Skip to main content

Sierra Agent OS 2.0: from answers to memory and action

Two years ago, Sierra did not exist, and most people had never heard of agents. Today, agents have gone from providing simple answers to originating mortgages, authenticating patients, and saving subscribers. And the big question on everyone’s minds: what’s next?

That’s the question Sierra Summit, our first-ever customer conference, set out to answer — with eight new products designed to help businesses take advantage of the opportunities in front of them, while navigating the challenges ahead.

Blueprint

Multi-channel → Single agent

First, the customer experience is moving from a multi-channel to a single agent world. Today, most companies still have separate teams — and separate customer experiences — for their call center, website, and mobile app. Yet AI can handle all of them. Your agent can chat with customers over WhatsApp or via text message, in your app or on your website — and most importantly, it can now pick up the phone. The conversation is becoming the interface.

Agents aren’t just transforming existing channels; they’re creating entirely new ones. AI assistants are the front door to the Internet, just like search has been for the past 25 years. ChatGPT is the fastest growing product in history, with over 800M weekly users. People are using it for everything — from trip planning to understanding their lab results to refining presentations. Soon, everyone will have a personal agent, and we’ll all use AI to improve our performance at work.

In this new world, your company’s AI agent is about so much more than just chat and voice. It’s a single agent for every channel — the starting point for every customer interaction; from product discovery and recommendations to sales, sign-up, troubleshooting, loyalty, and retention. It will also assist your service and sales associates and be available through products like ChatGPT and Gemini.

Sierra’s Agent OS makes it easy for businesses to thrive in this new single agent world. You can build your agent once and deploy it everywhere — chat, voice, email, SMS, and now in two new places: ChatGPT and your contact center.

Publish to ChatGPT

With one click, you can publish your agent to ChatGPT — extending your brand reach with minimal extra effort. Sierra’s universal web attachments support interactive maps, fillable forms, detailed charts, and more — all working seamlessly across channels. Because you maintain full control over exactly which journeys, data, and capabilities appear in ChatGPT, you don’t need to choose between distribution and disintermediation. You can build a stronger, deeper (see below) direct relationship with your customers via your first-party agent, while taking advantage of ChatGPT’s distribution and engagement with this new feature. Read more here.

Live Assist

Not every conversation should be handled by AI — sometimes you need the human touch. Live Assist brings your AI agent’s superpowers (like the ability to read millions of words a minute, use multiple tools at once, and represent your brand consistently) into every customer interaction. It guides support teams in real time, captures details automatically, surfaces answers instantly, and recommends the best next step. Live Assist helps improve your in-person conversations, relieves pressure on your team, and enhances performance across the board. Read more here.

Technology → Product

Second, we’re moving to a world where anyone, not just engineers, can become expert AI architects — building industrial-grade agents with true agency at scale, not standard operating procedures dressed up as agents.

In the early stages of any technology, you need an expert engineer to build it. Go back to 1997, and companies spent tens of millions of dollars just to get their websites live. As the technology matured, it became accessible to everyone without the need for huge implementation costs or sophisticated engineering teams. Today is the 1997-era of agent building.

You can build in code — which gives you full control, deep orchestration, and rich systems integrations — but it requires time and engineering resources. Or you can use today’s simplistic “no-code” tools that get your agent to first base quickly (basic question answering) but can't handle the complexity of enterprise use cases like subscription churn management, regulated workflows, or multi-step sales processes. And that’s where all the business value lies. Agents should be technology everyone can use — not just engineers.

Agent Studio 2.0, which we are launching today, productizes the agent building process: just like Shopify did for e-commerce. It gives every team the power to build sophisticated, production-ready agents, while Insights 2.0 uses AI to continuously improve them.

Agent Studio 2.0

With Journeys, every team gets the same control developers currently have with Sierra’s Agent SDK. Its easy-to-use natural language interface enables anyone to define the goals and guardrails of your customer experience with sufficient nuance to build a highly effective agent. Workspaces brings safe, GitHub-style collaboration across CX, ops, and engineering. And Integrations let you connect systems in minutes — so you can build and deploy with confidence. Read here for more.

Insights 2.0

Insights is your hub for optimizing agent performance. The new Explorer feature (think deep research for customer conversations) can instantly analyze huge numbers of interactions to diagnose issues and identify improvements. And Expert Answers turns your contact center’s expertise into new, grounded articles that automatically enhance your AI agent’s performance. Read here for more.

Conversations → Relationships

Third, we’re moving from a world of conversations to relationships, from basic customer support to enhancing the entire customer experience.

Lasting customer relationships aren’t transactional. But today, that’s how even the best customer agents operate. They complete one task — have a conversation, inspect a purchase, file a ticket — and they’re done. This is because they lack memory and access to the systems that would enable them to build deeper, more lasting customer relationships.

Agent Data Platform

It’s why we are excited to announce a first-of-its-kind platform that gives agents the memory and context they need to go from one-and-done transactions to lasting relationships. It’s called Agent Data Platform (ADP).

ADP is the memory and intelligence layer of Sierra Agent OS. It gives your agents the context and continuity to move from conversations to relationships. And it unifies every conversation (the unstructured data in your calls, chats, and emails) with your structured data — everything from your customer data, billing systems, inventory, policies, transactions, and more.

With that unified view, your agent gains true agency: the ability to connect dots across time, anticipate needs, recommend next best actions, and make informed decisions that strengthen your customer experience and grow your business. From greeting customers by name, to remembering prior conversations and preferences, surfacing relevant insights, and taking initiative on their behalf — whether suggesting a better plan, flagging a renewal, or resolving an issue before it even happens. Read here for more.

From answers to memory and action

Customer expectations are evolving quickly — and brands must adapt just as fast to take advantage of these new opportunities. Sierra’s Agent OS enables the great companies of the world to show up at their best, day in, day out.

It productizes the agent-building process so anyone can create a single, sophisticated production-grade agent, and deploy it wherever their customers are. It gives agents the memory and context they need to move from transactions to relationships, and from reactive to proactive. And it uses AI to continually improve your AI.

We can’t wait to build this future with you all.

Share

Subscribe to the Sierra blog

Get notified about new product features, customer updates, and more.

See what Sierra can do for you

Find out how Sierra can help your business build better, more human customer experiences with AI.