How avatarin built a 24/7 retail agent with GPT-Realtime
Quick Answer
avatarin developed a 24/7 multilingual retail agent using OpenAI's GPT-Realtime, enabling natural voice conversations and achieving 92% positive feedback from 30,000 users in two weeks.
Quick Take
This AI agent enhances customer service by understanding context and proactively guiding shoppers through their purchasing journey.
Key Points
- 30,000 users engaged with the AI agent in a two-week campaign.
- The agent achieved 92% positive survey responses from users.
- It combines voice, text, and visual understanding for seamless interaction.
- Conversations revealed customer insights previously hard to capture.
- avatarin aims for a unified AI experience across all customer interaction channels.
DeepSignal Analysis
What happened
avatarin has developed a 24/7 multilingual retail agent using OpenAI's GPT-Realtime, which allows for natural voice conversations. In a two-week campaign, the agent received positive feedback from 92% of approximately 30,000 users, demonstrating its effectiveness in enhancing customer service.
Key evidence
- avatarin partnered with Yamada Holdings to create a shopping agent that operates around the clock, addressing the need for expert sales support outside of store hours.
- The agent was used by around 30,000 people in a public campaign, with 92% of survey responses indicating positive experiences.
- The technology combines voice, text, and visual understanding, allowing the agent to adapt to customer needs and provide relevant recommendations.
Why it matters
This development highlights the potential of AI to transform customer service in retail by providing continuous support and personalized interactions. The high satisfaction rate suggests that consumers appreciate the ability to engage with an intelligent system that understands their context and preferences, potentially leading to improved sales and customer loyalty.
What to watch
Source Excerpt
avatarin uses OpenAI’s GPT-Realtime to give Yamada Denki shoppers 24/7 multilingual support. In two weeks, 30,000 people used the agent and 92% of survey responses were positive.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from OpenAI Blog
See more →Scientific computing in the age of agentic AI
AI agents are transforming scientific computing by streamlining software development, enabling researchers to focus on discovery. Projects using Codex and Claude Code report accelerated development and improved maintenance, though challenges in validating AI outputs remain. Long-term stewardship of research software is crucial to ensure reliability and reproducibility.