Is Informal Tone
Detects informal or casual language in AI output, including slang, contractions, and emoji.
Is Informal Tone flags casual language markers like slang, contractions, and emoji. Run it wherever a response needs to stay formal, or wherever it needs to sound conversational.
What it does
Is Informal Tone is an LLM-as-Judge eval. It reads the generated output and classifies its tone as formal or informal.
Input
| Required Input | Type | Description |
|---|---|---|
output | string | The text content to evaluate for informal tone |
Output
| Field | Type | Description |
|---|---|---|
| Result | Pass / Fail | Pass means informal tone was detected; Fail means formal tone was detected |
| Reason | string | A plain-language explanation of why the text was classified as formal or informal |
Run it from code
Call evaluate() with the template name and the eval’s required inputs. It returns the score and the reason.
Note
Before running: install the SDK and set FI_API_KEY / FI_SECRET_KEY. The model argument in the snippets is the evaluator model Future AGI uses to run the eval; turing_flash is a fast default.
from fi.evals import evaluate
result = evaluate(
"is_informal_tone",
output="heyy thanks a ton for this!! you're seriously the best, gonna try it out rn 😄",
model="turing_flash",
)
print(result.score)
print(result.reason)import { evaluate } from "@future-agi/ai-evaluation";
const result = await evaluate(
"is_informal_tone",
{
output: "heyy thanks a ton for this!! you're seriously the best, gonna try it out rn 😄"
},
{ modelName: "turing_flash" }
);
console.log(result);When to use
Run Is Informal Tone wherever the formality of the response needs to match a specific brand voice.
- Text and chat outputs where brand voice mandates a formal or casual register
- Customer support responses, to confirm tone matches the audience
- Compliance-sensitive content, where informal language could look unprofessional
What to do when Is Informal Tone fails
If the content is detected as having an informal tone but formality is required, replace contractions with full forms (for example, “don’t” to “do not”), remove slang, colloquialisms, and emoji, and use more professional terminology and phrasing. Maintain a consistent, professional tone throughout and avoid first-person perspective where appropriate.
If the content is detected as formal but informality is desired, incorporate appropriate contractions, use more conversational language, include relatable examples or analogies, and consider a first-person perspective when appropriate.
Questions & Discussion