Essam Mansour

Tenured Associate Professor, Concordia University · Head, CoDS Lab

I build AI agents that operate safely on organizational data. Architecture, not only LLM capability, decides whether an enterprise agent works.

  • General Chair, IEEE ICDE 2026
  • Demonstration Chair, VLDB 2027
  • Editor, ACM SIGMOD Blog
Portrait of Essam Mansour

What we work on

Agents have no governed way to accumulate what an organization knows, and no way to establish that what they accumulated is trustworthy. We work on this at the data layer, and release our systems open source through CoDS-GCS.

The research program

Recent systems

KGLiDS was adopted by Google and Kaggle teams, and RAGvis is released in Google’s own GitHub organization.

All systems and benchmarks

News

News archive