Low-effort reply filter
Keep the replies that add something; collapse the 'Great post!' and hide the trolls.
Judges each reply against the post it answers: does it add information, a question or a counterpoint, or is it generic praise, self-promotion, AI-written filler or trolling.
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 post and reply, then asks 5 questions in one call.
- Q1Adds somethingYes / no
Does the
replyadd information, an experience, a counterpoint or a specific question about thepost? (A generic question that fits any post, such as 'What's your biggest takeaway?', doesn't count.) - Q2GenericYes / no
Could the
replybe posted under almost any post ('Great post!', 'This 🔥', 'So true', 'Agreed')? - Q3Self-promotionYes / no
Does the
replymainly promote the replier's own product, content or profile? - Q4HostileYes / no
Is the
replyhostile, condescending or trolling? - Q5AI fillerYes / no
Does the
replyread like an AI-generated comment (it restates the post, praises it generically, and asks a question to farm engagement)?
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Hostile ≥ 0.75Hide
- 2If Self-promotion ≥ 0.75Hide
- 3If Generic ≥ 0.7Low effort
- 4If AI filler ≥ 0.7Low effort
- 5If Adds something < 0.35Low effort
- ·DefaultKeep
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/reply-filter/run.
curl -X POST https://tryevally.com/api/v1/judges/reply-filter/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "post": "We migrated 40 services from REST to gRPC. Latency dropped 30%, but debugging got much harder.", "reply": "Great insights! 🙌 This is so true. What'\''s your biggest takeaway from this journey?" }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in Content & growth
- 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
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