How Does Sierra Co-Founder Clay Bavor Make Customer-Facing AI Agents Delightful?

TL;DR

Customer-facing AI agents can delight users by letting them describe desired outcomes conversationally instead of navigating catalogs, menus, and company processes. Sierra helps businesses create branded agents that represent their voice, values, policies, and processes, while additional AI-based checks address errors that models may miss during generation. Read on to see how these agents improve shopping and support while managing hallucination risks.

Transcript

one of the more interesting learnings from the past you know year and a half of working on this stuff is that the solution to many problems with AI is more Ai and it's somewhat unintuitive but one of the remarkable properties of large language models is that they're better at detecting errors in their own output than in not making those errors in t... Read More

Key Insights

• Large language models are capable of reasoning through metaphors and analogies. An early Google model summarized the 2008 financial crisis through an Inception comparison, connecting nested dreams with nested debt and demonstrating an ability to combine concepts rather than merely repeat a memorized description.
• Generative image systems can combine concepts that have never appeared together in a specific image. Early DALL-E examples created avocado-shaped chairs pixel by pixel, showing Bavor that AI models could understand qualities associated with separate concepts and synthesize them into something new.
• Sierra is a platform for creating branded, customer-facing AI agents. Companies can use these agents for interactions ranging from customer service to commerce, giving customers a conversational interface that represents the business rather than requiring them to navigate conventional menus and organizational structures.
• Conversational AI changes how customers access products and services. A shopper can describe the desired type of running shoe and refer to an earlier purchase instead of navigating a hierarchy of categories, while an insurance customer can request a policy change without locating the correct application screen.
• AI agents can understand language, generate responses, reason, and make decisions. These combined capabilities distinguish them from static websites, social-network interactions, and conventional mobile applications, creating a new way for businesses to communicate with customers and help them complete practical tasks.
• Customer experience improves when customers do not need detailed knowledge of a company’s catalog or internal processes. Sierra’s approach allows the agent to interpret a person’s intended outcome, connect it with relevant business information, and guide the interaction through ordinary conversation.
• Additional AI can solve some problems created by AI. Bavor says large language models are better at detecting errors in their own output than at preventing those errors during the original generation, making AI-based evaluation and checking important parts of reliable agent systems.
• Customer service is a strong early business application for generative AI because existing solutions combine high costs with low satisfaction and substantial room for return on investment. The central deployment challenge is allowing useful customer interactions while controlling the errors and hallucinations associated with language models.

Questions & Answers

Q: How does Sierra co-founder Clay Bavor make customer-facing AI agents delightful?

Sierra lets companies create branded agents that help customers pursue outcomes through ordinary conversation rather than conventional menus and organizational structures. These agents can understand requests, reason about relevant information, make decisions, and represent the company’s voice, values, policies, and processes.

Q: What is Sierra’s customer-facing AI platform?

Sierra is a platform for building branded AI agents that interact directly with customers across activities ranging from customer service to commerce. Its agents provide a conversational interface for accessing a company’s products, services, policies, and processes.

Q: How do customer-facing AI agents improve customer service?

Customer-facing agents let people explain what they want without first understanding how a company organizes its website, application, or internal procedures. The agent can interpret the request, reason about it, make decisions, and help the customer complete the intended outcome.

Q: Why is customer service a strong early application for generative AI?

Existing customer-service solutions combine high costs, low satisfaction, and substantial room for return on investment. Generative AI can make those interactions more natural, although companies must control the errors and hallucinations that large language models can produce.

Q: Why can more AI help correct problems caused by AI?

Clay Bavor says large language models are better at detecting errors in their output than at avoiding those errors during initial generation. Agent systems can therefore use additional AI-based evaluation and checking to identify potential mistakes.

Q: How can an AI agent simplify online shopping?

A shopper can describe a desired product, such as a lightweight running shoe or something resembling an earlier purchase. The agent can interpret that description and help find suitable products without requiring the shopper to navigate the company’s catalog hierarchy.

Q: What convinced Clay Bavor that large language models were fundamentally different?

An early Google model summarized black holes in three words and explained the 2008 financial crisis through an analogy to the movie Inception. Bavor saw its connection between nested debt and nested dreams as evidence that the model could reason through metaphor and analogy.

Q: How did avocado-shaped chairs influence the founding of Sierra?

Early DALL-E examples generated chairs that looked like avocados even though those specific images had never existed before. The system’s ability to combine the qualities of avocados and chairs pixel by pixel reinforced Bavor’s belief that AI offered fundamentally new building blocks for software.

Summary & Key Takeaways

• Clay Bavor co-founded Sierra with longtime friend Bret Taylor after spending 18 years at Google across Search, ads, Workspace, virtual and augmented reality, Google Lens, and Google Labs. Early language models demonstrated reasoning through metaphor and analogy, convincing Bavor that conversational AI represented a fundamentally new foundation for software and business interaction.

• Sierra enables companies to create branded, customer-facing AI agents for activities ranging from customer service to commerce. Instead of forcing customers to understand product catalogs, application menus, or corporate processes, these agents let people describe what they want conversationally, reason about the request, make decisions, and help produce the desired outcome.

• Deploying generative AI in customer interactions requires sophisticated engineering because large language models can produce errors and hallucinations. One important lesson is that additional AI can address some AI problems because models may detect errors in generated output more reliably than they avoid those errors initially. Sierra packages these capabilities through AgentOS and outcome-based pricing.