Robert Chilvers

VP Data & AI dLocal

Tuesday 14th April - Conference Day One

3:40 PM Closing Panel Discussion - Security & Abuse Guardrails for Autonomous Actions

Agentic AI doesn't just automate tasks - it makes decisions, executes transactions, and acts on behalf of customers at speed and scale. That's a competitive advantage. It's also a largely unmapped attack surface.

This session examines what happens when autonomous agents go wrong - through adversarial manipulation, unexpected failure modes, or actions that fall outside the boundaries anyone thought to define. The panel moves beyond threat awareness to what effective guardrails look like in production: how they're designed, where they break down, and who owns them when they do.

Mapping the agentic abuse surface: prompt injection, credential misuse, and actions that are technically permitted but commercially damaging
Designing controls that constrain agent behaviour without killing the autonomy that made deployment worthwhile
Establishing accountability when an agent - not a human - initiates a transaction that goes wrong

Check out the incredible speaker line-up to see who will be joining Robert.

Download The Latest Agenda

In 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