Skip to main content

Primary supervisor

Zhixi Cai

Co-supervisors


This project aims to design and implement an Agentic AI for Human Assistance (the “assistant agent”) to support everyday information work, e.g. email coordination. Unlike conventional chatbots, the proposed system follows an agentic workflow: it can plan, use tools, and execute multi-step tasks, while incorporating Human-in-the-Loop (HITL) mechanism at critical decision points to ensure trustful, safety, controllability, and explainability.

Aim/outline

1. Initial discovery and literature review.

2. Design the Agentic AI system for human intelligent assistant.

3. Deploy demo for internal evaluation and analysis.

4. Thesis and paper writing for the system prototype.

Required knowledge

- Python programming

- LLM application development: prompt design, structured outputs (JSON), function/tool calling, agentic AI

- Basic AI and NLP concepts

- Linux DevOps basics

- Software engineering basics