[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cheat-sheet---en":3,"domain-info---en":3,"topic-info----en":3,"lesson-aws-certified-ai-practitioner-foundation-model-applications-prompt-engineering-prompt-engineering-best-practices-en":4,"prev-aws-certified-ai-practitioner-foundation-model-applications-prompt-engineering-prompt-engineering-best-practices-en":18,"next-aws-certified-ai-practitioner-foundation-model-applications-prompt-engineering-prompt-engineering-best-practices-en":28},null,{"locked":5,"reason":6,"meta":7,"item":3},true,"paywall",{"title":8,"description":9,"isFree":10,"estimatedMinutes":11,"difficulty":12,"learningObjectives":13},"Prompt Engineering Best Practices","The concrete habits that turn a vague prompt into a reliable one: be specific, place the instruction well, use separators, give a fallback answer, and say what you do not want.",false,16,"intermediate",[14,15,16,17],"Apply the clarity rules: simple, specific instructions with an explicit output format","Explain why the instruction belongs at the end and why separators help","Use a default fallback answer to reduce confident wrong answers","Distinguish a negative prompt from a role from an output indicator",{"locked":5,"reason":6,"meta":19,"item":3},{"title":20,"description":21,"isFree":10,"estimatedMinutes":22,"difficulty":12,"learningObjectives":23},"Prompting Techniques","From zero-shot to chain-of-thought: the named prompting techniques, how much scaffolding each one adds, and which task each is built for.",17,[24,25,26,27],"Compare zero-shot, one-shot, and few-shot prompting by the amount of example guidance each provides","Explain what chain-of-thought prompting does and when it helps","Distinguish chain-of-thought from prompt chaining","Match a task to the lightest technique that reliably solves it",{"locked":5,"reason":6,"meta":29,"item":3},{"title":30,"description":31,"isFree":10,"estimatedMinutes":32,"difficulty":12,"learningObjectives":33},"Prompt Attacks and Risks","How attackers turn your own prompt against you: prompt injection, jailbreaking, and prompt leaking, plus the layered defenses including Amazon Bedrock Guardrails.",18,[34,35,36,37],"Explain prompt injection and why it resembles SQL injection","Distinguish prompt injection, jailbreaking, and prompt leaking","Describe layered defenses: input isolation, instruction hardening, and Amazon Bedrock Guardrails","Identify who owns prompt-security risk under the AWS shared responsibility model"]