SXSW Panel Discussion on AI Shopping Agents: Reliability is Key

robot
Abstract generation in progress

AIMPACT News, May 14 (UTC+8), during a podcast recorded live at SXSW, cognitive scientist Danielle Perszyk, Amazon’s Vice President of Core Shopping Amanda Doerr, and Michael Giannangeli, Head of AI for Amazon Nova, discussed the challenges of AI agents from research to real-world deployment. The discussion noted that the real world is full of uncertainty, and shopping agents need to handle real-time information such as ambiguous user intent and inventory changes. Amazon shopping agents must manage millions of products and complex preferences while maintaining a low error rate. Building reliable agents requires multi-layered verification and feedback loops; agents should have common-sense reasoning and error-recovery capabilities, and be able to explain their decision-making process to build user trust. Future directions include multimodal models and real-time data processing, but the core challenge is balancing capability and reliability. (Source: InFoQ)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned