Agents & MCP - full curriculum

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

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

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

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.

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

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

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

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

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.

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

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.

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.

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.