API Overview

The PrompTick API provides programmatic access to execute your deployed agents from any application.

Base URL

https://api.promptick.ai/api/v1

Authentication

All API requests require an API key in the Authorization header:

Authorization: Bearer pk_live_YOUR_API_KEY

Learn more about authentication →

OpenAPI Specification

The machine-readable OpenAPI 3.0 spec for the public API is available at:

https://api.promptick.ai/openapi.yaml

You can import this into Postman, Insomnia, or any OpenAPI-compatible tool.

Quick Example

Execute an agent:

curl -X POST https://api.promptick.ai/api/v1/agents/{agentId}/execute \
  -H "Authorization: Bearer pk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"variables": {"product_name": "Smart Watch"}}'

Response (202 Accepted):

{
  "success": true,
  "executionId": "550e8400-e29b-41d4-a716-446655440000",
  "agentId": "agent_123",
  "agentName": "Product Description Generator",
  "status": "processing",
  "message": "Agent execution started",
  "statusUrl": "/api/v1/agents/agent_123/executions/550e8400-e29b-41d4-a716-446655440000"
}

API Endpoints

Endpoint	Method	Description
/agents/{agentId}/execute	POST	Execute an agent
/agents/{agentId}/executions/{executionId}	GET	Get execution status

note

The public v1 API does not provide a list-executions endpoint. Use the PrompTick dashboard to browse execution history.

Response Format

All responses are JSON.

Success (202 Accepted) — agent execution accepted and started:

{
  "success": true,
  "executionId": "string",
  "agentId": "string",
  "agentName": "string",
  "status": "processing",
  "message": "string",
  "statusUrl": "string"
}

Error (4xx/5xx):

{
  "error": "string",
  "message": "string"
}

Error Codes

Code	Status	Description
400	Bad Request	Invalid request body or missing required fields
401	Unauthorized	Invalid or missing API key
403	Forbidden	Agent not active or API access disabled
404	Not Found	Agent does not exist
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	Server error
503	Service Unavailable	Background job system unavailable

Rate Limiting

Each API key has three configurable counters with these defaults:

Window	Default	Max configurable
Per minute	10	100
Per hour	100	1,000
Per day	1,000	10,000

When a limit is exceeded, the API returns 429 Too Many Requests with the current rateLimits object in the body.

Learn more about rate limits →

Best Practices

1. Handle Errors Gracefully - Implement retry logic with exponential backoff
2. Use HTTPS - All requests must use HTTPS
3. Secure API Keys - Store in environment variables
4. Implement Timeouts - Set reasonable request timeouts
5. Poll Status, Don't Block - Execution is asynchronous; poll the status URL

SDKs & Libraries

Official SDKs coming soon. For now, use any standard HTTP client:

• Node.js: axios, fetch
• Python: requests, httpx
• PHP: guzzle, curl
• Ruby: faraday, httparty
• Go: net/http

Need Help?

• Authentication - API key setup
• Code Examples - Working samples
• Troubleshooting - Common issues
• Support - Get help

---

Ready to integrate? View authentication guide →