Core concepts

Test targets

Fix the target version, parameters, and behavioral boundary, then determine whether its interface is suitable for the no-code Evaluation Trigger.

Define the exact model or application you want to test, then keep its version and material parameters fixed during the evaluation. Targets with a simple HTTP request-and-response interface can usually connect through the no-code Evaluation Trigger.

Types of test target

Target typeWhat is testedTrigger fit
Hosted modelA fixed model version and serving configurationGood fit when it has a callable inference endpoint
ChatbotThe chatbot backend, instructions, retrieval, and filtersGood fit when its API reflects the user-facing behavior
AI applicationThe final response produced by the applicationGood fit when one request returns one evaluable response

Fix the target version and parameters

Record the settings that can change the target response and keep them unchanged for the full run.

FixRecord
Model versionProvider, model ID, checkpoint, fine-tune, or application release
System configurationSystem prompt, retrieval or knowledge version, guardrails, and filters
Generation parametersTemperature, top_p, maximum output length, seed, or equivalent settings
Connection contractTarget URL, request shape, response path, and session behavior

Check Evaluation Trigger compatibility

Evaluation Trigger sends each AIDX prompt to the target and extracts the answer without a custom integration script.

Trigger works whenRequirement
The target is reachableAIDX can call its HTTP endpoint with the supported headers
The request is mappableThe prompt can be inserted into a stable request body
The response is mappableOne request returns answer text at a stable JSON path