AI & ML Engineering · Unit 11 · AI Engineering
Working With LLMs
Using large language models through their APIs, reliably and at a known cost.
- 11.1
How LLMs Work
Tokens, context windows, temperature and next-token prediction.
- 11.2
Prompt Engineering
Instructions, examples, roles and chain-of-thought prompting.
- 11.3
Model APIs
Calling OpenAI, Anthropic and Google models, and how they differ.
- 11.4
Structured Output
Getting JSON you can trust, with schemas and validation.
- 11.5
Function Calling
Letting a model call your code through tool definitions.
- 11.6
Cost, Latency and Streaming
Counting tokens, choosing models and streaming responses.
Unit project
An LLM-powered tool that takes messy input and returns validated, structured output, with cost and latency measured.
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.