Create Prompt Version

create a new prompt version under /agents//prompts/versions.

POST /v1/agents/{agent_id}/prompts/versions

Create Prompt Version Agent Scoped

cURL

curl --request POST \
  --url https://api.getbluejay.ai/v1/agents/{agent_id}/prompts/versions \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <x-api-key>' \
  --data '
{
  "prompt_text": "<string>",
  "commit_message": "<string>",
  "labels": [
    "<string>"
  ],
  "metadata": {}
}
'

200

{
  "prompt_text": "<string>",
  "version": 123,
  "agent_id": 123,
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "commit_message": "<string>",
  "labels": [
    "<string>"
  ],
  "metadata": {}
}

Integration Prompt for AI Agents

# Bluejay — Testing & Monitoring Platform for Conversational AI Agents

You are a senior backend engineer integrating the Bluejay API. Think step-by-step: first understand the endpoint, then plan the integration, then implement with minimal changes.

## Create Prompt Version — POST /v1/agents/{agent_id}/prompts/versions

> **What this endpoint does:** create a new prompt version under /agents/{agent_id}/prompts/versions.

**Endpoint:** POST `https://api.getbluejay.ai/v1/agents/{agent_id}/prompts/versions`
**Auth:** `X-API-Key` header
**Content-Type:** application/json

### Required Parameters
| Name | Type | Description |
|------|------|-------------|
| agent_id | integer |  |
| X-API-Key | string | API key required to authenticate requests. |
| prompt_text | string |  |

Review the full parameter list at https://docs.getbluejay.ai/api-reference/endpoint/create-prompt-version and include any optional parameters (e.g., `commit_message`, `labels`, `metadata`) that serve your integration's use case and align with Bluejay's testing and monitoring capabilities.

### Request Body (required fields)
```json
{
  "prompt_text": "You are a helpful assistant."
}
```

Refer to the full schema at https://docs.getbluejay.ai/api-reference/endpoint/create-prompt-version. Include optional fields that serve the goal of setting up for testing and monitoring on Bluejay.

### Example
**POST with body:**
```python
import requests

def create_prompt_version(agent_id: int, payload: dict, api_key: str) -> dict:
    url = f"https://api.getbluejay.ai/v1/agents/{agent_id}/prompts/versions"
    headers = {"X-API-Key": api_key}
    response = requests.post(url, headers=headers, json=payload)
    response.raise_for_status()
    return response.json()
```

### Constraints
- Minimal changes — only add/change files needed for this integration.
- Match existing codebase patterns (naming, file structure, error handling).
- Include error handling for 422: Validation Error.

### Integration Checklist
Before writing code, verify:
1. Which module/service owns this API domain in the codebase?
2. What HTTP client and error-handling patterns does the project use?
3. Are there existing types/interfaces to extend?

Then implement the integration, export it, and confirm it compiles/passes lint.

Creates a new prompt version under /agents/{agent_id}/prompts/versions.

Headers

X-API-Key · string · required

API key required to authenticate requests.

Path Parameters

agent_id · integer · required

Body

application/json

body for agent-scoped create version endpoint (agent_id in path).

prompt_text · string · required

commit_message · string | null

labels · string[] | null

metadata · Metadata · object

Response

200

application/json

Successful Response

response model for prompt without created_at.

prompt_text · string · required

the prompt content

version · integer · required

the version number of the prompt

agent_id · integer · required

id of the agent that owns this prompt

id · string<uuid> | null

the id of the prompt

commit_message · string | null

labels · string[] | null

labels associated with the prompt

metadata · Metadata · object

arbitrary JSON metadata