AIP-C01 sample questions with answers
The other 92 questions are in the practice tool, with answers revealed as you go.
Start 20 questionsFoundation model integration and data
- A fintech fine-tuned a supported Bedrock model on support tickets. Traffic is spiky, so the team wants to pay per use and avoid buying reserved capacity. Which inference path fits, where the model type and Region support it?
- A team fine-tuned a Mistral checkpoint with its own tooling outside AWS and wants to serve it on Bedrock through the standard InvokeModel call. Which Bedrock feature handles this?
- An ML team must run Llama 3.1 70B with its own inference container, a GPU instance type it chooses, and a vLLM serving configuration, because managed Bedrock hosting does not expose those controls. Which AWS service is the best fit?
Implementation and integration
- A tutoring app uses Claude to solve multi-step word problems, and it often gets intermediate arithmetic wrong. Which prompt change most directly targets this failure?
- A ride-sharing startup wants riders to chat with a Bedrock-backed assistant from its iOS and Android apps, with as little custom infrastructure as possible while staying secure. Which approach is most straightforward?
AI safety, security and governance
- A claims-support bot answers from retrieved policy excerpts. The team wants responses that drift away from those excerpts to be caught automatically, using a score they can set a threshold on. Which Guardrails feature provides this?
- A public-facing assistant built on Amazon Bedrock is suddenly receiving thousands of crafted requests from a handful of client IP ranges, apparently trying prompt injection at scale. Which combination gives the fastest automated mitigation and alerting?