AIT case studies
AIT · Put your knowledge to work in context.
AIT is a professional credential focused on applied artificial intelligence: the vocabulary and concepts behind modern AI systems, the data and machine-learning practices that make them work, and the neural-network, language-model, ethics, and deployment knowledge needed to use them responsibly on the job. It suits analysts, engineers, product and project staff, and technically literate managers who need to reason about AI systems rather than merely operate a tool. The AIT case studies are 5 cases and about 2,571 words.
1The Support Triage Classifier That Fails on Weekends
A SaaS company deploys a ticket-routing classifier trained on 18 months of historical support tickets. Overall validation accuracy is 94%, so the team ships it.
487 words, about 2 min2The Summarizer That Hallucinates Citations
A legal-tech startup builds a retrieval-augmented generation (RAG) assistant that summarizes case law for paralegals. The pipeline retrieves the top 5 passages from an internal corpus, then prompts a large language model to 'summarize the relevant holdings and cite the source documents.' In a 200-query evaluation, 12% of summaries contained at least one citation to a case that was not in the retrieved passages, and 5% cited a real case for a proposition it does not support.
507 words, about 3 min3The Fraud Model With a Fairness Complaint
A bank deploys a gradient-boosted fraud-detection model that flags transactions for manual review. The model uses features including transaction amount, merchant category, device age, IP geolocation, and 'account tenure.' An internal audit finds that the flag rate for customers in low-income ZIP codes is 2.3× the rate for high-income ZIP codes, even after controlling for actual fraud rate.
522 words, about 3 min4Fine-Tuning a Chatbot on Thin Data
A mid-size retailer wants a customer-service chatbot that answers questions about returns, shipping, and product specs. They have 4,000 historical chat transcripts, of which about 600 contain a clear question–answer pair.
537 words, about 3 min5The Model Card That Says 'High Accuracy'
A hospital's innovation lab builds a model that predicts 30-day readmission risk to help discharge planners prioritize follow-up. The model card states 'AUC 0.84, high accuracy' and lists training data as 'electronic health records, 2019–2021.' The lab wants to deploy it in three hospitals with different patient populations and EHR systems.
518 words, about 3 min