CtrlK
BlogDocsLog inGet started
Tessl Logo

sharaf/product-experience-audit

Use when the user wants to audit a user journey, audit a signup/onboarding/checkout flow, do a UX audit, find the friction in a funnel, understand why users are dropping off or where they are being lost, or improve conversion in a web app — any diagnostic review of a multi-step, in-product flow. Use it whenever the user mentions drop-off, funnels, session replay, heatmaps, activation, time-to-value, cart or checkout abandonment, onboarding friction, or rage clicks, or wants to know where users struggle and what to fix first, even if they don't say "audit." Produces a severity-ranked, prioritized, experiment-validated improvement backlog via evidence-first intake, five parallel specialist lenses, and synthesis.

94

1.26x
Quality

100%

Does it follow best practices?

Impact

72%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

82%

36%

Onboarding Flow Audit: LoopSync B2B SaaS

Five-lens onboarding audit with journey brief and dark pattern detection

Criteria
Without context
With context

Journey brief present

25%

100%

Brief schema — 9 fields

12%

100%

Analytics marked missing

100%

100%

Five lenses addressed

37%

62%

Clean lens documented

0%

85%

Finding block template

50%

100%

Invite-step finding deduplicated

100%

100%

Dark pattern flagged for removal

100%

100%

Regulatory exposure cited

57%

100%

Falsifiable hypothesis

0%

12%

LIFT or Fogg model referenced

0%

0%

What's Working Well section

0%

100%

No analytics invented

100%

100%

53%

1%

Checkout Funnel Audit

Checkout funnel audit with absolute-volume prioritization and analytics trust caveats

Criteria
Without context
With context

Absolute volume calculation

100%

100%

Correct top-priority step

100%

100%

Instrumentation sanity check

10%

0%

Analytics data-trust caveats

0%

0%

Mobile segment isolated

100%

100%

Hidden drop-offs flagged

0%

20%

Finding blocks with all 7 fields

0%

0%

Backlog alongside finding blocks

80%

20%

Needs-research labeling

60%

100%

What's Working Well section

40%

20%

Falsifiable hypothesis present

40%

80%

81%

7%

Password-Reset Flow: Rapid Triage Report

Quick triage with ICE/PXL prioritization, no analytics

Criteria
Without context
With context

Triage scope stated

75%

62%

2-3 lenses selected

100%

12%

Lens justification present

100%

100%

Heuristic or qualitative lens included

37%

100%

9-field journey brief present

12%

37%

Missing evidence marked 'not provided'

87%

87%

ICE or PXL framework used

25%

100%

Per-factor scores shown

100%

100%

7-field finding blocks used

37%

100%

No fabricated drop-off rates

100%

87%

Magnitudes described as unmeasured

100%

100%

Treat benchmarks as directional

100%

66%

Next evidence step stated

100%

100%

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents