Gen AI Lingo

Your next step

Why responses take time and cost money

Prefill, decode, caches, memory limits and end-to-end budgets.

Start learning

What you’ll learn

  1. Prefill reads the input

    Identify processing that happens before the first generated token.

    About 4 minutes · Open activity

  2. Decode generates the continuation

    Distinguish generation steps from input processing.

    About 4 minutes · Open activity

  3. A KV cache reuses attention work

    Explain why stored keys and values can avoid repeated computation.

    About 4 minutes · Open activity

  4. Prompt caching and answer caching differ

    Distinguish reused prefix computation from reusing a previous response.

    About 4 minutes · Open activity

  5. Memory capacity can limit a run

    Identify weights and temporary state as separate memory demands.

    About 4 minutes · Open activity

  6. A local interface can call a remote model

    Trace where inference and tools actually run.

    About 4 minutes · Open activity

  7. Budget the whole task

    Account for input, output, tool work and retries.

    About 4 minutes · Open activity

  8. Read a request receipt

    Locate prefill, decode, cache use and repeated work in two fictional receipts, and explain the tradeoff without naming a winning model.

    About 5 minutes · Open activity