> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryyomira.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Credits and timeouts

> How to choose simulation size, avoid timeouts, and control cost.

Yomira jobs run asynchronously.

Create a simulation, receive a `simulation_id`, then poll until the job is completed. This keeps agent workflows stable even when the simulation takes longer than a normal request.

## Simulation size

Use smaller runs while drafting and larger runs when the artifact is close to real publication.

| Use case                   | Suggested `target_n` | Mode                          |
| -------------------------- | -------------------: | ----------------------------- |
| Quick message check        |                40-60 | `fast`                        |
| Content preflight          |               60-120 | `fast` or `standard`          |
| Product idea check         |               80-160 | `standard`                    |
| Multiple option comparison |    40-100 per option | `fast` first, then `standard` |
| Enterprise grounded pilot  |               custom | custom                        |

## Timeout behavior

If the initial request returns `202 Accepted`, the job is queued correctly.

Poll:

```bash theme={null}
curl -s "https://tryyomira.com/api/simulations/SIMULATION_ID" \
  -H "x-api-key: $YOMIRA_API_KEY"
```

If a client or AI agent times out, do not restart the simulation immediately. Poll the existing `simulation_id` first.

## Cost control

When testing:

* start with `target_n: 40`
* limit `max_agent_voices`
* export Markdown only after completion
* simulate fewer options first, then expand

When making a real decision:

* include the exact artifact
* include richer context
* simulate every option that could actually be chosen
* use a larger `target_n` only after the options are concrete

## When self-serve is not enough

Self-serve simulations are context-enriched synthetic simulations. For high-stakes enterprise work, use a grounded pilot where Yomira builds the audience dataset from customer notes, interviews, reviews, CRM context, social data, or market source material.