Cianplan

Level 5: AI / LLM systems · L5.8 Generative AI on AWS: Bedrock in practice (AIP-C01)

Cost, performance and governance for generative AI on AWS

Cut token cost and latency with model choice, prompt caching, routing, batch and streaming, and set up prompt governance, model cards and audit trails.

13 min · Pro

What you take away

  • Measure tokens per request first; a long shared prefix is usually the biggest line on the bill, and prompt caching is the lever for it.

And 3 more inside the class, in Pro.

How the class is laid out

  1. The problem
  2. Rereading the rulebook for every order
  3. The levers, mapped to L5.4
  4. The customisation ladder
  5. Governance you can show
  6. Worked example
  7. Bedrock model layer
  8. Knowledge Bases
  9. Agents
  10. Guardrails and data protection
  11. Evaluation and monitoring
  12. Data for models
  13. Prompts and flows
  14. Assistants in 2026
  15. Bias and drift
  16. Customizing a model
  17. Cost, performance, governance
  18. Check your understanding
  19. Before you book AIP-C01