Few-shot prompting — CCA-F Exam Prep

×
L2.020
REAL STORYTwo dashboards showing invoice extraction accuracy. Left: 'Zero-shot: 61% accuracy' with red error highlights. Right: 'Few-shot (3 examples): 94% accuracy' with green checkmarks. Same stack of messy invoices feeding into both. Clean data viz style.

Same model. Same invoices. Same task. One prompt got 61% accuracy. The other got 94%.

A fintech startup was extracting data from thousands of invoices per day. Different formats, different layouts, different languages. They needed vendor name, date, line items, and total.