Speakers Agenda Why attend Partners Venue

Co-located ▼

Locations ▼

Get invited

Partnership opportunities

Secure your seat

Call to action

Your text goes here. Insert your content, thoughts, or information in this space.

Button

Back to speakers

Shubhangi

Goyal

Senior Data & AI Analyst

Admiral Group

Shubhangi is a multi-award-winning senior Data & AI professional and Microsoft MVP with a career spanning Fortune 500, FTSE 100, and agile startups. With a decade of experience across data analytics, data science, data strategy, and AI, she specializes in leveraging algorithms to extract insights, surface patterns, and decode human language in complex datasets. She currently serves as a senior analyst at a leading FTSE 100 financial services and insurance firm in the UK. Previously, she led high-impact AI and data initiatives at ICS AI Ltd, delivering cutting-edge technology to the UK public sector. She holds a degree in Computer Science Engineering and an MSc in Business Analytics from the University of Bath. An international speaker, Shubhangi has delivered talks in 14 countries across the globe. She leads the London Chapter of Women in Data, championing the next generation of women in tech, and co-founded Builders Foundry, a community-driven platform where practitioners learn from real-world experience. She is also a verified expert and mentor on TopMate.

Button

02 December 2025 12:30 - 13:00

Panel | Why do agent systems break in production? The gap between design and reality

Agent systems that perform well in controlled environments can behave very differently once they meet real users, changing data and unpredictable workflows. Tool calls fail, context degrades, edge cases multiply and seemingly minor errors compound across multi-step tasks. This panel will examine the gap between designing an agent and operating one reliably in production. We'll unpack where agent systems most commonly break, why failures are difficult to reproduce and how engineering teams can build for recovery, observability and control from the outset. Key takeaways: → Identify the failure modes that emerge only under production conditions. → Understand how context, tools and multi-step workflows create compounding errors. → Design agents that can recover safely when actions fail or outputs become unreliable. → Build observability and evaluation into the system before scaling deployment.