JEVVIS.OSyour ultimate commander

How matching works

Jevvis does not score a new coin or guess whether it will go up. The same Jev questions are asked of both sides: the creator's from his own posts, the coin's from its launch material read as one package, and then each question is compared. Every creator × coin pair stands alone; creators are not ranked against each other. An example first, then the rules; details come last.

At a glance

  1. A coin launchesIts name, ticker, pitch and optional fields, plus the launcher's X bio and posts, are read as one package.
  2. Same questions, both sidesJev asks the package the questions each creator's posts were asked, word for word; an answer Jev is unsure of counts as can't tell.
  3. One verdict per questionThe coin's answer against his share: alike, unlike, neither has it, or can't tell.
  4. A similarity per cardAlike ÷ (alike + unlike), on each of the four cards.
  5. One overallThe cards weighted 5/15/30/50; a card that can't be told drops out. Coverage under 50% → can't tell.
  6. Your thresholdStrict ≥ 75% · Standard ≥ 60% · Loose ≥ 50%; enough creators pass → you are notified.

Example: Sam and three new coins

Of Sam's 100 posts, 30% are jokes; of his 40 coin posts, 35% are about Animal mascot coins, 25% give “Lore” as the reason, and only 3% bring up “Tech depth”. Each new coin is compared with these numbers question by question; the four cards are weighted into one overall with the default weights (5/15/30/50).

example.run
  1. Sam's numbers Counted from his own posts: how often each thing shows up. ≥ 10% counts as often, < 5% as almost never.
  2. Each coin answers Jev reads each coin with the same questions; every answer is checked against his number.
  3. Card similarity Per card: alike ÷ (alike + unlike). Neither-has-it and can't-tell stay out of the count.
  4. Weighted overall Cards weighted 5/15/30/50. Cards that can't be told drop out; the counted cards' weight is the coverage.
  5. Thresholds The overall against Strict 75%, Standard 60% and Loose 50%.
Question by question, for the three coins
QuestionCoin ACoin BCoin C
Base profile · weight 5%
Content depthLow 10%, Mid 60%, High 30% (100 posts)Coin A: Mid band → AlikeCoin B: Mid band → AlikeCoin C: Not read → Can't tell
Similarity100%100%Can't tell
Personality · weight 15%
Brags about gains2% (2 of 100 posts)Coin A: No (Jev 10%) → Neither has itCoin B: No (Jev 10%) → Neither has itCoin C: Not read → Can't tell
Attacks people12% (12 of 100 posts)Coin A: No (Jev 10%) → Unlike · lacks what he usually wantsCoin B: Yes (Jev 90%) → AlikeCoin C: Not read → Can't tell
Similarity0%100%Can't tell
Posting · weight 30%
Humor30% (30 of 100 posts)Coin A: Yes (Jev 90%) → AlikeCoin B: No (Jev 10%) → Unlike · lacks what he usually wantsCoin C: Not read → Can't tell
Style mixMeme 50%, Commentary 40%, News 10% (100 posts)Coin A: Meme → AlikeCoin B: Commentary → AlikeCoin C: Not read → Can't tell
Similarity100%50%Can't tell
Coin picking · weight 50%
Theme: Animal mascot35% (14 of 40 posts)Coin A: Yes (Jev 90%) → AlikeCoin B: Yes (Jev 90%) → AlikeCoin C: Yes (Jev 90%) → Alike
Lore25% (10 of 40 posts)Coin A: Yes (Jev 90%) → AlikeCoin B: No (Jev 10%) → Unlike · lacks what he usually wantsCoin C: No (Jev 10%) → Unlike · lacks what he usually wants
Tech depth3% (1 of 40 posts)Coin A: No (Jev 10%) → Neither has itCoin B: Yes (Jev 90%) → Unlike · he stays away from itCoin C: Not read → Can't tell
SectorsMemecoins 75%, AI 15%, DeFi 10% (40 posts)Coin A: Memecoins → AlikeCoin B: Memecoins → AlikeCoin C: Memecoins → Alike
Similarity100%50%66.7%

Coin A

An animal coin with a story; the launcher's posts joke a lot and never pick fights

Alike 6 · Unlike 1 · Can't tell 0 · Neither 2 (9 in all) · overall 85%

Cards counted: coverage 100%Overall 85%
  • Strict ✓
  • Standard ✓
  • Loose ✓

Coin B

An animal coin with no story that leads with tech; the launcher's posts don't joke but do pick fights

Alike 5 · Unlike 3 · Can't tell 0 · Neither 1 (9 in all) · overall 60%

Cards counted: coverage 100%Overall 60%
  • Strict ✗
  • Standard ✓
  • Loose ✓

Coin C

An animal coin with only a name and pitch, and no launcher X account

Alike 2 · Unlike 1 · Can't tell 6 · Neither 0 (9 in all) · overall 66.7%

Cards counted: coverage 50%Overall 66.7%
  • Strict ✗
  • Standard ✓
  • Loose ✓

B is unlike on two cards, so its overall only reaches 60%: Standard, not Strict. C has no launcher account, so only the coin-picking card can be told; the other three drop out and the weight is re-spread (coverage 50%), just enough. Any less coverage and the overall reads can't tell, passing nothing.

