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 →

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:

{
  "jobId": "550e8400-e29b-41d4-a716-446655440000",
  "status": "queued",
  "agentId": "agent_123",
  "message": "Agent execution queued successfully"
}

API Endpoints

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

Response Format

All responses are JSON with this structure:

Success (200):

{
  "jobId": "string",
  "status": "queued" | "processing" | "completed" | "failed",
  "agentId": "string"
}

Error (4xx/5xx):

{
  "error": "string",
  "message": "string",
  "code": "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

• Limits are configured per API key
• Headers include rate limit info:

  X-RateLimit-Limit: 100
  X-RateLimit-Remaining: 47
  X-RateLimit-Reset: 1638360000

• When exceeded, returns 429 with retryAfter seconds

Learn more about rate limits →

Best Practices

1. Handle Errors Gracefully - Implement retry logic with exponential backoff
2. Monitor Rate Limits - Check response headers
3. Use HTTPS - All requests must use HTTPS
4. Secure API Keys - Store in environment variables
5. Implement Timeouts - Set reasonable request timeouts

SDKs & Libraries

Official SDKs coming soon! Currently use standard HTTP clients:

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

Need Help?

• API Reference - Detailed endpoint documentation
• Code Examples - Working samples
• Troubleshooting - Common issues
• Support - Get help

---

Ready to integrate? View authentication guide →