EUROPE'S PREMIER GATHERING FOR INDUSTRY LEADERS IN AI GOVERNANCE
Alessandro Castelnovo
Head of Responsible AI – Data Science & Responsible AI Intesa Sanpaolo
Alessandro Castelnovo holds a PhD in Computer Science (cum laude), with a specialization in Responsible AI in the banking sector. He leads the Office of Responsible AI at Intesa Sanpaolo, where he manages a team of data scientists dedicated to ensuring the ethical development and deployment of artificial intelligence. His work centers on building governance frameworks that promote fairness, transparency, and accountability in AI systems, with a strong focus on bias mitigation and inclusive design.
Responsible AI Summit Main Conference Day 2 - Wednesday 24 September
12:30 PM Presentation - Guardrailing Generative AI at Scale: Intesa Sanpaolo’s Technical Approach to Mitigating Risk
As generative AI rapidly integrates into banking workflows—from customer service chatbots to advisory copilots—the risks of hallucination, toxicity, privacy violations, and regulatory non-compliance are rising. Intesa Sanpaolo, one of Europe’s largest banking groups, is tackling this head-on. In this session, Alessandro, Head of Responsible AI, shares how his team is designing and implementing technical guardrails around generative AI models, with a sharp focus on risk mapping, prompt injection protection, and fundamental rights impact assessments.
- Building proactive defences against prompt injection and out-of-context content generation
- Implementing toxicity filters and privacy safeguards in systems leveraging external LLMs
- Operationalizing EU AI Act principles through guardrails and continuous risk monitoring
Alessandro Castelnovo, Head of Responsible AI, Intesa Sanpaolo
Check out the incredible speaker line-up to see who will be joining Alessandro.
Download The Latest AgendaIn Partnership With:
QUESTIONS?
Address: IQPC Ltd, 129 Wilton Road,
London SW1V 1JZ
Telephone: 44 (0) 207 368 9300
Fax: 44 (0) 207 368 9301
Email: enquire@iqpc.co.uk
©2025 IQPC. All rights reserved.
