Skip to Content
Introduction

Introduction

Veris is a simulation platform for testing and training AI agents.

It provides a complete simulation sandbox to help you develop, test, and train high-quality AI agents that are optimized for automating a task. Veris environments come pre-loaded with simulated users and simulated versions of common services and SaaS platforms — your agent makes real API calls to LLM-powered mocks without any code changes.

Agent-Native Development

Traditional software development relies on unit tests and staging environments. But AI agents are fundamentally different — they make decisions, use tools, and have conversations. They need to be trained and tested in an environment that closely mirrors their final production setup.

Veris enables agent-native development: you build, test, and improve your agent inside a simulation environment that replicates the real world. The same services your agent will call in production (Salesforce, Google Calendar, Stripe, Jira, Slack, and more) are available as intelligent mocks that understand context and generate realistic data. A simulated user with specific goals drives the conversation, just like a real customer would.

This approach means every iteration happens in conditions that match production — so the behaviors you see during development are the behaviors you get in deployment.

The Workflow

One-time setup

  1. Setup — Install the CLI, configure veris.yaml, package your agent, and push to Veris
  2. Generate scenarios & graders — AI reads your agent’s code and creates test cases (regenerate when services or integrations change)

How to Use the Sandbox

Development Loop

Development Loop

Simulate → Evaluate → Report → Fix → Simulate again. Each iteration improves your agent based on root cause analysis and actionable recommendations.

CI/CD & Regression Testing

CI/CD Pipeline

Integrate Veris into your CI/CD pipeline to catch regressions before they ship. Every push triggers a simulation suite, evaluations compare against your baseline, and a quality gate blocks deploys that fall below your threshold.

Training: Reinforcement Learning

RL Training

The simulation environment serves as a live training ground. Graders and assertions provide reward signals, and the model is updated to favor higher-scoring behaviors.

Training: Supervised Fine-Tuning

SFT Training

High-scoring simulation transcripts become supervised training data. Fine-tune a base model on correct agent behavior for your specific task domain.

Key Concepts

ConceptWhat It Is
EnvironmentAn isolated sandbox that simulates the production environment for an AI agent
ServiceA simulated API (Salesforce, Calendar, Stripe, etc.) that your agent calls
ScenarioA test case defining actors, objectives, context, and assertions
SimulationA single test run — one scenario executed in an isolated container
RunA collection of simulations (e.g., a scenario set run at scale)
GraderAn evaluation function that scores agent behavior from transcripts
EvaluationResults of graders running against simulation transcripts
ReportRoot cause analysis with actionable recommendations and auto-apply
TrainingFine-tune models using simulation data (SFT) or environments (RL)

Getting Started

  • Quickstart — Get your first simulation running in under 10 minutes
  • Templates — Ready-to-use veris.yaml templates for common setups
  • Full Walkthrough — Comprehensive guide explaining every step and concept
  • CLI Installation — Install and authenticate the Veris CLI