Skip to main content

​
1. Get an API key

Create an account at the dashboard: https://tryyomira.com/admin.html Store the returned API key as an environment variable. 
export YOMIRA_API_KEY="sim_..."
If you are using an AI agent, you can give the key to the agent and ask it to follow the agent setup guide.

​
2. Create a simulation

curl -s -X POST "https://tryyomira.com/api/simulate" \
  -H "content-type: application/json" \
  -H "x-api-key: $YOMIRA_API_KEY" \
  -d '{
    "objective": "Decide whether to publish this landing page.",
    "artifact": {
      "type": "landing_page",
      "content": "Paste the exact page, message, post, or offer people will see."
    },
    "audience": {
      "description": "Describe who will see it, where they see it, what they already believe, and what action matters."
    },
    "simulation": {
      "mode": "fast",
      "target_n": 40,
      "max_agent_voices": 8,
      "max_output_tokens": 30000
    }
  }'
The API returns 202 Accepted with a simulation_id. Do not treat 202 as a failure. Yomira simulations are asynchronous.

​
3. Poll the result

curl -s "https://tryyomira.com/api/simulations/SIMULATION_ID" \
  -H "x-api-key: $YOMIRA_API_KEY"

​
4. Export Markdown

curl -L "https://tryyomira.com/api/simulations/SIMULATION_ID?format=markdown" \
  -H "x-api-key: $YOMIRA_API_KEY" \
  -o simulation.md

​
What to include

The output is only useful when the input contains real context. Include:
  • The exact artifact people will see.
  • The target audience.
  • The channel where they see it.
  • Sender or company context.
  • The desired action.
  • Known worries, objections, and alternatives.

​
First useful tests

Start with one of these: