Brand voice check
Hold AI-written copy to your brand guidelines, including the words you never use.
Paste your voice guidelines once, then score every AI draft against them: on voice or not, banned words and claims (quoted), unexplained jargon and readability.
Try it live
Real calls to Jev. Pick an example or paste your own.
Pick an example or paste your own input, then run it.
Under the hood
Every question and rule, in the open. Fork it to change any of them.
What it asks
Reads guidelines and text, then asks 4 questions in one call.
- Q1On voiceScore
How well does the
textfollow the voice described inguidelines?- 0Clashes with it
- 1Partly on voice
- 2On voice
- 3Unmistakably on voice
- Q2Uses banned words or claimsYes / no quotes evidence
Does the
textuse a word, phrase or claim that theguidelinessay to avoid? - Q3Unexplained jargonYes / no
Does the
textuse jargon a first-time customer wouldn't understand, without explaining it? - Q4ReadabilityScore
How easy is the
textto read?- 0Hard: long, dense sentences
- 1Moderate
- 2Easy: short, plain sentences
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Uses banned words or claims ≥ 0.7Off brand
- 2If On voice < 1 of 3Off brand
- 3If On voice < 1.8 of 3Revise
- 4If Unexplained jargon ≥ 0.6Revise
- 5If Readability < 0.8 of 2Revise
- ·DefaultOn brand
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/brand-voice-check/run.
curl -X POST https://tryevally.com/api/v1/judges/brand-voice-check/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "guidelines": "We sound like a helpful friend who knows their stuff. Plain words, short sentences. Never say '\''revolutionary'\'', '\''synergy'\'', '\''best-in-class'\'' or '\''leverage'\''. No exclamation marks.", "text": "Leverage our revolutionary, best-in-class platform to unlock synergy across your entire organization!" }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in Guardrails
- Guardrails
Prompt injection guard
Screen user messages for jailbreaks, injected instructions and data exfiltration.
AllowReviewBlock7 questions - Guardrails
LLM reply guard
Check every model reply for policy breaks, unsafe advice and leaked data before it's shown.
AllowReviewBlock+18 questions - Guardrails
PII detector
Find personal data and secrets in text, and quote exactly where they are.
No personal dataPossible PIIContains PII5 questions - Guardrails
Off-topic guard
Keep an assistant on the job you built it for.
AnswerDeflect politelySmall talk3 questions