AAIA case studies
AAIA · Put your knowledge to work in context.
The AWS Certified AI Practitioner (AIF-C01) is a foundational-level credential for people who work with AI and machine learning on AWS but are not necessarily building models themselves. It suits sales, product, project, operations, and early-career technical roles that need a working vocabulary for foundation models, generative AI, and the AWS services that support them. The AAIA case studies are 5 cases and about 3,401 words.
1Fraud Model Threshold, Leakage, and Metric Reporting
A retail bank deploys a gradient-boosted fraud detector trained on 2.1 million card transactions spanning 18 months, with a 0.9% fraud prevalence. Offline ROC-AUC is 0.97.
694 words, about 3 min2HR Policy Assistant Retrieval and Grounding Failures
A people-operations team launches an internal policy assistant over 1,200 HR PDFs averaging 14 pages each. Documents are split into 512-token chunks with 50-token overlap, embedded with a general-purpose embedding model, and the top five chunks are passed to a hosted LLM at temperature 0.7 with an 8K context window.
703 words, about 4 min3Claims Extraction: Fine-Tune Versus Hosted LLM Under Residency Constraints
A health insurer must extract 14 fields - member ID, provider NPI, procedure codes, dates, billed amount, and nine others - from 60,000 claim documents per month. About 40% arrive as scanned images.
654 words, about 3 min4Vendor Resume Screener with Adverse Impact
A staffing vendor offers a resume-screening model that predicts whether a candidate will be invited to interview, trained on five years of a client's human decisions and marketed at 92% accuracy. In a validation sample of 12,000 applications, the selection rate is 0.42 for male candidates and 0.29 for female candidates.
663 words, about 3 min5HR Assistant Prompt Injection, Over-Broad Retrieval, and EU Data
A 4,000-employee company deploys an HR assistant that retrieves from a single embedding index covering every internal wiki space, including documents uploaded by external vendors. The assistant can call two tools: an internal email API and a ticketing API.
687 words, about 3 min