Module · Intermediate
AI Agent Fundamentals
What an agent is, what a harness is, and when a problem actually needs an agent — and when it does not.
- 4 lessons
- 1h 13m
- 4 simulations
Included in Building AI Agents: Harness Engineering· $9
Harness Engineering
Context, permissions, sandboxing, errors and tracing — everything that makes an agent trustworthy outside a demo.
- Level
- Intermediate
- Lessons
- 4
- Total time
- 1h 2m
- Simulations
- 5
Included in Building AI Agents: Harness Engineering · $9
Tools you'll use
Python
Claude
OpenAI
FastAPI
Skills
- Context management
- Sandboxing
- Tracing
Try it now — free
This is the real simulation from the module. No account needed.
What you will be able to do
- Keep a long-running agent inside its context window
- Constrain what an agent is allowed to do
Before you start
A suggestion, never a lock — you can start here.
- agent-fundamentals
Modules that help first
Syllabus
4 lessons · 1h 2mEvery lesson's title and summary is public. The lessons themselves open once you own the track.
Every lesson in Building AI Agents: Harness EngineeringContext Management in Agent Loops
18 minTrimming, summarising and offloading when the task runs long — without losing the facts the next step needs.
Included with the track SimulationPermissions and Sandboxing
16 minAllowlists, human approval and isolated environments for risky tools — enforced by the harness, not by the model's good behaviour.
Included with the track SimulationError Handling and Recovery
14 minError messages that help the model correct itself, retries that do not make things worse, and when to give up.
Included with the track SimulationObservability and Tracing
14 minLogging every step, token and cost so failures can be traced — and so you know what a normal run looks like.
Included with the track Simulation
Lifetime access
$9More in Building AI Agents: Harness Engineering
Module · Intermediate
Tools and the Model Context Protocol
Connecting agents to APIs, databases and files — with MCP as the standard interface.
- 3 lessons
- 50 min
- 2 simulations
Included in Building AI Agents: Harness Engineering· $9
Module · Intermediate
Multi-Agent Systems
Orchestrators and workers, subagents and context isolation — when splitting the work helps, and when it hurts.
- 3 lessons
- 42 min
- 3 simulations
Included in Building AI Agents: Harness Engineering· $9
Module · Intermediate
Evaluating Agents
Task-level evals, trajectory analysis, and reliability and cost metrics.
- 3 lessons
- 46 min
- 3 simulations
Included in Building AI Agents: Harness Engineering· $9