Is Concise
Measures whether a response is brief and to the point, detecting verbose or padded outputs that add length without substance.
Is Concise checks whether a response stays brief and avoids padding that adds length without adding substance. Run it wherever verbosity hurts the user experience.
What it does
Is Concise is an LLM-as-Judge eval. It reads the generated output and checks whether it’s concise and free of unnecessary redundancy.
Input
| Required Input | Type | Description |
|---|---|---|
output | string | Generated content by the model to be evaluated for conciseness |
Output
| Field | Type | Description |
|---|---|---|
| Result | Pass / Fail | Pass means the content is concise; Fail means it’s not |
| Reason | string | A plain-language explanation of the evaluation |
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_concise",
output="Honey doesn't spoil because its low moisture and high acidity prevent the growth of bacteria and other microbes.",
model="turing_flash",
)
print(result.score)
print(result.reason)import { evaluate } from "@future-agi/ai-evaluation";
const result = await evaluate(
"is_concise",
{
output: "Honey doesn't spoil because its low moisture and high acidity prevent the growth of bacteria and other microbes."
},
{ modelName: "turing_flash" }
);
console.log(result);When to use
Run Is Concise wherever padded, repetitive responses would frustrate users or waste space.
- Text and chat outputs where brevity is part of the expected user experience
- Customer support responses, to catch answers padded with filler
- Interfaces with limited display space, where verbose answers get truncated
What to do when Is Concise fails
Conciseness depends on context: what’s concise for a complex topic might still be relatively lengthy. This evaluation works best on complete responses rather than fragments, and very short responses may be marked as concise but might fail other evaluations like completeness.
Consider the balance between conciseness and adequate information, since extremely brief responses might miss important details.
Questions & Discussion