SUMMARY
Purpose: Retesting Criteria is a method used to validate whether design changes, iterations, or fixes—based on earlier test findings—are actually successful in improving the user experience.
Design Thinking Phase: Test
Time: 45–60 min session + 1–2 hours analysis
Difficulty: ⭐⭐
When to use:After updates to a prototype based on usability testing feedbackTo validate fixes addressing previously identified usability flawsWhen deciding whether a new design is ready for launch or further iteration
What it is
Retesting Criteria refers to a structured approach to validating whether specific changes to a design solution have alleviated previous usability issues. Instead of general testing, it focuses on pre-identified pain points and how updated flows now perform under real user behaviour.
📺 Video by Ask UX . Embedded for educational reference.
Why it matters
While usability testing uncovers friction, gaps, and user frustration, Retesting Criteria helps teams confidently assess whether changes made from those learnings are solving the core issues. It transitions feedback into measurable product improvements. Without this step, you risk shipping incremental UX fixes that don’t deliver real value.
When to use
- After a design or feature iteration informed by usability testing
- Prior to handoff or implementation freeze
- When prioritising feature refinements based on impact
Benefits
- Rich Insights: Helps uncover user needs that aren’t visible in metrics.
- Flexibility: Works across various project types and timelines.
- User Empathy: Deepens understanding of behaviours and motivations.
How to use it
- Before testing, revisit previous usability findings and identify the problems addressed in the next iteration.
- Form test objectives that directly assess those problem areas (e.g., "Can users now successfully complete the X task without needing help?").
- Select participants similar to the original test group for behavioural consistency.
- Run moderated or unmoderated sessions focusing on real tasks tied to previous issues.
- Compare qualitative and quantitative changes (task completion, error rate, confidence score).
- Synthesise results into “met”, “partially met”, or “unmet” criteria for clear next steps.
Example Output
Iteration: Mobile checkout redesign to fix drop-off at shipping screen
Retest Objectives:
- Can users now add a shipping address without confusion or guidance?
- Is the error message properly triggered on incorrect postcode input?
Result:
- ✅ 6/6 participants successfully completed the flow without prompts.
- ⚠️ 2 participants failed to notice postcode autofill toggle.
- Recommendation: Make the toggle state clearer and auto-scroll into view on error trigger.
Common Pitfalls
- Retesting everything: Not everything needs retesting — keep focus on changed areas or key breakpoints.
- Losing continuity: If you don’t document earlier problem areas clearly, linking findings to outcomes becomes guesswork.
- Subjective criteria: Success measures must be concrete (task completion, error rate) to track gains effectively.
10 Design-Ready AI Prompts for Retesting Criteria – UX/UI Edition
How These Prompts Work (C.S.I.R. Framework)
Each of the templates below follows the C.S.I.R. method — a proven structure for writing clear, effective prompts that get better results from ChatGPT, Claude, Copilot, or any other LLM.
C.S.I.R. stands for:
- Context: Who you are and the UX situation you're working in
- Specific Info: Key design inputs, tasks, or constraints the AI should consider
- Intent: What you want the AI to help you achieve
- Response Format: The structure or format you want the AI to return (e.g. checklist, table, journey map)
Level up your career with smarter AI prompts.Get templates used by UX leaders — no guesswork, just results.Design faster, research smarter, and ship with confidence.First one’s free. Unlock all 10 by becoming a member.
Prompt Template 1: “Define Retesting Success Criteria Based on Previous Test Insights”
Define Retesting Success Criteria Based on Previous Test Insights
Context: You are a Lead UX Researcher preparing a follow-up usability test after a navigation redesign.
Specific Info: The prior round revealed confusion around icon labels and unexpected drop-off during onboarding. Changes have since been implemented.
Intent: Identify what “success” looks like for each issue, based on user behaviour, not opinion.
Response Format: Generate a table with three columns — Previous Issue, Testable Success Criteria, Validation Method.
If any prior issue appears ambiguous, flag it and ask for clarification.
Then, suggest one follow-up metric to capture improvement over time.
Prompt Template 2: “Generate Moderated Test Plan Focused on Iteration Impact”
Generate Moderated Test Plan Focused on Iteration Impact
Context: You are a UX Strategist preparing a targeted usability session to assess updates made to a price comparison feature.
