Pandora: How Much Freedom Should a Shopping Agent Have? (AI Summit LDN)

Pandora: How Much Freedom Should a Shopping Agent Have? (AI Summit LDN)

Author: Brave Software June 24, 2026 Duration: 22:02

Riccardo Arnaldi, Agentic AI Product Manager at Pandora, shares what it actually looks like to build and scale a brand-facing LLM shopping agent live with millions of customers. He explains why too much autonomy is a liability, how a deterministic routing layer keeps the AI from going off-script, and why traditional QA teams had to rebuild their processes from scratch. He also breaks down a real customer interaction that exposed the gap between automation and appropriate human sensitivity, changing how the team handles frustrated users.

Key Takeaways

  • Which metrics Pandora uses to measure success of Gemma, their customer-facing AI agent

  • What breaks when traditional QA processes meet agentic products, and how testing an agent differs from testing software

  • How a brand's voice gets engineered into an AI agent, including exact words it's allowed to use and the persona it borrows

  • What a frustrated customer's outburst revealed about the line between automation and human sensitivity

Guest Bio:

Riccardo Arnaldi is a product manager with 6+ years' experience building and iterating on digital products through data, experimentation, and AI. Currently, he owns end-to-end development and strategy of LLM-based shopping and customer support agents at Pandora. Previously, he drove X60M+ DKK in incremental revenue by scaling Pandora's website and CRM personalisation programme from the ground up across 7+ markets. An Italian based in Copenhagen, Riccardo is a sports lover and guitar strummer, and is always on the lookout for the next great travel destination (with hype-worthy local foods).

----------------------------------------------------------------------------------------

About this Show:

The Brave Technologist is here to shed light on the opportunities and challenges of emerging tech. To make it digestible, less scary, and more approachable for all!

Join us as we embark on a mission to demystify artificial intelligence, challenge the status quo, and empower everyday people to embrace the digital revolution. Whether you're a tech enthusiast, a curious mind, or an industry professional, this podcast invites you to join the conversation and explore the future of AI together.

The Brave Technologist Podcast is hosted by Luke Mulks, VP Business Operations at Brave Software—makers of the privacy-respecting Brave browser and Search engine, and now powering AI everywhere with the Brave Search API.

Music by: Ari Dvorin

Produced by: Sam Laliberte

 


Hosted by Brave Software, The Brave Technologist is a series for anyone curious about the real human impact of our digital evolution. It moves past the surface-level buzzwords to ask how technologies like AI, machine learning, and Web3 actually affect everyday decisions, privacy, and the fabric of society. The conversations here are grounded and thoughtful, prioritizing the user's perspective in a landscape often dominated by abstract visions of disruption. You'll hear from builders, thinkers, and technologists who are shaping these tools, discussing not just what is possible, but what is responsible and meaningful. This podcast sits at the intersection of technology, business, and marketing, examining how these forces converge to shape our collective future. It’s for listeners who want to understand the "why" and "for whom" behind the code, offering a nuanced take that is often missing from tech commentary. Tune in for a deeper, more inclusive dialogue about the systems that are redesigning our world.
Author: Language: English Episodes: 50

The Brave Technologist
Podcast Episodes
How a 200-Year-Old Bank Deploys AI Agents [not-audio_url] [/not-audio_url]

Duration: 26:31
Andy McMahon, Principal AI Engineer at Barclays, shares how a 200-year-old bank is deploying autonomous agents inside one of the most heavily regulated environments in the world. He argues that observability and kill swi…
LIVE FROM THE AI SUMMIT LDN: Inside Sony AI's Bet on Open Research [not-audio_url] [/not-audio_url]

Duration: 22:55
Fred Gifford, Strategy Lead and Sr. Product Manager at Sony AI, shares how his team is building knowledge graphs from academic literature to predict new biomedical relationships and accelerate drug discovery. He explains…
AI Is Now Buying Cars and Negotiating Better Than You [not-audio_url] [/not-audio_url]

Duration: 30:07
Zach Shefska, Founder & CEO of CarEdge, shares how he and his father (a 43-year auto industry veteran) turned a broken, opaque car buying process into a transparency-first business powered by AI agents that now negotiate…
Why Your VPN Isn't Actually Keeping You Anonymous [not-audio_url] [/not-audio_url]

Duration: 42:23
Harry Halpin, CEO of Nym Technologies, shares why the surveillance Web is more dangerous than most people realize, and why most privacy tools aren't enough. He explains how traditional VPNs still leave you exposed, why m…
AI Agents Need Names, And Nobody Owns Them Yet [not-audio_url] [/not-audio_url]

Duration: 42:16
Balazs Nemethi, CEO of the Agent Community, explains why AI agents need identities and why the window to decide who controls that infrastructure is closing fast. He breaks down how a community-governed effort is working…
Why One AI Agent Will Never Be Enough [not-audio_url] [/not-audio_url]

Duration: 33:13
João Moura, CEO of crewAI, shares why single AI agents fall short and what changes when you give them a crew. He explains how multi-agent systems are already running inside Fortune 500 companies; why accountability and h…
How U.S. Policy on Bitcoin Is Changing Fast [not-audio_url] [/not-audio_url]

Duration: 40:38
Sam Lyman, Head of Research at the Bitcoin Policy Institute and former Senior Advisor and Chief Speechwriter to Treasury Secretary Scott Bessent, shares what it looks like inside the U.S. Treasury when Bitcoin, stablecoi…
Why Cyberattacks Are Now a Matter of Life and Death [not-audio_url] [/not-audio_url]

Duration: 35:24
Ed Gaudet, CEO and founder of Censinet, shares how cybersecurity threats have evolved from data breaches to full-scale operational disruptions, and why modern resilience strategies must go beyond prevention. He explains…
General Assembly: The Skills That Actually Matter Now [not-audio_url] [/not-audio_url]

Duration: 40:43
Jourdan Hathaway, Chief Business Officer at General Assembly, discusses her experience integrating AI agents into her admissions team, including stories of real-world complexities, edge cases, and unexpected messiness of…