Today, Sierra’s launching Voice Personas, which enable you to give your agent not just a voice, but a personality. Voice AIs shouldn't sound the same. It's time to empower every company to define their own brand voice. And we had a ton of fun messing around, as you’ll see in the video.
For more than 165 years, Santander has helped people and businesses prosper.
Ana Botín has long advocated for AI — not as a technology project, but as a way to increase productivity, drive growth, and deliver better customer experiences.
@claybavor and I are incredibly proud the partnership between Santander and Sierra, and we’re excited about what we're building together.
Lots of great 👻Ghostwriter stories this week as folks get their hands on our new agent-building agent. The best practices of your top support associates are buried in transcripts. Ghostwriter can read them, find the best, and build or refine the agent from there.
Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus.
Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf.
I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.
Last week, Sierra released 𝜏³-Bench, an update to our industry standard agent benchmark, expanding the benchmark in several important ways:
𝜏-Knowledge tests whether agents can operate over large collections of internal company documents spread across systems and formats;
𝜏-Voice evaluates agents built for live voice conversations; and
We’ve also incorporated fixes contributed by the 𝜏-Bench community across existing 𝜏-Bench domains to improve evaluation accuracy.
Read more here: https://t.co/wBZ4ImNoII
Testing an early preview of @googlecloud's Gemini 3 Flash, with good results: recall as much as 14% higher, precision as much as 20% higher across classification tasks. Agents built on Sierra will be able to support even more complex, high-value workflows for customers. Excited to get this live soon.
Great conversation in London today with Kiran Uppal, Head of Customer Care Experience & Transformation at ASOS - the global online fashion destination for 20-somethings. Their agent went live in 4 weeks, with some customers even calling it their new “bestie.”
In case you missed it: here’s everything we launched at Sierra Summit. 🚀🏔️
1⃣Publish to ChatGPT
2⃣Live Assist
3⃣New Journeys
4⃣Workspaces
5⃣Integrations Library
6⃣Explorer
7⃣Expert Answers
8⃣Agent Data Platform
https://t.co/rIk8xrj4iD
Building enterprise grade agents is part science, part art. They need enough direction to get the job done, and not too much that they feel robotic. Read more here: https://t.co/Ks9ezjEbvU.
Voice Sims is a new feature to test voice agents in real world conditions before they ever talk to a customer. You can create multiple “users,” who speak different languages, have different needs, call from different locations, in different emotional states, and in different situations. Once created, you can run them multiple times before, during, or after launch.
With Sierra's Agent OS companies can launch their own agents within weeks -- from healthcare to apparel, home furnishings and more. Speed matters because faster to launch is faster to impact.