# Simulations

**Summary:** Scripted conversations that run against the Customer Agent at scale. Coming soon.

**In short:** Scripted conversations that run against the Customer Agent automatically. Catch regressions and validate edge cases before a change goes live.

**Last updated:** 2026-05-27

Preview is one human, one session. Useful, but slow. Simulations turn the questions you care about into a regression suite that runs every time you change a Source, a Procedure, or a Personality. The suite is what makes Living Knowledge improvements safe.

## Key concepts

### Scripted turns
The customer's side of a conversation, written as a sequence of messages. Includes follow-ups and Procedure clicks.

### Conditions
The Audience, Living Context, topic, and surface the Simulation runs under. Same setup you would use in Preview.

### Expected outcomes
What you expect the agent to say or do. Used to score each run.

### Suites
Groups of Simulations that run together. A daily regression suite, a per-moment suite, a pre-release suite.

## What you can do here

Once Simulations ship, you will be able to:

- Write scripted conversations that drive the agent through specific scenarios
- Group Simulations into suites and run them on a schedule or on demand
- Compare scores across runs to catch regressions
- Trace failures to the Source, Procedure, or Living Context value that caused them

## When to use it

- Before any change to Living Knowledge that could break existing answers
- Before publishing a new component or Moment
- Before scaling to a new market or language

## What to do until Simulations ship

Three things cover most of what Simulations would do.

- Use [Preview](/en/help/test/preview/) for ad-hoc checks
- Use [Quality reports](/en/help/test/quality-reports/) to score the agent against control questions
- Use [Conversations](/en/help/analyze/conversations/) to spot answers that need attention in production