Content dashboard tagging
Tag any post across topic, hook, format and style at once — the annotation behind a 1,315-post content dashboard.
Yum tagged 1,315 X posts across ~8 dimensions — topic, hook, writing style and more — for about 8.6 cents in model cost, then filtered by tag and compared engagement. What it really saves isn't writing; it's the hours of opening every post one by one to take notes.
Try it live
This is the real thing, not a mockup. Edit the input, hit Run, and Jev returns every typed answer in one round trip — free, no signup. Now picture the same call fired across thousands of items in parallel.
Pick a demo, tweak the input, and hit Run Jev.
The decisions Jev makes
In a single call, Jev evaluates each of these — in parallel, against the same input:
What is the main topic?
picks one of these options:
productivity— productivity / focusgrowth— audience or business growthai— AI / tech / buildingmindset— mindset / psychologypersonal— personal story / life
What hook style opens the post?
picks one of these options:
contrarian— challenges a common beliefquestion— opens with a questionstat— opens with a number/statstory— opens a personal storystatement— a plain declarative statement
What is the post format?
picks one of these options:
one_liner— a short punchy single ideathread— the opener of a threadlisticle— a list of tips/pointsstory— a narrative
What is the writing style?
picks one of these options:
punchy— short, high-contrast linesanalytical— explanatory / reasonedstorytelling— narrative-drivencasual— conversational
How strong is this post's engagement potential?
rates it on an ordered scale:
- weak
- average
- strong
- very strong
The exact request
This is the real payload behind the live demo — copy it, change the state, and you're building:
{
"model": "jev-latest",
"state": "X post (single, 3,100 likes):\n\n\"Most people don't have a productivity problem.\n\nThey have a 'too many open tabs in their brain' problem.\n\nWrite everything down. Your mind is for having ideas, not holding them.\"",
"questions": {
"topic": {
"type": "choice",
"instructions": "What is the main topic?",
"criteria": {
"productivity": "productivity / focus",
"growth": "audience or business growth",
"ai": "AI / tech / building",
"mindset": "mindset / psychology",
"personal": "personal story / life"
}
},
"hook_style": {
"type": "choice",
"instructions": "What hook style opens the post?",
"criteria": {
"contrarian": "challenges a common belief",
"question": "opens with a question",
"stat": "opens with a number/stat",
"story": "opens a personal story",
"statement": "a plain declarative statement"
}
},
"format": {
"type": "choice",
"instructions": "What is the post format?",
"criteria": {
"one_liner": "a short punchy single idea",
"thread": "the opener of a thread",
"listicle": "a list of tips/points",
"story": "a narrative"
}
},
"writing_style": {
"type": "choice",
"instructions": "What is the writing style?",
"criteria": {
"punchy": "short, high-contrast lines",
"analytical": "explanatory / reasoned",
"storytelling": "narrative-driven",
"casual": "conversational"
}
},
"engagement": {
"type": "score",
"instructions": "How strong is this post's engagement potential?",
"criteria": [
"weak",
"average",
"strong",
"very strong"
]
}
}
}Wire it into your code
Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.
Build your own
Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it in minutes.