Skip to content
All courses

Course 07

Agents & MCP

The agent loop as a mechanism you could draw, and everything wrapped around it: tools, MCP, context, permissions, evaluation and the bill.

Written for someone whose agent already works on the happy path and falls over everywhere else. You can build one; you cannot yet say why turn three called the wrong tool, where the tokens went, or what happens when the page it reads tells it to do something.

13
modules
60
lessons
145
curated videos
51h 19m
of video
01

What an agent actually is

Replace the word 'agent' with a mechanism you could draw on a whiteboard.

5 lessons · 12 videos · Free
02

Tools and function calling

Give a model hands, and make the hands safe: function calling, tool schemas, validating arguments, errors and retries, and having too many.

5 lessons · 11 videos
03

MCP: the protocol

Understand Model Context Protocol as a wire format, not a product.

5 lessons · 14 videos
04

Building an MCP server

Ship a server of your own and know why each part is there: a first server, exposing resources, testing it, and packaging it for other people.

4 lessons · 6 videos
05

Context engineering

The loop's real constraint is the window. Manage it deliberately.

5 lessons · 13 videos
06

Planning and decomposition

When a plan beats a bigger prompt: plan-then-execute, scratchpads, subtasks and checkpoints, and the cases where planning makes an agent worse.

4 lessons · 11 videos
07

Multi-agent orchestration

More agents is a design choice with a bill: when more than one is warranted, handoffs, subagents, orchestrator-worker, and committee cost.

5 lessons · 10 videos
08

Permissions and sandboxing

Decide what the loop may touch before it touches it: least privilege, sandboxed execution, human-in-the-loop gates, and handling credentials.

4 lessons · 12 videos
09

Untrusted input in a loop

The security model that changes once the model can act: prompt injection through tools, the lethal trifecta, OWASP's LLM Top 10, and real defences.

4 lessons · 10 videos
10

Evaluating agents

Judging a process, not an answer: why output eval falls short, building a test set, trajectory eval, LLM-as-judge, and regression before deploy.

5 lessons · 14 videos
11

Cost, latency and caching

Where an agent loop burns money and how to stop it: where tokens go, prompt caching, model routing, latency in a loop, and circuit breakers.

5 lessons · 10 videos
12

Observability and debugging runs

Reading a trace of something that will not repeat: what to log, tracing a run end to end, reproducing a bad run, and monitoring one in production.

4 lessons · 11 videos
13

Shipping an agent

Put it in front of people and keep it there: scoping what it may do, building a real one, the failure modes users see, and rolling out safely.

5 lessons · 11 videos

Curated from 15 channels

Every video is a public YouTube video. We pick the single clearest explanation for each lesson and credit the channel that made it.