Learning tracks by role
AI learning track: Software engineers new to AI
For software engineers adding language models and agents to their existing engineering skills.
After this track: You can explain an AI application’s components, test its behavior and review the code used to build it.
Follow these 12 steps in order, or return to the one you need for your current work. Reading times are estimates; listening times cover the full episode.
-
How do large language models actually work?
Start with how a language model generates output so you know which assumptions from ordinary software still hold.
-
What is a token in AI, and why does it decide what AI costs?
Understand the input and output units before estimating request size or inference cost.
-
Context Window
Add the request’s capacity limit to that model before designing conversation history or document inputs.
-
How do you give an AI assistant a useful brief?
Practice specifying tasks and constraints before adding retrieval or orchestration to compensate for unclear instructions.
-
What is RAG, and why do AI systems use it?
Follow the retrieve-then-generate flow before deciding how your application will supply facts the model lacks.
-
Embeddings
Learn what similarity search represents before choosing how to retrieve documents for that flow.
-
Vector Database
Connect embeddings to storage and search before treating a vector database as the whole retrieval system.
-
Should you use MCP or build a custom integration to connect AI to your tools?
Compare a shared tool protocol with a custom integration once you know which data and actions the application needs.
-
Do you still need an AI agent framework?
Decide how much orchestration the task needs before taking on a framework’s abstractions.
-
How do you test an AI system when the output isn't deterministic?
Build checks for variable outputs before letting a successful example stand in for a test suite.
-
250,000 Lines of Code/Week: Inside an AMD VP's Agent-First Workflow | Anush Elangovan
Examine a working AI-assisted coding process after establishing the tests you would need to trust its output.
-
Who reviews the code when AI writes most of it?
Finish by deciding how generated changes will be reviewed when writing code is faster than checking it.
Choose another role or continue through the five-level pathway.