Body text size
type:Smallest sampled text is 10px, below the 13px floor this check uses.
FixKeep body copy ≥15-16px; reserve sub-13px for fine print only.
01
Homepage / Lander
2 tactics
50% OFF · 1 proof point
saas · Oct 2, 2026
jev-ai.pro
We found more conversion tactics here than on 3% of the 1,331 multi-step SaaS funnels we have measured.
2 conversion tactics detected
4 pages walked · measured by Roentgen 1.28.1
How this was measured
Measured by Roentgen 1.28.1 on 2026-10-02. A capture is read once and its measurements freeze there, so the stamp says which ruleset read this one.
This is detection coverage, not a verdict — it counts the conversion tactics we could prove are present, out of the 11 that apply to a saas funnel. A low count means we did not detect those patterns, not that the funnel is weak.
Against all 1,747 multi-step funnels, more conversion tactics than 10% of them.
Walk 91 links on the entry page, 83 walkable. 3 matched a funnel step; we captured 4 pages in all, this one included.
The short version, in 5 parts
-
Proven on the page
2 conversion tactics detected, each backed by text on the page
- Answers buyer objections
What is Jev AI? What is the Jev model? What is the Jev AI platform? How does the Jev API o
- Offers a demo or docs entry point
Documentation
-
Not seen
9 of 11 applicable tactics we checked for and did not see
- Trusted-by logo wall
- Customer/company logos or a "trusted by / used by" claim.
- Free trial / freemium
- A free trial, free tier, or "no credit card" entry offer.
- Pricing tiers
- Named plan tiers with per-month / per-seat pricing.
+ 6 more
-
Flagged
3 of 12 build checks flagged, each with a fix
- Body text size
- Smallest sampled text is 10px, below the 13px floor this check uses.
- Oversized images
- 8 images are shipped at more than 2x the width shown.
- Tap-target size (mobile)
- 222 of 332 interactive targets are under 44×44px on mobile.
-
Walked
4 pages walked, Homepage / Lander to Compare
- Step 1
- Homepage / Lander
- Step 2
- Use Cases
- Step 3
- Pricing
+ 1 more step
-
In their words
The headline:
Jev AI
- Promise
Jev AI lets you try Jev, the TypeSafe System One model, in the browser. Ask yes/no, choice and score question…
What we recorded
The funnel, frame by frame
4 steps walkedsee their whole funnel without clicking through it. scored step by step
measuredextracted directly from the live page. a fact, not an opinionIn their own words
30 quotedthe entry page’s own title, headline, buttons and prices — quoted, never paraphrased
measuredextracted directly from the live page. a fact, not an opinion- Page title
Jev AI — Try the Jev Model by TypeSafe: Playground & API
- Meta description
Jev AI lets you try Jev, the TypeSafe System One model, in the browser. Ask yes/no, choice and score questions about any text and get calibrated probabilities and confidence, then call the same Jev API with your own key.
- Headline
Jev AI
- Section headings
Jev AI playground
Build with Jev AI
What is Jev AI?
Three Jev AI question types
How Jev AI works
Jev AI pricing
Jev AI FAQ
LLM as a Judge
+7 more, not shown- Buttons and links
Essential only
Allow analytics
Models
Sign in
Support ticket triage
Content moderation
Chatbot intent routing
Product review scoring
Sales lead qualification
LLM guardrail
+2 more, not shown
Sections
4 identified
structural bands identified on this funnel, cropped from its own capture
measuredextracted directly from the live page. a fact, not an opinion
What we found
2 tacticsconversion tactics we could prove are present, with the on-page text that evidences each
measuredextracted directly from the live page. a fact, not an opinionobjection1 of 2
Answers buyer objections
What is Jev AI? What is the Jev model? What is the Jev AI platform? How does the Jev API o
checkout1 of 2
Offers a demo or docs entry point
Documentation
What we didn’t find
9 of 11 applicableapplicable tactics we checked for and did not see on any step we reached
measuredextracted directly from the live page. a fact, not an opinionWhat we didn’t see9 of 11 applicable
Trusted-by logo wall
1,461 of the 2,012 funnels we checked
Free trial / freemium
1,326 of the 1,654 SaaS funnels we checked
Pricing tiers
866 of the 1,654 SaaS funnels we checked
Press / "as seen in"
629 of the 2,379 funnels we checked
Us-vs-them comparison
436 of the 2,382 funnels we checked
Lead-capture form
432 of the 1,664 funnels we checked
Proof above the fold
367 of the 2,382 funnels we checked
Usage / adoption proof
282 of the 2,012 funnels we checked
Scarcity / urgency copy
122 of the 2,379 funnels we checked
Absence is a measurement, not a recommendation: we do not know why a tactic is missing, whether it belongs here, or whether adding it would change anything. Where a walk stopped early, a tactic living deeper would also read as not detected.
How well it’s built
12 run · 3 flaggedcontrast, mobile, typography, accessibility, weight — each with what would fix it
measuredextracted directly from the live page. a fact, not an opinion3 of 11 measured checks need work1 could not be measured — not counted either way
Oversized images
weight:8 images are shipped at more than 2x the width shown.
“logo.svg” is 150px wide, displayed at 40px
FixServe responsive sizes (srcset/sizes) matching the rendered width.
Tap-target size (mobile)
mobile:222 of 332 interactive targets are under 44×44px on mobile.
smallest: “Jev AI” at 31×19px
FixGive tappable controls a ≥44×44px hit area. the touch minimum.
Worth knowing4
Line length
1 paragraph runs past ~95 characters per line.
FixCap measure at ~60-75ch for comfortable reading.
type:Link text
4 links use generic text (“click here” / “learn more”).
FixMake link text describe its destination out of context.
a11y:Render-blocking resources
5 stylesheets/scripts in <head> block first paint.
FixDefer non-critical JS (defer/async) and inline only critical CSS.
weight:Keyboard reachability
7 elements look clickable but cannot be reached by keyboard.
FixUse <button>/<a>, or add role + tabindex="0" and a key handler.
structure:Not measurable1
Page weight
At least 0.3 MB across 86 measurable resources, but 98 cross-origin resources did not expose a size. The true weight cannot be determined from the page.
weight:Clear4
Text contrast (WCAG AA) · Mobile viewport · Language declared · Image alt text
Brand kit
5 colour roles
palette by on-page usage · type rendered live
measuredextracted directly from the live page. a fact, not an opinionfull palette ordered by on-page usage %
primary#4fe0c0
accent#4fe0c0
bg#eefaf7
surface#eefaf7
text#93aba5
See the roles applied
accent
Body copy in their text role, on a surface card.
the roles, doing their job
The quick brown fox44px
Jumps over the lazy dog24px
A subheading in their voice22px
Body copy set at their measured paragraph size. This is how their product reads to a first-time visitor. same family, same scale, same weight.
- List item one, at body scale
- List item two
- List item three
Type scale, weights & families
SIZE SCALE
10pxAa
11pxAa
12pxAa
13pxAa
14pxAa
15pxAa
16pxAa
18pxAa
20pxAa
22pxAa
24pxAa
44pxAa
WEIGHTS
Aa400
Aa700
Aa750
Aa800
Aa900
FAMILIES
Space Grotesk Variable · Manrope Variable
rendered in their own type system · webfont not loaded. system fallback if uninstalled
Measured, found none
2 of 9 layerslayers we ran on this funnel that came back empty
measuredextracted directly from the live page. a fact, not an opinionElements — the atomic pieces — price anchors, ratings, guarantees — with their verbatim on-page text
Playbook match — which funnel play this page runs — measured, evidence-quoted
We ran these passes on the pages we captured and found nothing to show. That is a measurement of this funnel, not a recommendation — and it is a different statement from a layer we never ran, which does not appear here at all.
