Lab for AI-Agents in Business and Economics

Lab Directors:

Prof. Ye Luo

Associate Director, Institute of Digital Economy and Innovation

Associate Professor, Economics and Finance

Prof. Xin Tong

Professor, Economics and Innovation and Information Management

Mission

Core Objectives

To develop platforms for AI agents and multi-agent architecture for business, management and AI-transformation of organizations

To study and understand the economic impact of AI transformation on economic behavior of human, business and organizations

To study and design AI agents for specific business applications with deep domain knowledge

Latest Article

人工智慧時代的思考權：在堅守與讓渡之間 | 經濟一週

📚 Major Projects

Econometric AI

This project is an international collaborative open source initiative aiming to build an AI-agent system that provides solid econometric knowledge, code-generation, and execution capability for education and research in applied econometrics. The system would consist of the following key features:

We develop an “Econometrics AI Agent” which exhibits outstanding performance in planning econometric tasks strategically, generating and executing code, employing error-based reflection for improved robustness, and allowing iterative refinement through multi-round conversations. It establishes a testbed for exploring AI’s impact on social science research and enables cost-effective integration of domain expertise, making advanced econometric methods accessible to users with minimal coding skills.

Paper

Github

Dataset

A chat based agent for explaining and suggesting econometric method and identification strategy.

An RAG based agent with recommendation ability build on theoretical and applied econometrics papers published at top journals along with datasets.

A latex copilot writer agent that helps thesis writers with citations and references, mathematical formulas, table compiling, etc., in applied econometrics.

Agent Git

Agent Git is the first self-contained package that extends the standard Agentic framework, such as LangGraph and Agno by introducing Git-like version control for AI conversations. By enabling operators such as State Commit, State Revert, and Branching, Agent Git provides durable and reproducible checkpoints, allowing users to reverse actions and travel to previous states on a Markov Chain of Agentic flow.

Github

White Paper

LangGraph Agent Rollback System

Explore a live, sandboxed demo of conversation rollback and branching. Create checkpoints, branch timelines, and see how tool calls auto-checkpoint. Use this to understand how AI agents can safely explore alternatives while preserving original state.

Interactive Demo

Original Timeline

Messages

Checkpoints

Branches

Tools Used

🌳 Session Branch Tree

⭐️ Key Features

Full Snapshot

Complete conversation state saved at each checkpoint

Branching

Create multiple timelines from any checkpoint

Tool Rollback

Automatically reverse tool operations

Auto-Checkpoint

Smart saves after tool execution

💻 Code Example

from src.agents.rollback_agent import RollbackAgent
from langchain_openai import ChatOpenAI

# Create agent with rollback capabilities
agent = RollbackAgent(
external_session_id=session_id,
model=ChatOpenAI(model="gpt-4"),
tools=[calculate_sum, fetch_data, save_to_db],
auto_checkpoint=True  # Auto-save after tools!
)

# Have a conversation
response = agent.run("Calculate 42 + 58")
# Auto-checkpoint created after tool use!

# Create manual checkpoint
checkpoint = agent.create_checkpoint_tool("Important State")

# Continue conversation
response = agent.run("Now multiply by 2")

# Rollback when needed - creates new branch!
new_branch = RollbackAgent.from_checkpoint(checkpoint_id)

# Original timeline preserved, new branch active
response = new_branch.run("Let's try division instead")

Research Labs.

Learn More

Deloitte-HKU Lab for Organizational
Transformation

Organizations succeed by attracting talent, motivating action, and coordinating efforts—areas AI is transforming, demanding structural adaptation. Our lab guides this shift, identifying effective responses and their interplay with markets, norms, and institutions. Through research and industry collaboration, we assess AI adoption, spotlight pitfalls, and craft frameworks for leaders.

Learn More

Lab for AI-Agents in Business and Economics

Our mission is to pioneer AI-driven solutions for business challenges by developing multi-agent systems and domain-specific AI architectures, while guiding organizations through ethical, scalable, and transformative AI adoption. We focus on developing platforms for AI agents and multi-agent architecture for business and management, designing AI agents for specific business applications with deep domain knowledge, and studying the economic impact of AI transformation on human behavior, business and organizations.

Learn More

AI Implementation (AI²) Lab

The AI Implementation (AI²) Lab is dedicated to turning AI and business research into real-world AI adoption. We collaborate with organizations to identify frictions, develop deployment strategies, and measure impact of AI implementation. Our work focuses on helping firms adopt and scale AI, designing business models for the AI era, and incubating AI-related innovations through experimentation and prototyping.

Learn More

Lab for the Future of Work
and Well-being

We advance understanding of generative AI’s transformation of China’s labor markets, leisure, and wellbeing through rigorous, data-driven, causally robust research generating actionable insights. Our people-centered approach prioritizes human wellbeing, going beyond productivity and profitability to foster better jobs and lives.