Skip to content

Core Concepts

Understanding the key concepts behind Converra's AI optimization platform.

Prompts

A prompt is the system instruction that guides your AI's behavior. In Converra, prompts are:

  • Versioned - Every change is tracked
  • Optimizable - Can be improved through automated testing
  • Measurable - Performance metrics are collected from real conversations
typescript
// Example prompt structure
{
  name: "Customer Support Agent",
  content: "You are a helpful customer support agent...",
  llmModel: "gpt-4o",
  tags: ["support", "production"]
}

Optimization

Optimization is the process of improving your prompts through simulation testing:

  1. Variant Generation - AI creates alternative versions of your prompt
  2. Simulation - Each variant is tested against diverse personas
  3. Evaluation - Performance is measured across multiple metrics
  4. Selection - The best-performing variant is identified

Optimization Modes

ModeUse Case
ExploratoryQuick iteration, finding improvements fast
ValidationStatistical rigor, production-ready decisions

Conversations

A conversation is a logged interaction between a user and your AI. Logging conversations enables:

  • Insights generation - Understanding what's working and what isn't
  • Performance tracking - Measuring prompt effectiveness over time
  • Optimization fuel - Real data to guide improvements

Personas

Personas are simulated users that test your prompts:

  • Frustrated Customer - Tests patience and de-escalation
  • Enterprise Buyer - Tests technical depth
  • First-time User - Tests clarity and onboarding
  • Power User - Tests efficiency

You can create custom personas to match your specific user base.

Variants

A variant is an alternative version of your prompt created during optimization:

  • Variants compete against your original prompt
  • The winner can be applied with one click
  • Previous versions are always preserved

Insights

Insights are AI-generated analysis of your prompt's performance:

  • Task completion rates
  • Sentiment analysis
  • Common topics and issues
  • Improvement recommendations

Next Steps