PhD Student in Computer Science @ NUS
Research Focus: Data Systems for AI Agents · Agent Infrastructure
Creator of Alive, EasyNet, GEM-Bench, and Easy-Notebook
I believe AI should be accessible to everyone—not just experts.
My goal is to make AI easier to discover, easier to use, easier to manage, easier to organize, easier to protect, easier to govern, and easier to monetize.
I am interested in building system-level foundations for AI agents, especially at the intersection of:
- Database systems for AI agents
- Hierarchical & dynamic knowledge structures
- Agent behavior versioning, reuse, and evolution
- Agent execution infrastructure & distributed systems
My current research direction focuses on designing AI-native data systems that support:
- Open-World Capability Routing under Capability Drift and Partial Observability
- evolving agent knowledge,
- traceable reasoning paths,
- and reusable agent behaviors as first-class system assets.
A distributed execution infrastructure for AI agents and functions.Designed to support language-agnostic agent behaviors, privacy-first compute sharing, and agent-level orchestration.
Python · Go · gRPC · Distributed Systems
A benchmark and evaluation toolkit for ad-injected LLM responses. Designed to study the satisfaction–engagement trade-off across chatbots and AI Overviews, with curated datasets, human-validated judges, and reproducible CLI/agent workflows.
Evaluation · Benchmarking · Agent Alignment
- Languages: Python, Go, Rust, TypeScript
- Systems: Databases, Distributed Systems, Agent Infrastructure
- AI: LLM Agents, Planning, Reinforcement Learning
- Tools: React, Tauri, gRPC, Docker
- GitHub: https://github.com/Qingbolan
- Website: https://silan.tech
- Email: silan.hu@comp.nus.edu.sg
I believe AI agents will become long-running system entities, and we need new database and infrastructure abstractions to support them.