The rules: the same questions, compared one by one

Yes/no questions: how often he has it
  1. < 5%almost never
  2. 5–10%in between
  3. ≥ 10%often
He has it…Coin has itCoin doesn't
often (≥ 10%)AlikeUnlike · lacks what he usually wants
almost never (< 5%)Unlike · he stays away from itNeither has it
in betweenCan't tellCan't tell
One-choice questions: how much of his mix the coin's answer takes
  1. < 5%Unlike
  2. 5–20%Can't tell
  3. ≥ 20%Alike
Card similarity

Similarity = alike ÷ (alike + unlike)

E.g. Coin B, Posting: 1 ÷ (1 + 1) = 50%

Default weights (each group can set its own)
  • Base profile 5%
  • Personality 15%
  • Posting 30%
  • Coin picking 50%

The counted cards must weigh at least 50% in all (coverage).

⚠️ Every threshold is provisional, waiting for calibration (yes/no 10% / 5%, one-choice 20% / 5%, coverage 50%, tiers 75% / 60% / 50%): the numbers will change, and this page follows the same spec file.

The rules in full

The same questions: on the creator's side each of his posts is asked once and counted into the four cards' shares, distributions and score bands; on the coin's side the coin's name, ticker, pitch and optional fields, plus the launcher's X bio and posts, go to Jev as one package — same questions, same options, word for word, with the subject changed to “this launch”.

No post is cut short: only when the package is too long are posts dropped, fewest likes + reposts + replies + quotes first, and the coin page says how many. The coin's own fields are never dropped. An answer Jev is unsure of (no option clearly ahead, or a score pulled both ways) counts as can't tell.

A yes/no question looks at his share: he often has it (≥ 10%) and so does the coin → alike; he often has it and the coin doesn't → unlike (lacks what he usually wants); he almost never has it (< 5%) and the coin does → unlike (he stays away from it); neither has it → listed, not scored; in between → can't tell.

A one-choice question looks at how much of his distribution the coin's answer takes: ≥ 20% alike, < 5% unlike, in between can't tell; his “none” is left out of the count, and a coin answering “none” is can't tell. A 0–3 score question is cut into low / mid / high and compared as a three-way choice. The account question (bot-like) uses 50% as its yes line.

Each card: similarity = alike ÷ (alike + unlike). Can't tell and neither-has-it stay out of the count but are always listed; a card with nothing comparable can't be told.

The overall = the four cards weighted (default 5/15/30/50; each subscriber group sets its own with sliders, always adding up to 100). Cards that can't be told, or weigh 0, drop out and the rest are re-spread by their weights. The comparable cards' weights add up to the coverage; under 50% the overall reads can't tell, so one lightly weighted card never stands for the whole.

Not compared: subject over time, following up on calls, posting rhythm, titles, token-talk share, coins called, repeat calls, chain, launchpad (they need a long record, or are the same for every coin); the five personality factors are sums of the markers and are shown, not counted twice. Market-cap range, followers, likes / reposts / replies / quotes are shown only. Five questions — main field, topic field, sentiment, conviction, falsifiable — are asked and listed with both sides and the verdict, but not scored: creators in the same field answer them almost alike, and the self-identification backtest showed they only raise everyone's similarity together.

Three thresholds

When you set up a group you pick one, which decides how high a creator's overall similarity must be to pass; then how many of the group's creators must pass before you are notified.

Where the example coins land
Strict ≥ 75%Passes: Coin A
Standard ≥ 60%Passes: Coin A, Coin B, Coin C
Loose ≥ 50%Passes: Coin A, Coin B, Coin C

A 85% · B 60% · C 66.7%

Strict
Overall similarity ≥ 75%
E.g. Sam at 80% overall → passes; 70% → does not
Standard
Overall similarity ≥ 60%
E.g. Sam at 65% overall → passes; 55% → does not
Loose
Overall similarity ≥ 50%
E.g. Sam at 55% overall → passes; 45% → does not

Every question links back to the source

Every question carries evidence from both sides: his posts read as “yes” (each opens the post on x.com), and which parts of this coin Jev read (the coin, the launcher's bio, the launcher's posts). Only what was there at launch is read — never later prices or chatter — so the outcome cannot leak into the reading.

What the four cards measure

The comparison profile comes from the analysis cards — counted from the same readings, with no new Jev call; a trait has the same name on the card, the creator page and the coin page.

The four cards always run together and are not sold separately. The three ways to run them differ only in how many posts are read and the price:

For programs

The API and webhooks carry the same numbers:

Full reference: API docs →

Limits