76 judges, ready to run
Every pattern people build with Jev, as a judge you can try live, call from your code, or fork and make your own.
- AI output quality
RAG answer grader
Is the answer grounded in the retrieved source, and does it answer the question?
PassNeeds reviewFail5 questions - AI output quality
Hallucination detector
Catch invented numbers, names and claims before your users do, with the sentence quoted.
GroundedSuspectHallucinated4 questions - AI output quality
Citation checker
Does the cited passage actually support the claim it's attached to?
SupportedPartly supportedUnsupported+12 questions - AI output quality
Summary checker
Faithful, complete and free of added opinions: the three ways summaries go wrong.
Good summaryNeeds editsUnfaithful5 questions - AI output quality
Support reply grader
Check an AI support reply against the customer's message and your policy before it's sent.
Ready to sendEdit firstEscalate+15 questions - AI output quality
Claim vs evidence
Does the evidence support the claim, contradict it, or not settle it? With the sentence that decides.
SupportedNot settledContradicted3 questions - 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 - Guardrails
Brand voice check
Hold AI-written copy to your brand guidelines, including the words you never use.
On brandReviseOff brand4 questions - Agents
Tool-call firewall
Judge every agent tool call before it touches your machine: allow, ask a human, or deny.
AllowAsk a humanDeny10 questions - Agents
Is the task done?
Don't trust an agent's "done". Check the transcript for proof, open errors and skipped work.
DoneDone, but unprovenNot done5 questions - Agents
Agent loop & drift detector
Spot an agent that's stuck in a loop, drifting off-goal, or blocked, and stop wasting tokens.
ContinueNudge: change approachStop and escalate4 questions - Agents
Model router
Send each prompt to the cheapest model that can handle it.
Small modelMid-size modelFrontier model+14 questions - Agents
Tool router
Pick the right tool for a request without an LLM tool-calling round trip.
Ask to clarifyConfirm firstWeb search+62 questions - Agents
Context relevance filter
Decide what an agent keeps in context: keep, compress or drop each chunk.
KeepCompressDrop3 questions - Agents
Memory gate
Decide which messages in an agent's chat are worth remembering next session, and which change what it already knows.
Save itReplace a lineSkip4 questions - Trust & safety
Community moderator
Approve, review or remove posts against your own community rules, with severity.
ApproveSend to moderatorsRemove+18 questions - Trust & safety
Spam detector
Separate real messages from promotion, bait and bots, and only delete what's clear.
Not spamMaybe spamSpam5 questions - Trust & safety
Scam message detector
Paste an SMS, email or DM and get the probability it's a scam, and why.
Looks safeSuspiciousScam7 questions - Trust & safety
Fake review detector
Flag fake and incentivized reviews, and route real defect reports to the right team.
GenuineSuspiciousLikely fake+16 questions - Trust & safety
Marketplace listing check
Catch prohibited items, counterfeits and off-platform deals before a listing goes live.
ApproveReviewReject5 questions - Trust & safety
Conversation red-flag detector
Paste a chat and spot love-bombing, money requests, pressure and inconsistent stories.
Looks fineBe carefulRed flags5 questions - Trust & safety
Bot intent classifier
Read a client's recent requests and name what it's after and how it crawls.
AllowSlow downBlock4 questions - Content & growth
AI slop detector
Stamp generic, filler-stuffed, template-shaped AI writing, with the tells quoted.
Human & usefulSome slopAI slop7 questions - Content & growth
Post virality scorer
Score a draft post's hook, specificity, novelty and shareability before you publish.
Ready to postRework itWon't travel7 questions - Content & growth
Short-form clip finder
Score transcript chunks for hook, payoff and standalone sense, and cut the best ones.
Clip itMaybeSkip5 questions - Content & growth
Ad creative teardown
Break any ad into hook, angle, awareness stage, offer and CTA, and grade it.
StrongAverageWeak+17 questions - Content & growth
Feed triage: read, skim or skip
Sort any feed against your interests, and let the bait fall through.
Must readSkimSkip4 questions - Content & growth
Low-effort reply filter
Keep the replies that add something; collapse the 'Great post!' and hide the trolls.
KeepLow effortHide5 questions - Content & growth
Buying-signal finder
Find the posts where someone is asking for exactly what you sell.
Reply nowWorth a lookSkip5 questions - Content & growth
SEO & GEO page audit
Would this page rank, and would an AI answer engine quote it?
StrongImproveRewrite6 questions - Content & growth
Search result beatability
Is this page-one result one you could outrank? Thin, off-intent, old, forum or small site.
BeatableNeeds a humanStrong5 questions - Content & growth
Comment & feedback analyzer
Stance, questions, feature requests and bug reports in every comment, at scale.
ToxicSupportiveCritical+36 questions - Content & growth
Ad anatomy labeler
Label any ad's format, hook, angle, awareness stage, offer, proof, objection and CTA in one call.
Other formatTalking head demoCustomer testimonial+78 questions - Content & growth
Ad brief scorer
Score an ad brief on its hook, brand fit and survival odds before anything gets shot.
Shoot itReviseCut it5 questions - Content & growth
Audience reaction
How would the room react to this line: laugh, be moved, applaud, groan, or sit in silence?
LandsWorksRework3 questions - Content & growth
Draft sentence check
Check every sentence of a draft: off-goal, filler, repeating itself, or stating facts the sources don't back.
KeepTightenFix4 questions - Sales
Lead qualifier
Score every lead against your ideal customer profile: hot, warm or cold.
