- Base URL:
https://api.qa.tech/v1 - Authentication: Bearer token (project API token)
- Content-Type:
application/json
When to Use This API
- Automated test creation – Send context from your system to create tests without opening the QA.tech UI
- PR/Change reviews – Automatically trigger AI-powered change reviews from CI/CD pipelines
- Custom integrations – Build buttons or workflows in your project management tools that interact with QA.tech Chat
- AI-assisted QA workflows – Let your automation systems communicate with QA.tech’s AI assistant
Authentication
All Chat API endpoints require Bearer token authentication:Create Chat Conversation
Create a new chat conversation and send the first message. Processing is asynchronous—poll the Get Conversation endpoint until the assistant’s response is complete. Endpoint:POST /chat
Request Body
Application Overrides
Each object in theapplicationOverrides array:
Environment override – use one of:
- By URL:
{ "url": "https://...", "name": "Optional name" } - By short ID:
{ "shortId": "env_aB3xY9" } - By build:
{ "applicationBuildShortId": "build_abc123" }(for mobile apps)
Response (202 Accepted)
messages array is empty on creation. Poll Get Conversation to retrieve the assistant’s reply.
Example
Example with Environment Override
Start Change Review
Create a conversation that initiates an AI-powered change review. Supports two modes: reviewing a pull request URL or raw code changes. Endpoint:POST /chat/change-review
Request Body (PR Mode)
Request Body (Raw Changes Mode)
Response (202 Accepted)
Same format as Create Chat Conversation.Example: Review a Pull Request
Example: Review Raw Changes
Send Message to Conversation
Send a follow-up message to an existing conversation. Returns 202 immediately—poll Get Conversation for the assistant’s reply. Endpoint:POST /chat/{chatConversationShortId}
Path Parameters
Request Body
Same as Create Chat Conversation.Response (202 Accepted)
Same format as Create Chat Conversation, with existing messages included.Example
Get Conversation
Retrieve conversation metadata and messages. Use this to poll for the assistant’s response after sending a message. Endpoint:GET /chat/{chatConversationShortId}
Path Parameters
Query Parameters
Response (200 OK)
Response Fields
Message Fields
Polling for Completion
To wait for the assistant’s response, poll until the most recentassistant message has status: "COMPLETED". We recommend polling every 2-5 seconds.
Assistant responses typically complete within 10-60 seconds depending on the complexity of the request. Test creation and execution may take several minutes.
Example
Error Responses
Error responses include a body:
{ "message": "Error description" }.
Related
- AI Chat Assistant – Learn about QA.tech’s AI assistant
- API Introduction – Authentication and ID reference
- Start Run API – Trigger test runs programmatically