[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cheat-sheet---en":3,"domain-info---en":3,"topic-info----en":3,"lesson-aws-certified-ai-practitioner-genai-fundamentals-genai-core-concepts-context-engineering-en":4,"prev-aws-certified-ai-practitioner-genai-fundamentals-genai-core-concepts-context-engineering-en":18,"next-aws-certified-ai-practitioner-genai-fundamentals-genai-core-concepts-context-engineering-en":27},null,{"locked":5,"reason":6,"meta":7,"item":3},true,"paywall",{"title":8,"description":9,"isFree":10,"estimatedMinutes":11,"difficulty":12,"learningObjectives":13},"Context Engineering","Treat the context window as a budget you allocate rather than a box you fill: what competes for the space, why more context can make answers worse, and the strategies that decide what earns a place in the prompt.",false,20,"intermediate",[14,15,16,17],"Define the context window and identify everything that consumes it","Explain the difference between the hard context limit and quality degradation within it","Distinguish context engineering from prompt engineering","Compare the strategies for keeping a context window within budget",{"locked":5,"reason":6,"meta":19,"item":3},{"title":20,"description":21,"isFree":10,"estimatedMinutes":11,"difficulty":12,"learningObjectives":22},"Token-Based Pricing","Learn how generative AI bills, why output tokens cost more than input tokens, and how on-demand, batch, Provisioned Throughput, and prompt caching change the cost of the same workload.",[23,24,25,26],"Explain how token-based pricing works and why input and output tokens are priced differently","Estimate the monthly cost of a workload from its token volumes","Compare on-demand, batch, and Provisioned Throughput and identify which fits a given scenario","Describe how prompt caching reduces cost and what its limitations are",{"locked":5,"reason":6,"meta":28,"item":3},{"title":29,"description":30,"isFree":10,"estimatedMinutes":31,"difficulty":12,"learningObjectives":32},"Agentic AI and the Model Context Protocol","See what turns a foundation model into an agent: the cyclical reasoning loop, tool use, memory, and multi-agent patterns, plus how the Model Context Protocol standardizes the connection between agents and the systems they act on.",22,[33,34,35,36],"Define an AI agent and explain what separates it from a single foundation model call","Trace an agent's reasoning loop through tool selection, action, and observation","Describe memory management and common multi-agent patterns","Explain what the Model Context Protocol standardizes and how AWS supports it"]