Documentation

← All agent examples

Score AI-written replies for accuracy, tone and policy

Paste a customer message and the reply your chatbot or AI agent wrote, and get it scored from 1 to 5 for accuracy, tone and policy compliance against the rules in the prompt, with the specific problems found. Replies that score low are sent to a person to mark as acceptable or needing a fix.

Customer support
Moderation
AI quality
chatbot QA
evaluation
scoring
tone
policy
LLM output review
human in the loop

How it starts

When you run it.

What it needs

No knowledge base, memory bank or connection to create first.

Steps

Score the reply

Prompt Call

Parse and validate the scores

Extract Content

Is any score low?

If / Else

If yes:

Review the low-scoring reply

Human-in-the-Loop

Otherwise:

Scored without review

Text

Show the scores

Display Result