single vs. multi-agent).
3
The Agent Loop: LLMs, Tools, and Memory
Describe the canonical agent loop (perceive → reason → act → observe) and identify where the LLM, controller, tools, and memory sit.
4
Agentic Workflows vs. Autonomous Agents: When to Use Which
Compare 'agentic workflows' (Anthropic) with 'autonomous agents' and articulate when each is appropriate.
LLM Agent Failure Modes
Identify the main failure modes of LLM agents, including hallucinated tool calls, infinite loops, context rot, and goal drift.
Next module isn't ready yet,
Back to course
Previous module
Next module