Core Concepts

Key concepts behind Converra's closed-loop optimization system for AI agents.

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

// Example prompt structure
{
  name: "Customer Support Agent",
  content: "You are a helpful customer support agent...",
  llmModel: "gpt-4o",
  tags: ["support", "production"]
}

Agent Systems

An agent system is a set of prompts that work together as a multi-step flow (for example: an entry/router prompt handing off to specialist prompts).

Converra can auto-discover agent systems from imported traces and show:

• the entry prompt
• the most common paths (prompt sequences) and their frequencies
• the weakest link (lowest-performing prompt in the system)
• a diagnostic, weighted “system score”

Flow constraints (what you should expect)

For reliable, bounded simulation, Converra models discovered agent systems with a constrained flow:

• Branching between steps is supported (based on what we observe in traces).
• Each run records the path taken so comparisons are apples-to-apples.
• Some patterns (like unbounded loops/retries or complex parallelism) may not be supported in early versions; in those cases Converra falls back to individual optimization.

These constraints apply to Converra’s simulation model, not your production code.

Optimization

Optimization is the closed-loop process of diagnosing prompt failures and proving fixes in simulation. It connects to where your prompts already live:

1. Import - Pull prompts and traces from LangSmith, your API, or paste manually
2. Diagnose & Fix - Identify failure patterns and generate targeted prompt variants
3. Simulate & Prove - Test fixes against diverse personas and regression scenarios
4. Select & Deploy - Ship the proven winner back to production

Optimization Modes

Mode	Use Case
Exploratory	Quick iteration, finding improvements fast
Validation	Statistical 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

• Quick Start - Get started in 5 minutes
• Creating Prompts - Create your first prompt
• Running Optimizations - Improve your prompts