shopping-assistant

Tag

Cards List
#shopping-assistant

Walmart is inviting AI agents to shop for you

The Verge ↗ · 2d ago Cached

Walmart will let users connect their own AI agents to shop on its site via a new Agent Gateway built on the Model Context Protocol, with purchase approvals, spending limits, and Agent Profiles for reviewing agent activity — a sharp contrast to Amazon blocking rival AI shopping agents.

0 favorites 0 likes
#shopping-assistant

@yoheinakajima: letting agents find and buy stuff for you is here

X AI KOLs Following ↗ · 2026-09-02 Cached

AI agents are now capable of autonomously finding and purchasing items for users, as demonstrated by a user whose agent bought a JJ Watt Texans jersey.

0 favorites 0 likes
#shopping-assistant

PSA: Amazon’s shopping AI can now tell you if that message is a scam

TechCrunch AI ↗ · 2026-09-02 Cached

Amazon has introduced an AI feature in Alexa for Shopping that allows customers to verify if messages are scams by analyzing sender information and content against Amazon's systems.

0 favorites 0 likes
#shopping-assistant

Amazon Alexa can now alert you when something new might tempt you to shop

TechCrunch AI ↗ · 2026-09-01 Cached

Amazon has launched a new AI feature for Alexa called 'Update Me When' that sends personalized notifications to alert users about potential shopping temptations, enhancing the shopping experience through anticipation of user needs.

0 favorites 0 likes
#shopping-assistant

PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants

arXiv cs.CL ↗ · 2026-08-28 Cached

The paper introduces PACEShop, a benchmark dataset, and PACEJudge, a judging protocol for evaluating personalized, actionable, compositional, and evidence-grounded shopping assistants, addressing gaps in current evaluation methods.

0 favorites 0 likes
#shopping-assistant

Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants

arXiv cs.CL ↗ · 2026-06-12 Cached

The Shopping Reasoning Bench is an expert-authored benchmark for evaluating multi-turn conversational shopping assistants, with 525 missions and over 10,000 binary rubrics. Evaluations of GPT, Claude, and Gemini show that current models achieve only 57-77% pass rates, revealing significant gaps in expert-level shopping reasoning.

0 favorites 0 likes
← Back to home

Submit Feedback