AI Model Wiki

    Skip to main content
    20 min
    Lesson 5 of 5
    practice

    Hands-On Practice

    From the course Prompt Caching & Cost Optimization

    Put what you have learned in this course into practice with the structured exercise below. Working through it end-to-end is the single best way to consolidate the concepts.

    Exercise: Prompt Caching Optimization in the Real World

    Pick one realistic scenario from your own work, study, or curiosity and apply the techniques covered in earlier lessons. Aim for a small, completable artifact — a notebook, a working script, a written design, or a side-by-side comparison.

    Suggested Workflow

    1. Frame the goal: write a one-sentence problem statement that the techniques in this course can address.
    2. Pick the right tool: revisit the lessons above and choose the specific method, model, or pattern that best fits.
    3. Build an MVP: produce the simplest version that proves the approach works. Keep it small.
    4. Evaluate: how did it perform? What surprised you? What broke?
    5. Iterate: refine one decision (prompt, parameter, tool) and re-evaluate.

    Self-Check Questions

    • Could you explain the chosen approach to a teammate in under two minutes?
    • Where might this break in production? What guardrails would you add?
    • What is the next thing you would try if you had another day?

    Stretch Goal

    Document your run as a short write-up. Compare against alternative approaches and note the trade-offs.

    This practice loop converts passive reading into durable skill — the exact transfer-of-learning step most learners skip.

    Concrete Starter Project: Optimize a Customer Support Chatbot

    Goal: Take an existing chatbot with a large system prompt and measure and optimize its cost using prompt caching and model routing.

    Steps:

    1. Build a simple chatbot with a 3,000-word system prompt (use a customer support FAQ document).
    2. Log token usage (prompt tokens, completion tokens, cache read tokens) for every API call to a CSV.
    3. Enable Anthropic prompt caching on the system prompt with cache_control: { type: "ephemeral" }.
    4. Run 100 test conversations and compare cost per conversation before vs. after caching.
    5. Implement a simple model router that sends queries containing "order" or "account" to claude-haiku and complex queries to claude-sonnet.

    Extend it:

    • Add Redis-based response caching for the 20 most common questions.
    • Build a cost dashboard that shows cost per conversation, daily spend, and cache hit rate.
    • Calculate the monthly break-even analysis for each optimization technique.

    What you will learn: How to measure AI costs accurately and apply layered optimization strategies for real production cost reduction.

    Key Takeaways

    • •Hands-on application converts course concepts into real skill
    • •Start small with an MVP before optimising
    • •Self-check questions catch gaps in understanding before they ship to production
    0 of 5 lessons marked complete

    Progress is kept in this browser only.