unvibed.
Menu
Free UI audit

Agent-built demo / After audit

Settleline

Fintech · Nov 8, 2026

Overall gradeADesign grade after deductions

3 measured views. Local app. Design grades compare the actual screen with published product references. N/A means there was no applicable sample. Unverified means evidence was insufficient.

Product specificity and generic signals · A

Both widths identify a concrete reconciliation task through Morrow Foods, TX-091, BNK-407, $1,840.00 and Match deposit. The unmatched count and row status make the outstanding decision recognizable immediately. (/)

Visual specificity before deductions A. Weighted design base A. Distinct signal deductions 0.

Product specificity supplies 55% of the base, and the five visual design dimensions share 45%. Round the base to the nearest letter. Each distinct verified generic signal lowers it by one letter, down to F. Foundations are reported separately. The detector ceiling is A. Vision reviewed 1 of 1 measured routes.

Template copy · not observed
No instance was identified in the reviewed views.
Gradient hero · not observed
No instance was identified in the reviewed views.
Emoji bullets · not observed
No instance was identified in the reviewed views.
Default shadcn grays · not observed
No instance was identified in the reviewed views.
Purple on white · not observed
No instance was identified in the reviewed views.
Centered everything · not observed
No instance was identified in the reviewed views.

Compared with the 2026 references

  • / · Like fintech-1, both captures use compact dated records, aligned amounts and rightmost statuses to support financial scanning. Here, the comparison panel adds an explicit matching decision; repeating TX-091’s amount beside its reference would reduce the need to consult the ledger. Actual Budget · account register

Visual design

Hierarchy
A
At 1440, heading, totals, review panel and ledger form a clear sequence. At 390, totals move below the heading while the review action still precedes the ledger. The blue button remains the dominant control. (/)
Typography
B
Both widths distinguish heavy headings, monospaced identifiers and quieter metadata. At 390, the condensed review heading is visually dense, though readable; amounts and statuses retain clear emphasis. (/)
Spacing
A
At 1440, panel padding and ledger rules separate the comparison and records cleanly. At 390, consistent side margins preserve the two-column comparison, button and three readable ledger rows without visible overflow. (/)
Copy and labels
B
Both widths use concrete labels including Bank deposit, Incoming reference and Match deposit. “Review one payment” is less informative than naming Morrow Foods, and the incoming amount requires looking down to its ledger row. (/)
Imagery
B
The small converging-line illustration stays subordinate at 1440 and 390 and fits the reconciliation context. It supplies little decision evidence; the identifiers, amounts and statuses carry the task. (/)

Foundations · B

Contrast, responsive layout and keyboard reach are sampled separately. The foundations grade is the lowest verified result in this group.

Color contrast
A
At least four opaque text samples per view passed the contrast threshold. Verified across 3 measured views.
Responsive layout
A
All sampled viewports fit without horizontal overflow and contained readable text. Verified across 3 measured views.
Keyboard access
B
Checked 3 Tab probes reaching a visible target across the captured views. No issue detected by this check.

Fix these first

No repair could be verified from these views.

Evidence from the screens

Gray blocks conceal form values or sensitive text. Numbered outlines identify measured issues.

Captured / at 390 pixels wide
/ · 390 × 844

No issue was detected in this view.

Captured / at 1440 pixels wide
/ · 1440 × 900

No issue was detected in this view.

Captured / at 768 pixels wide
/ · 768 × 1024

No issue was detected in this view.

Independent task review

The reviewer assesses each route against its user task using desktop and phone evidence. Its task grades describe the interaction evidence available for that route.

/

The audited interface is SettleFine’s working settlement desk at /. Review Morrow Foods payment TX-091 against bank deposit BNK-407 for $1,840.00, then choose “Match deposit.”

Reviewed at 1440 × 900 and 390 × 844.

Task hierarchy
A
At 1440, the review panel and blue Match deposit button precede the payment list. At 390, the same order remains clear, with TX-091, BNK-407 and the action visible. The unmatched row identifies the record requiring attention.
Landing message
N/A
This is an internal settlement workspace, not a public product landing page.
Interaction feedback
Unverified
Both images show Awaiting match and one unmatched payment. Supplied checks do not record button activation or its outcome, so success feedback, persistence and retry behavior remain unverified.
Access and recovery
B
At both widths, the supplied Tab check reached a visible focus target. At 390, the action and all three payment rows fit without visible clipping. Keyboard activation, focus appearance and recovery paths were not demonstrated.
Release evidence
Unverified
The supplied local renders establish the opening layout at 1440 × 900 and 390 × 844; checks establish one primary heading, one visible control and a reachable focus target per width. Matching behavior and deployed operation were not observed.

First action

Record activation of Match deposit for TX-091 at both supplied widths. This is the first missing observation needed to establish whether the main task completes.

How to verify At 1440 and 390, focus and activate Match deposit. Confirm that TX-091 becomes matched, the unmatched count changes from 1 to 0, and a clear result appears. Reload to check persistence. Separately measure contrast and exercise failure recovery; neither is established by these captures.

What a repair could look like

Settleline is an agent-built fintech settlements demo. Both captures show the same task.

Settleline before the rebuild
Before
Settleline after the rebuild
After
Compare Settleline at both widths →