Transparency in Agentic AI
Explainable and compliant agent-based AI systems
Overview
This project develops transparency mechanisms for agentic AI systems.
Funding
- Insight Research Ireland
- Genesys (Industry)
Duration
Nov 2025 – Apr 2027
Team
- PI: Dr Ihsan Ullah
- Co-PIs: John McCrae, Andy Donald, Edward Curry
Researchers
Andy Donald; Atul Kumar Ojha; Edward Curry; Emir Muñoz; Fergal Monaghan; Ihsan Ullah; John McCrae; Talha Iqbal
Description
The system introduces:
- ReAct and Chain-of-Thought explanations
- Compliance engine for regulatory alignment
- Traceable and verifiable AI workflows
Ensures compliance with:
- ISO 42001
- EU AI Act
Thematic Areas
- Artificial Intelligence / Machine Learning
- Data Science
- Knowledge Graphs & Linked Data
Impact
- SDG 9: Industry, Innovation & Infrastructure