Postmark
Web demo that reads a draft social post and returns Jev's tone choice, a 0-3 virality score and a cringe probability in one call.
Overview
Postmark is a small web app that reads a draft social post before you publish and tells you how it might land, built as a demo of TypeSafe Jev returning structured answers instead of a paragraph. You paste up to 2,000 characters and press Vibe check; three questions run in parallel in one API call.
Vibe is a Choice over hot take, humble brag, inspirational, informative, funny and vulnerable with per-option probabilities and confidence. Viral potential is a Score on a 0-3 scale (Ignored, Mild, Solid traction, Breakout). The cringe meter is a Noul probability shown as a 'sus level'. A verdict stamp combines them: cringe at 0.6 or higher gives 'Hold up', virality at 2.2 or higher with low cringe gives 'Send it', otherwise 'Clear to post'. Four sample posts let you try it without typing. It is aimed at LinkedIn-style posts per the list summary.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What is the dominant tone? | hot take · humble brag · inspirational · informative · funny · vulnerable |
| Score | How far might this post travel? | Ignored · Mild · Solid traction · Breakout |
| Yes / no | Would a thoughtful reader wince? | yes · no |
How it works
- Paste a draft post.
- Send three questions in one Jev call.
- Combine scores into a verdict with fixed thresholds.
- Show cards and bars for each answer.
Strengths
- Clear demo of all three primitives at once.
- Simple, explainable thresholds.
- Sample posts for quick testing.
Caveats
- Demo app; judgments are subjective.
- Requires a TypeSafe key.
At a glance
- Type
- App
- Status
- prototype
- Language
- TypeScript
- Runtime
- web app
- Has code
- yes
Use cases and integrations
How curated lists describe it
A working Demo that acts as classifier to classify linkedin post which inside uses jev by Typesafe.ai.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev judge?
The post's tone, viral potential and cringe likelihood.
How is the verdict decided?
Cringe at 0.6+ says hold up; virality 2.2+ says send it; otherwise clear to post.
How many API calls per check?
One call with three parallel questions.
Related projects
Analytics engine that rates published posts on pre-registered rubrics with Jev and tests ratings against real engagement.
ProjectbetaTypeScriptChrome extension that grades readable page sections on ten rubric scores with Jev via Vercel AI Gateway and gives the page an A-E grade.
ProjectbetaTypeScriptCodex plugin that runs polls on simulated reader profiles with a System One model, recording typed answers for follow-up studies.
ProjectbetaTypeScriptExperimental editor that scores X drafts live on six viral dimensions with one Jev call, with a heuristic fallback.
ProjectprototypeTypeScriptCommunity tool that fetches a SaaS homepage as Markdown and asks Jev ten questions about first-visit clarity, with a leaderboard.
ServicebetaTypeScriptScores a page for SEO, answer engines and generative engines, using code for measurable checks and Jev rubric scores for judgment.
DemoprototypeTypeScript