For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.
This project supported WRAPP in scaling its mystery shopping operations by investigating whether AI-powered agents can help validate free-text visit reports more consistently and efficiently.

The students developed several validation approaches using large language models to check report completeness and compliance with predefined criteria, organised in a multi-agent architecture where agents cross-review each other's decisions. Experiments showed that this setup can improve the consistency and quality assurance of automated validation while keeping humans in the loop, pointing towards scalable AI-assisted quality control for real-world mystery shopping programmes.