Project Overview
An AI-powered web app that combines a curated FAQ system with a real-time chatbot, designed to handle complex topics respectfully and in line with the client's values.
Our team partnered with a client promoting interfaith, interracial, and intercultural education to support trainers facing burnout from answering repetitive, sensitive questions. The platform supports session-based customization, letting trainers tailor content and control access. A human-in-the-loop feedback system allows flagged responses to be reviewed and reused for few-shot training, enabling continuous improvement of the chatbot over time.
Key Contributions
- Designed and implemented a custom chatbot system using Google Vertex AI and Flask, integrating behavior filters aligned with nuanced client requirements.
- Deployed the application as a containerized service on Google Cloud Platform, ensuring modularity and scalability.
- Proposed and built a human-in-the-loop feedback mechanism, allowing flagged responses to be reviewed by the client and reused as few-shot training examples, enabling iterative chatbot refinement.
Skills and Tools Used
GIT
Python
Flask
VertexAI
Google CLoud Platform