Validate agent function-call output with repair hints

Created by

Dennis

Actor

LLM Output Validator: JSON Schema + Repair Hints

Check agent function-call JSON against a schema — get repair hints per error so the agent self-corrects without a new LLM call.

Try for free

LLM Output Validator: JSON Schema + Repair Hintscodeclouds/llm-output-validator

Valid

Error count

Truncated

+2 fields

Input

Documents to validate(required):{"function": "get_weather", "location": "Amsterdam", "units": "celsius"}

JSON Schema(required):{4 fields}

Generate repair hints:true

Apply safe normalization:false

Output fields

Valid

Error count

Truncated

Repairable

Errors

How it works

Sign up on Apify or log in

The LLM Output Validator: JSON Schema + Repair Hints Actor is ready to run with the inputs already set for "Validate agent function-call output with repair hints". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Validate agent function-call output with repair hints" task

The LLM Output Validator: JSON Schema + Repair Hints Actor will start running based on the input automatically. You can also change all the input fields, like documents to validate, JSON Schema, and more, to match your specific use case.

Receive the "Validate agent function-call output with repair hints" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as #, valid, error count, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Validate agent function-call output with repair hints" task via API.