In this discussion with Arya Asemanfar, a Product and Engineering leader at Sierra, listeners discover how AI-powered agents are revolutionizing customer interactions. Arya explains the critical differences between traditional chatbots and advanced agents that take meaningful actions. The conversation dives into Sierra's innovative 'Agent OS' that ensures robust, scalable development and addresses challenges like tool hallucination. Arya highlights the importance of collaboration with customers, showing how tailored solutions enhance customer service while reflecting brand values.
43:15
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
question_answer ANECDOTE
DoorDash Lunch
Aria Asemanfar ordered lunch through DoorDash using many taps and swipes.
He envisions AI agents simplifying this process to a quick conversation.
insights INSIGHT
Agents vs. Chatbots
Agents differ from chatbots through their ability to take action.
Chatbots function like search engines by providing answers, while agents perform tasks.
volunteer_activism ADVICE
Building Scalable Agents
Building scalable AI agents requires robust architecture.
Simply giving LLMs API access is insufficient for reliability at scale.
Get the Snipd Podcast app to discover more snips from this episode
In this episode, we sit down with Arya Asemanfar, Product and Engineering leader at Sierra, to explore the future of AI-powered enterprise agents. Arya breaks down how Sierra is transforming customer experiences by building agents that go beyond traditional chatbots—taking meaningful actions, embodying brand voice, and scaling reliably for unique business needs.
Learn how Sierra approaches agent development with their innovative “Agent OS,” solves challenges like tool hallucination, and co-designs solutions with customers. Arya also shares actionable insights for product and engineering leaders, from building better evaluation systems to designing intuitive feedback loops.
Topics covered in this episode:
What Are Enterprise Agents?
The difference between traditional chatbots and AI-powered agents that take meaningful actions.
Examples of how Sierra’s agents transform customer service interactions (e.g., returns, exchanges).
Building Scalable AI Agents
The importance of robust architecture for reliability and performance.
How Sierra’s “Agent OS” supports the full lifecycle of agent development—from design to monitoring.
Addressing tool hallucination and ensuring agents only take actionable, reliable steps.
Using evaluation frameworks to test and refine agent behavior at scale.
Collaborating with Customers
Why each agent is treated as a unique product tailored to a customer’s brand, policies, and processes.
The co-design process and how it ensures agents align with business needs.
Actionable Advice for Teams Building AI Agents
Start with concrete customer examples to develop intuition and build better agents.
Implement evaluation systems early to accelerate learning and iteration.
Invest in tools and processes to streamline human feedback and testing.
The Future of AI and Product Design
Emerging paradigms that will transform how users interact with software.
Predictions for how AI will shape new user experiences beyond automation.
Deployed: The AI Product Podcast