AI & ML Engineering · Unit 13 · AI Engineering
AI Agents
Systems that plan, use tools and complete multi-step tasks.
- 13.1
The Agent Loop
Reason, act, observe: how an agent works through a task.
- 13.2
Tool Use
Designing tools and tool schemas an agent can use correctly.
- 13.3
Memory and State
Short-term and long-term memory, and managing context.
- 13.4
Planning and Multi-Step Reasoning
Breaking a goal into steps and recovering from errors.
- 13.5
Model Context Protocol
Connecting agents to tools and data through MCP.
- 13.6
Multi-Agent Systems
Orchestrators, sub-agents and when one agent is enough.
- 13.7
Guardrails and Human-in-the-Loop
Limits, approvals and safe failure.
Unit project
An agent that completes a multi-step task using at least three tools, with human approval before any irreversible action.
Paid learners get the full brief, submit it from their dashboard and have it reviewed. It goes in your portfolio.
Open every unit
Enrol once to open every unit, its videos and a reviewed project for your portfolio.