Azure AI-102 case studies
Azure AI-102 · Put your knowledge to work in context.
AI-102 is the exam behind the Microsoft Certified: Azure AI Engineer Associate credential, an intermediate-level, Azure-role certification with an artificial intelligence subject focus. It targets engineers who build, manage, and deploy AI solutions on Azure - people who work across requirements definition and design, development, deployment, integration, maintenance, performance tuning, and monitoring, and who collaborate with solution architects, data scientists, data engineers, IoT specialists, and infrastructure administrators to deliver complete, secure end-to-end AI solutions. The Azure AI-102 case studies are 5 cases and about 5,321 words.
1Northwind internal assistant: private networking, keyless auth, and chargeback
Northwind's internal assistant serves 1,200 staff and answers about 18,000 questions per day from a 600,000-chunk index. The solution pairs an Azure AI Foundry resource hosting a GPT-4o deployment with Azure AI Search, and source documents live in Blob Storage.
1,014 words, about 5 min2Fabrikam HR assistant: 58% citation accuracy on a RAG pipeline
Fabrikam shipped a retrieval-augmented assistant over 12,000 HR policy documents (about 1.4M tokens). Files are chunked at a fixed 512 tokens with no overlap and indexed into a single vector field using the default text-embedding-3-small deployment; queries retrieve the top 3 chunks by cosine similarity only.
1,017 words, about 5 min3Trident IT helpdesk agent: unverified password resets and runaway loops
Trident's IT helpdesk agent runs in Azure AI Foundry Agent Service with four tools: lookup user, reset password, create ticket, and send email. Its instructions state that the agent must verify the caller's identity before resetting a password.
1,042 words, about 5 min4Hairline crack detection: classification model on a 180-image defect set
An automotive supplier inspects 4,000 parts per shift with a fixed 1280x720 camera. QA labeled 180 images across six defect classes; the rarest class has 9 examples, and hairline cracks occupy roughly 20x8 pixels.
1,074 words, about 5 min5Insurer's claim digitization: enrichment cost, indexer timeouts, and confidence-based review
An insurer is digitizing 240,000 claim PDFs spanning 1998–2024. About 30% are image-only scans, 6% contain handwritten adjuster notes, and the rest have embedded text.
1,174 words, about 6 min