Tone

Tone identifies the dominant emotional tone of a response, from formal and empathetic to frustrated or blunt. Run it to confirm content matches the communication style your audience expects.

What it does

Tone is an LLM-as-Judge eval. It reads the generated output and scores its dominant emotional tone.

Input

Output

Run it from code

Call evaluate() with the template name and the eval’s required inputs. It returns the score and the reason.

from fi.evals import evaluate

result = evaluate(
    "tone",
    output="Dear Sir, I hope this email finds you well. I look forward to any insights or advice you might have whenever you have a free moment",
    model="turing_flash",
)

print(result.score)
print(result.reason)

import { evaluate } from "@future-agi/ai-evaluation";

const result = await evaluate(
  "tone",
  {
    output: "Dear Sir, I hope this email finds you well. I look forward to any insights or advice you might have whenever you have a free moment"
  },
  { modelName: "turing_flash" }
);

console.log(result);

When to use

Run Tone wherever the emotional register of a response matters as much as its content.

• Text, audio, and chat outputs where brand voice or emotional register matters
• Safety reviews, to catch responses that read as hostile, dismissive, or overly familiar
• Customer-facing copy, to confirm tone matches the audience and context

What to do when Tone fails

Adjust the tone of the content to align with the intended emotional context or communication goal, ensuring it’s appropriate for the audience and purpose.

Use tone analysis to refine messaging, making it more engaging, professional, or empathetic as needed. Continuously improving tone detection models helps recognize and interpret nuanced emotional expressions, leading to more accurate and context-aware assessments.