How voice agents engage customers in multimodal interactions
summary
Blended results merges first-, second-, and third‑party skills on multimodal devices to present multiple answers instead of a single reply, e.g., “order pizza” surfaces three selectable options (Amazon Fresh, Domino’s, local pizzeria) and follow‑up actions like fitness cards after “how can I lose 100 calories.” It uses deep‑learning rankers, self-learning from real customer interactions with no manual annotation, and developer support via viewport flags plus an analytics dashboard, increasing discovery and measurable engagement on multimodal devices through blended results.
AI-written summary · about
chapters (12)
- 0:00Introduction to voice agents
- 1:28History of human-computer interaction
- 3:43Evolution of Alexa devices
- 5:08Fundamental AI tasks in Alexa
- 8:50Customer experience attributes
- 12:47Multimodal interaction introduction
- 14:35What are blended results
- 17:06AI powering blended results
- 21:01Developer participation in blended results
- 24:13Value of blended results for developers
- 26:27Demo of multimodal interactions
- 28:15Conclusion and Q&A
related talks
17mReimagining Customer Experiences Integrating Voice into Digital Strategy
11mEnabling richer experiences through multimodal interactions
19mFrom Demo to Deployment: Multimodal Conversational Agents
19m‘The Voice’: New Challenges in a Zero UI world
33mYour e-commerce bot
27mReinventing Customer Experience with Voice and Generative AI
11mMedia Interview
17mBuilding Effective Voice Agents