Salesforce AI Research Introduces eVerse, a Simulation Environment for Enterprise-Ready Voice and Text Agents
Salesforce AI Research today announced eVerse, an enterprise simulation environment for voice and text agent training through synthetic data generation, stress-testing, and reinforcement learning.
“Jagged intelligence” — a phenomenon where AI excels at complex tasks but stumbles on simple ones — creates unacceptable business risk.
eVerse directly addresses this reliability crisis, building the trust required to make the Agentic Enterprise possible — a business where human employees and AI agents can finally work together in a seamless, collaborative ecosystem. eVerse builds trust in AI outputs through a continuous loop of synthesizing data, measuring performance, and optimizing agent behavior.
Stress-testing agents with synthetic conversations
eVerse has been used to power the development of Agentforce Voice, enabling it to handle unpredictable customer interaction scenarios — from spotty phone connections to background noise to diverse accents — with enterprise-grade reliability.The need for resilient, reliable voice agents has never been greater. Despite the explosion of digital channels, most customer interactions still begin with a phone call. When stakes are high, calling a help line remains the go-to channel for most people.
eVerse gives Agentforce Voice the ability to handle even the most unusual voice conversations. The AI agents are trained and stress-tested in eVerse’s virtual environments that mirror the noise, accents, crosstalk, and complexity of real-world operations.
Before launching, Agentforce Voice was put through thousands of conversations simulated through eVerse, allowing teams to identify and fix errors early and deliver the enterprise-grade reliability customers demand.
“With eVerse, we were able to explore many nuances of human conversation before Agentforce Voice reached production,” said Madhav Thattai, COO of Salesforce AI. “This type of rigor is what turns breakthrough research into scalable products and dependable customer experiences. It’s how we’re expanding that same level of responsiveness and consistency across the full observability stack to solve our customers’ most complex needs.”
Optimizing agent performance with UCSF Health
eVerse is currently in pilot testing with customers such as UCSF Health, where the team is partnering with clinical experts to train and refine AI agents that simplify healthcare billing — a domain where reliability and accuracy are critical.
Industry data shows that only 60–70% of healthcare contact center inquiries are routine and can be fully handled by AI agents, as much of the knowledge isn’t formally documented. To increase coverage, eVerse optimizes accurate AI agent behavior and adapts to complex scenarios over time with reinforcement learning from human feedback (RLHF), achieving up to 88% coverage across routine and complex tasks according to preliminary evaluations.
When used responsibly, we believe AI can help our teams simplify one of the most complex parts of healthcare, creating a billing experience that feels seamless and truly patient-centered.
Sara Murray, MD, MAS, VP & Chief Health AI Officer at UCSF Health
“When used responsibly, we believe AI can help our teams simplify one of the most complex parts of healthcare, creating a billing experience that feels seamless and truly patient-centered,” said Sara Murray, MD, MAS, VP & Chief Health AI Officer at UCSF Health.
“Our partnership with UCSF Health demonstrates how applied science translates directly to customer value, proving that when you train agents in environments that mirror real-world complexity, they perform reliably when it matters most,” said Silvio Savarese, Chief AI Scientist, Salesforce.
This continuous loop — synthesizing environments, measuring performance, and optimizing behavior — transforms agents from generic language models into enterprise-specialized systems ready for production deployment.
The path to Enterprise General Intelligence
eVerse is a critical milestone on the path to building the Agentic Enterprise. To make this vision a reality, a new kind of AI is required, which Salesforce AI Research calls Enterprise General Intelligence (EGI): AI optimized for business applications that excels in both capability and consistency.
While consumer AI optimizes for impressive demonstrations and creative outputs, the Agentic Enterprise demands reliability across every interaction. eVerse bridges this gap by bringing real-world complexity into the development cycle, creating the trusted, predictable performance that enterprises require.
AI adoption depends on an organization’s ability to deploy AI agents that are both highly capable and highly accurate in their domain of expertise. With eVerse, Salesforce AI Research is building that future through rigorous scientific methodology that transforms how enterprise AI gets developed, validated, and deployed.
Learn more
Follow Salesforce AI Research on the web and on X to explore the latest publications, open-source releases, and scientific contributions advancing the field of enterprise AI.
Additional resources
- Learn more about enterprise simulation environments The New AI Agent Training Ground: Simulating Enterprise Environments
- Explore Enterprise Deep Research on GitHub
- Learn more about Agentforce Voice
About Salesforce AI Research
Salesforce AI Research advances the science of artificial intelligence to power enterprise applications. The team develops breakthrough models, benchmarks, and methodologies that make AI more intelligent, trustworthy, and capable in real-world business environments.