HotWarmCold6 questions - Sales
Outreach message checker
Check a cold email or DM for personalization, relevance and spam triggers before it's sent.
SendImproveRewrite6 questions - Sales
Deal review router
Which teams must sign off on this deal: legal, finance, security or execs?
Standard: approveNeeds reviewsMissing documents5 questions - Sales
Sales call scorer
Score discovery, objection handling and next steps on every call transcript.
Strong callCoaching momentsDeal at risk6 questions - Support & ops
Support ticket router
Route every ticket to the right team, fast-track the urgent ones, auto-answer the easy ones.
Needs triageUrgentSend a docs link+65 questions - Support & ops
Inbox triage
Sort every email: action needed, FYI, meetings, newsletters, receipts, spam, and what's urgent.
UrgentAction neededSpam+73 questions - Support & ops
Churn risk detector
Spot the customers who are about to leave while there's still time to save them.
HealthyAt riskSave now6 questions - Support & ops
Alert & log triage
Page on-call for what matters, open tickets for the rest, and ignore the noise.
Page on-callOpen a ticketIgnore4 questions - Support & ops
Customer chat monitor
Watch busy customer groups and chats, and only interrupt the owner when it matters.
Notify the ownerKeep an eye on itNothing needed5 questions - Recruiting
Resume screener
Check each resume against the bar you define, with the supporting line quoted.
AdvanceHuman reviewBelow the bar6 questions - Recruiting
Application reviewer
Find evidence of real work in thousands of applications, not polished filler.
ShortlistMaybeNot now5 questions - Recruiting
Interview feedback checker
Make interview write-ups evidence-based and flag biased language before the debrief.
Solid feedbackIncompletePossible bias4 questions - Finance & compliance
Expense categorizer
Put every transaction in the right bookkeeping category, and flag what looks personal.
Needs reviewPersonal?Software+123 questions - Finance & compliance
Contract risk check
Spot auto-renewals, uncapped liability, broad indemnities and IP grabs, clause by clause.
Standard termsLegal reviewHigh risk7 questions - Finance & compliance
Marketing claims compliance
Catch guarantees, health claims, unproven superlatives and missing disclosures in ad copy.
CompliantReviseBlock6 questions - Finance & compliance
Transaction risk screen
Prioritize AML alerts: unusual for the customer, structuring, high-risk places, vague purpose.
ClearInvestigateEscalate6 questions - Finance & compliance
Insurance claim triage
Fast-track simple claims, request what's missing, and send the rest to the right specialist.
Straight-throughRequest informationSpecialist review+14 questions - Engineering
PR risk review
Is this pull request safe to merge, or does it need a careful human look?
Safe to mergeNeeds careful reviewChanges requested7 questions - Engineering
Semantic code lint
Lint code against conventions written in plain English, the rules a regex can't express.
CleanWarningsViolations5 questions - Engineering
Commit message check
Does the commit message match the staged diff, with no secrets or debug leftovers?
Looks goodAmendBlock5 questions - Engineering
PR labeler
Label pull requests by type and area, and flag what belongs in the changelog.
FeatureBug fixRefactor+64 questions - Engineering
Package risk check
Catch typosquats and hostile install scripts before an install runs them.
AllowReviewBlock7 questions - Engineering
Vulnerable code check
Flag injection, path traversal, hardcoded secrets and other common holes in a change.
CleanReviewVulnerable4 questions - Engineering
Judge question review
Review a question before Jev answers it: two judgments in one, inputs no option fits, a rating hiding in a yes/no.
Good to goImproveRewrite3 questions - Engineering
Should this be a judge?
Paste a prompt from your code. Find out whether it's really a decision a judge would answer faster and cheaper.
Use a judgeSplit itKeep the LLM4 questions - Research & data
Survey response coder
Code open-ended survey answers into themes and sentiment, thousands at a time.
PositiveNegativeMixed+18 questions - Research & data
Systematic review screener
Screen abstracts against your inclusion and exclusion criteria, one criterion at a time.
IncludeFull-text reviewExclude5 questions - Research & data
Sentiment & emotion
Sentiment, the dominant emotion, its intensity, and whether it's sarcastic.
Very negativeNegativeNeutral+24 questions - Research & data
Record matcher (dedupe)
Do these two records describe the same person, company or product?
MatchPossible matchDifferent4 questions - Research & data
News & event severity
Rate headlines by severity, topic and region, and alert on the ones that matter.
AlertWatchLog4 questions - Research & data
Research desk router
Send each item in a research feed to the right desk: papers, repos or market news.
No deskPapers deskRepos desk+11 questions - Research & data
Novelty check: new, update or duplicate?
Check a fresh note against what you already know: new, an update, or a duplicate.
NewUpdateDuplicate1 questions - Product
User intent classifier
What does the user want, and are they telling the app to do something right now?
Ask to clarifyAsk a questionReport a problem+72 questions - Product
Product feedback triage
Sort feedback into bugs, requests, confusion and praise, and surface what's critical.
Critical bugUser at riskBug+64 questions - Product
Landing page clarity audit
Would a first-time visitor get what you sell, who it's for and why it's better?
ClearFixableConfusing7 questions - Product
Startup idea roast
Kill it, fix it, or ship it: pressure-test an idea in one call.
Ship itFix itKill it6 questions - Product
Dark pattern detector
Flag manipulative UX copy and flows: confirmshaming, hidden costs, roach motels.
FairQuestionableManipulative6 questions