AI-generated conversation participants with unique profiles and characteristics
Personas are AI-generated individuals who participate in conversations with your agents during simulations. Each persona has unique attributes, personality traits, and behavioral patterns that create realistic and diverse interactions.
Personas represent the people your agent will interact with in real-world scenarios. They’re automatically generated based on your simulation’s scenario and provide the diversity needed for comprehensive agent evaluation.
Each persona is automatically generated with a unique profile that includes:
Summary - A brief descriptive label like “Detail-Oriented Analyst” or “Frustrated Long-time Customer”
Story - Background context that explains their situation and needs
Purpose - Their specific goal within the simulation scenario
Attributes - Detailed personality traits, communication style, and behavioral patterns
Personas go through an approval process where you can review and approve them before they participate in conversations. This ensures only realistic, appropriate personas interact with your agent.
{ "summary": "Frustrated Repeat Customer", "story": "Sarah is a long-time customer who has been dealing with the same billing issue for three weeks. She's contacted support multiple times but hasn't received a satisfactory resolution. She's considering switching to a competitor if this isn't resolved quickly.", "purpose": "Get definitive resolution to recurring billing problem and restore confidence in the service", "attributes": { "age_group": "adult", "education": "Bachelor's degree in Marketing", "occupation": "Marketing Manager at mid-sized company", "economic_status": "Middle class, budget-conscious about recurring charges", "personality_traits": "Detail-oriented, expects accountability, values long-term relationships but has limits on patience", "values": "Fairness, reliability, and transparent communication", "habits": "Takes detailed notes of support interactions, follows up persistently on unresolved issues", "interests": "Digital marketing trends, customer experience optimization", "speech_style": "Direct and business-like, becomes more formal when frustrated", "speech_patterns": "Uses phrases like 'as I mentioned before' and references previous conversations", "typical_behavior": "Methodical problem-solver who escalates when standard processes fail", "stress_triggers": "Feeling ignored or having to repeat information multiple times", "stress_reactions": "Becomes more formal and documents everything in writing" }}
Copy
{ "summary": "Tech-Savvy New User", "story": "Alex is a software developer who just signed up for the service. He's exploring advanced features and wants to integrate the API into his workflow. He appreciates technical details and comprehensive documentation.", "purpose": "Understand advanced features and get technical implementation guidance", "attributes": { "age_group": "young_adult", "education": "Computer Science degree, self-taught in multiple frameworks", "occupation": "Full-stack developer at a startup", "economic_status": "Good income, invests in tools that improve productivity", "personality_traits": "Analytical, methodical, appreciates efficiency and well-designed systems", "values": "Clean code, thorough documentation, and reliable tools", "habits": "Reads documentation thoroughly before asking questions, tests edge cases", "interests": "Open source projects, API design, developer experience", "speech_style": "Technical and precise, uses industry terminology naturally", "speech_patterns": "Asks specific questions with context, references technical specifications", "typical_behavior": "Explores features systematically, contributes feedback for improvements", "stress_triggers": "Poorly documented APIs, inconsistent behavior, lack of examples", "stress_reactions": "Becomes more detailed in questions, seeks alternative solutions" }}
