Cresta Introduces Synthetic Customers
Synthetic Customers power simulated conversations for AI agent testing and human agent training, while unlocking deeper insights into customer behaviour.
Topics
Cresta, the unified customer experience AI platform for human and AI agents, has announced the launch of Synthetic Customers, a capability creating realistic, representative, evolving customer personas directly from an enterprise’s own conversation data.
Synthetic Customers power simulated conversations for AI agent testing and human agent training, while unlocking deeper insights into customer behaviour across the business.
Most companies build customer personas from surveys, CRM records, support tickets, and periodic research: sources that are siloed, incomplete, and quickly out of date. The result is testing and training that reflects how teams think customers behave, not how they actually behave.
ALSO READ: Memorable Experience is the New Growth Engine
Synthetic Customers unlock historical conversation data to provide evidence-based, dynamic customer personas that evolve as your customers do.
“The data that enterprises need to build accurate customer personas for better testing, training, and decision-making is right in front of them, at their finger tips. It lives in every call, chat, or email conversation,” said Ping Wu, CEO of Cresta.
“With Synthetic Customers, enterprises can finally put all that data to work to truly understand their customers, prepare for how they actually behave, and serve them better across every channel.”
Synthetic Customers automatically mine historical conversation data to extract behaviour and derive customer profiles grounded in real language, actions, and emotional patterns. This includes the frustration, impatience, topic-shifting, and unpredictability that ungrounded personas consistently miss.
Synthetic Customers evolve over time as these patterns shift with the market. Cresta measures simulation realism using a blind evaluation methodology, testing whether humans and AI can distinguish synthetic conversations from real ones.
Synthetic Customers unlock new ways to understand, test, and prepare for customer interactions across the business:
- AI agent simulated testing: Validate AI agents against Synthetic Customers that reflect how real customers actually behave, before a single live interaction happens, and continue to optimise throughout the AI agent lifecycle.
This capability dramatically expands testing coverage, surfacing more edge cases to ensure AI agents are even more reliable. Synthetic Customers integrate directly into Cresta’s AI Agent automated testing suite, giving teams a faster, more realistic path to launch confidence.
ALSO READ: Artificial Intelligence Alone Cannot Fix Broken CX
- Human agent training: With Synthetic Customers, agents can prepare for what actually happens on the job. Synthetic Customers enable dynamic role play training to onboard agents faster, develop specific skills in precise situational contexts, and facilitate practice exercises that mirror real customer interactions to improve sales, service, and retention.
- Simulated customer interviews: Anticipate how your customer base might respond to a business update, like a product change, new policy, or messaging shift, before it goes live.
- Customer insights: Understand how different customer personas and segments behave and what they’re likely to need next, based on real historical patterns. Surface actionable AI recommendations to improve the customer experience before issues repeat.
Wu added, “What we’re announcing today is just the start; accurate AI representations of customers can be used for everything from incident planning to market research. The use cases for Synthetic Customers are endless.”
