UX Flow Audit from Screenshots with Prioritized Fix Plan

Audits a user flow from screenshots or descriptions and returns an evidence-labeled issue table plus a fix-now, next, defer plan for a sprint decision.

You get: Decision summary, flow walkthrough table and issue register table

More like this

The prompt

ux-flow-audit-from-screenshots-with-prioritized-fix-plan.md
Role: You are a senior UX designer and design reviewer.Context: Job to be done: help {product_team} decide which usability issues in the {flow_name} flow to fix first. Decision to support: what ships in the next {timeframe} versus what is deferred.
Task: Audit the flow using only the material I provide.Constraints: Do not invent analytics, user quotes, or benchmarks. Label every inference as an assumption. If a screen is missing or unreadable, say so instead of guessing. Use WCAG 2.2 AA as the accessibility reference, and do not claim assistive-technology testing was done.

Inputs
- Product and audience: {product} / {audience}
- Flow and business goal: {flow_name} / {goal}
- Screens or written description, in order: {screens_or_description}
- Known data (drop-off, tickets, research notes): {known_data}
- Constraints (platform, dev capacity, brand rules): {constraints}
If any input is missing, ask up to 5 targeted questions first and wait for answers.

Workflow
1. Restate the job to be done and the decision. List the inputs received and list Assumptions separately.
2. Walk the flow step by step: user intent, what the screen shows, friction, and whether the evidence is Observed (in the input) or Inferred.
3. Log each issue with Severity (1-4), Reach (low/med/high), Effort (S/M/L), and Confidence (low/med/high).
4. Sort issues into Fix now, Next, and Defer, and justify the top 3.
5. For each Fix now item, propose a specific design change and one way to validate it (usability test task, metric, or A/B check).

Output format
1. Decision summary (max 5 lines)
2. Assumptions
3. Flow walkthrough table: Step | User intent | Friction | Evidence type | Issue ID
4. Issue register table: ID | Issue | Severity | Reach | Effort | Confidence | Fix
5. Prioritized plan: Fix now / Next / Defer
6. Validation plan
7. Risks and missing information
8. Next actions (owner role, due within 1 week)

Acceptance criteria
- Every issue cites a specific step or screen.
- Observed and Inferred evidence are visibly separated.
- The plan lets a team lead choose sprint scope without extra analysis.
- Each Fix now item has a concrete change and a validation method.

Quality checks
- No statistic, quote, or benchmark appears that I did not supply.
- Severity ratings are consistent across the table.
- Accessibility notes name the specific WCAG criterion when one applies.
- Missing information is listed with the question that would resolve it.

Tool notes: In ChatGPT, Claude, or Gemini, attach screenshots in order and label them Screen 1, Screen 2, and so on. Refer to screens by label. If text in an image is hard to read, state that and ask for a crop rather than guessing.

Example output

AI-written example

1. Decision summary

  • Flow: Guest checkout (mobile web), Brightleaf meal kits. Decision: what ships in the next 2 weeks.
  • Fix now: I1 (promo field), I2 (error handling), I3 (contrast).
  • Known data supplied: 41% drop-off between Screen 2 and Screen 3, and 14 tickets about "promo code" last month.
  • Screens 1-4 were all readable.

2. Assumptions

  • A1: Most users arrive with a promo code from email (inferred from the tickets).
  • A2: The 2-week sprint has one designer and two developers.

3. Flow walkthrough

StepUser intentFrictionEvidenceIssue
Screen 1: CartReview the orderNone notedObservednone
Screen 2: Contact and addressEnter details fastThe prominent promo field above the form invites leaving to hunt for a codeObserved (layout), Inferred (leaving)I1
Screen 2: SubmitFix mistakesErrors appear only at the page top, not by the fieldObservedI2
Screen 3: PaymentPay securelyGrey helper text on a white background looks low contrastObservedI3
Screen 4: ConfirmationConfirm the orderEmail-receipt notice is easy to missInferredI4

4. Issue register

IDIssueSevReachEffortConfFix
I1Promo field prominent on Screen 23HighSMedCollapse behind an "Add promo code" link
I2Errors only at top of Screen 2; WCAG 3.3.14HighMHighInline messages plus focus on the first error
I3Helper text contrast; WCAG 1.4.3 (ratio not measured)2HighSMedMeasure, then darken to at least 4.5:1
I4Receipt notice is weak1MedSLowAdd a confirmation banner

5. Prioritized plan

  • Fix now: I2, I1, I3. I2 has the highest severity and sits at the drop-off point. I1 is a cheap change tied to the ticket volume. I3 is a quick accessibility fix.
  • Next: I4.
  • Defer: Address autocomplete, which is not evidenced in the input.

6. Validation plan

  • I2: Usability test with 5 users submitting a form containing two deliberate errors. Success means both are fixed unaided.
  • I1: A/B check on the Screen 2 to Screen 3 conversion rate.
  • I3: Run a contrast checker on the final colors. No assistive-technology testing has been done.

7. Risks and missing information

  • Is the drop-off split by device? (This would show whether I2 is mobile-specific.)
  • Are there promo-code analytics? (This would confirm A1.)
  • Does the "Add promo code" link risk lowering promo redemption?

8. Next actions (within 1 week)

  • Designer: Mock up inline errors and the collapsed promo field.
  • Developer: Estimate I2 and confirm the sprint fit.
  • Product manager: Pull the device-level drop-off data.
  • QA: Run a contrast check on Screen 3.
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Attach screenshots in flow order and keep known data brief. Best for one flow at a time, such as checkout, onboarding, or account setup. Treat the output as a hypothesis list and validate top fixes with real users.

Questions about this prompt

More in Design

Design System Component Spec Writer for Figma Handoff

Produces a developer-ready component specification covering anatomy, variants, states, tokens, accessibility, and open questions from a short component brief.

UX Copy Audit: Flag Unclear Labels, Jargon and Weak CTAs with Rewrites

Audits pasted screen copy for unclear labels, jargon and weak calls to action, then returns a table with a rewrite and a one-line reason for each issue.

30-Minute Moderated Usability Test Script with Tasks and Notes Template

Produces a timed 30-minute moderated usability script with task scenarios, neutral follow-up questions and a ready-to-use notes template.

Competitor UX Pattern Research Plan with Evidence Table and Design Recommendation

Builds a source discovery plan, evidence log, citation table, and synthesis for comparing UX patterns across competitors, without claiming live browsing.

Design Brief from Client Notes with Assumptions and Next Actions

Turns a client's rough notes into a structured design brief with goals, audience, deliverables, constraints, references to gather and measurable success criteria.

Brain Dump to Weekly Plan with Top 3 Outcomes

Turns a messy brain dump into a realistic weekly plan with three outcomes, time blocks and a drop or delegate list.

Technical SEO Crawl Triage: Prioritized Fix Plan for the Next Sprint

Turn a crawl export and Search Console data into a scored, sprint-ready technical SEO fix list. It separates facts from assumptions and flags what needs verification before developers start work.

Weekly Capacity Plan with Commit, Defer, Delegate, Drop Table

Turns a messy task list, fixed commitments, and available hours into a realistic weekly plan. It also produces a trade-off table that supports the decision on what to commit to, defer, delegate, or drop.

Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

4-Week Small Business Launch Plan: $0 and Small-Budget Versions

Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.

60-Minute Lesson Plan with Checks for Understanding and Differentiation

Builds a timed, objective-aligned lesson plan with formative checks, differentiation, and a teach-or-revise readiness verdict. It asks for missing inputs first and keeps assumptions separate.

90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.