saas · Aug 15, 2026
70/100 Partial
Scores higher than 82% of 1,391 multi-step funnels we have measured. Among the 1,074 saas funnels in that group, higher than 78%.
Measured by Roentgen 1.25.1 on 2026-08-15. A capture is read once and its measurements freeze there, so the stamp says which ruleset read this one.
Coverage 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. Per device: desktop 70 · mobile 70.
Walk 53 links on the entry page, 28 walkable. 2 matched a funnel step; we captured 3 pages in all, this one included.
this funnel’s coverage score across measured re-scans
measuredextracted directly from the live page. a fact, not an opinionsee their whole funnel without clicking through it. scored step by step
measuredextracted directly from the live page. a fact, not an opinionthe entry page’s own title, headline, buttons and prices — quoted, never paraphrased
measuredextracted directly from the live page. a fact, not an opinionAI Agent Memory + Skills API — AgentPrizm
Governed memory, reusable AgentSkills, and audit receipts for AI agents. REST API + MCP. Built for agents that need persistent recall, skill reuse, and trust.
Agent memory you can audit.
Stateless agents are expensive amnesiacs.
What changes when your agent remembers?
Wire trusted memory into your agent in an afternoon.
Memory, not just retrieval.
One memory layer. Two ways in.
Now your agents share skills, not just memory.
Built for agents in high-stakes work.
Honest where it matters.+8 more, not shown
Start building free
Try it live — no signup →
Browse the marketplace →
How AgentSkills works
Start free
Start building
Contact sales
How is this different from a vector database? +
What does it take to integrate? +
How do fact-validity windows work? ++2 more, not shown
$0
$16
$66
$208
structural bands identified on this funnel, cropped from its own capture
measuredextracted directly from the live page. a fact, not an opinion
the atomic pieces — price anchors, ratings, guarantees — with their verbatim on-page text
measuredextracted directly from the live page. a fact, not an opinion
conversion tactics we could prove are present, with the on-page text that evidences each
measuredextracted directly from the live page. a fact, not an opinionfree, $19/mo, $79/mo, $249/mo
free trial
name, email, password
Read the docs
logo wall (5 distinct marks)
comparison grid: 8 rows
applicable tactics we checked for and did not see on any step we reached
measuredextracted directly from the live page. a fact, not an opinionAbsence 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.
contrast, mobile, typography, accessibility, weight — each with what would fix it
measuredextracted directly from the live page. a fact, not an opinion4 of 13 measured checks need work1 could not be measured — not counted either way
Smallest body text is 11px (base ~19px). below the ~16px readable floor.
FixKeep body copy ≥15-16px; reserve sub-13px for fine print only.
10 stylesheets/scripts in <head> block first paint.
FixDefer non-critical JS (defer/async) and inline only critical CSS.
No <main> or <header> or <footer> landmark. screen-reader users cannot jump between regions.
FixWrap the page in <header>, <main> and <footer> (or matching ARIA roles).
95 of 128 interactive targets are under 44×44px on mobile.
smallest: “Home” at 32×17px
FixGive tappable controls a ≥44×44px hit area. the touch minimum.
2 paragraphs run past ~95 characters per line.
FixCap measure at ~60-75ch for comfortable reading.
type:3 headings skip a level (e.g. <h2> followed by <h4>). Screen-reader users navigate by this outline.
FixStep heading levels one at a time; use CSS for size, not a deeper level.
a11y:3 controls have an aria-label that does not contain its visible text, so voice-control users cannot activate it by saying what they see.
FixMake the accessible name start with the visible label text.
a11y:3 images are shipped at more than 2x the width shown.
FixServe responsive sizes (srcset/sizes) matching the rendered width.
weight:At least 1.6 MB across 179 measurable resources, but 65 cross-origin resources did not expose a size. The true weight cannot be determined from the page.
weight:Text contrast (WCAG AA) · Mobile viewport · Language declared · Image alt text · Inline validation
palette by on-page usage · type rendered live
measuredextracted directly from the live page. a fact, not an opinionBody copy in their text role, on a surface card.
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.
layers we ran on this funnel that came back empty
measuredextracted directly from the live page. a fact, not an opinionPlaybook match — which funnel play this page runs — measured, evidence-quoted
We ran this pass 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.
