Skip to content

Learning tracks · Track 4 of 7

AI learning track: Software engineers new to AI

For software engineers adding language models and agents to their existing engineering skills.

Start with step 1: How do large language models actually work?

After this track: You can explain an AI application’s components, test its behavior and review the code used to build it.

  • 12 steps
  • 41 min reading
  • 1 episode, 51 min

The path

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.

  1. Step 1: Explainer About 5 min reading

    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.

  2. Step 3: Glossary About 2 min reading

    Context Window

    Add the request’s capacity limit to that model before designing conversation history or document inputs.

  3. Step 4: Explainer About 3 min reading

    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.

  4. Step 5: Explainer About 4 min reading

    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.

  5. Step 6: Glossary About 2 min reading

    Embeddings

    Learn what similarity search represents before choosing how to retrieve documents for that flow.

  6. Step 7: Glossary About 2 min reading

    Vector Database

    Connect embeddings to storage and search before treating a vector database as the whole retrieval system.

  7. Step 9: Explainer About 3 min reading

    Do you still need an AI agent framework?

    Decide how much orchestration the task needs before taking on a framework’s abstractions.

  8. Step 12: Explainer About 5 min reading

    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.

  9. Take it into your work. You can explain an AI application’s components, test its behavior and review the code used to build it.

Choose another track or continue through the five-level pathway.