Specific Info: The changes include UI grouping, tooltip improvements, and a new sticky summary bar.
Intent: Build a test guide that sharpens focus on validating these feature changes against prior user confusions.
Response Format: Provide a session outline detailing tasks, questions, timing, and observable behaviours for each iteration area.
Include one follow-up scenario that might emerge if new usability issues arise.
Prompt Template 3: “Compare First-Round and Retest Findings”
Compare First-Round and Retest Findings
Context: You are a Senior Designer completing a usability retrospective for a redesigned login experience.
Specific Info: You ran two testing rounds—initial and follow-up—with 5 participants each and minor variation in conditions.
Intent: Identify what changed, what remained difficult, and which new issues appeared unexpectedly.
Response Format: Produce a comparison table with Issue Description, Initial Observation, Retest Finding, Suggested Next Step.
Highlight any patterns suggesting deeper system-level UX flaws.
Prompt Template 4: “Create a Retesting Scorecard for Task Performance”
Create a Retesting Scorecard for Task Performance
Context: You’re a UX Lead facilitating a workshop to analyse recent iterative tests before releasing new account settings UI.
Specific Info: Tasks involve changing notification preferences, updating payment info, and toggling privacy settings.
Intent: Create a shared scorecard that enables product stakeholders to rate usability success across tasks.
Response Format: Provide a scorecard template with columns for Task, Success Rating (1–5), Observed Issues, and Confidence Level.
Suggest one method to engage stakeholders during the workshop in discussing tradeoffs.
Prompt Template 5: “Identify Red Flags That Still Exist After Iteration”
Identify Red Flags That Still Exist After Iteration
Context: You're a UX Researcher analysing post-iteration results of a checkout redesign.
Specific Info: The redesign was based on usability friction at the shipping and payment steps.
Intent: Spot which issues were only partially resolved or have shifted elsewhere.
Response Format: List unresolved issues, severity, and potential cause hypotheses to investigate next.
Add one clarifying question that would help refine those hypotheses.
Prompt Template 6: “Draft Stakeholder-Ready Summary of Retest Results”
Draft Stakeholder-Ready Summary of Retest Results
Context: You are a Product Designer preparing a slide deck for an exec walkthrough.
Specific Info: You ran a 5-person retest, targeting onboarding friction addressed in V2 prototype.
Intent: Communicate what was fixed, what’s improved, and what still needs triage.
Response Format: Return a structured summary with sections for Context, Findings, Key Wins, and Open Concerns.
Include one slide title suggestion that grabs stakeholder interest.
Prompt Template 7: “Map Retest Outcomes to Future Sprint Priorities”
Map Retest Outcomes to Future Sprint Priorities
Context: You’re a Design Lead in sprint planning with product and eng.
Specific Info: Retesting flagged a few minor UX regressions and one blocker in mobile responsiveness.
Intent: Help prioritise adjustments for the next sprint with clarity on urgency.
Response Format: Return a prioritised backlog list with issue, impact, effort estimate, and sprint recommendation.
Challenge team assumptions if anything is deprioritised without evidence.
Prompt Template 8: “Translate Retest Learnings into Accessibility Improvements”
Translate Retest Learnings into Accessibility Improvements
Context: You’re an Accessibility Designer reviewing what came out of usability retests on a dashboard tool.
Specific Info: Improvements targeted keyboard nav and screen reader flow in admin section.
Intent: Convert observed pain points into actionable a11y fixes.
Response Format: Provide a list of changes grouped by WCAG guideline, with user quote or session evidence for each.
Suggest one retroactive check to confirm fix readiness.
Prompt Template 9: “Identify Research Gaps Exposed Through Retesting”
Identify Research Gaps Exposed Through Retesting
Context: You’re a UX Research Ops lead reviewing logs of two testing cycles for a multi-device app.
Specific Info: Some user types were missed in round one and tested only in the retest.
Intent: Clarify what we still don’t know and how to close those insight gaps.
Response Format: Return a list of lingering questions, blind spots, and quick-win research methods to fill them.
Offer one suggestion to balance insight depth with speed.
Prompt Template 10: “Co-write a Test Summary for Design QA Handoff”
Co-write a Test Summary for Design QA Handoff
Context: You’re a UX Designer preparing documentation for a handoff to QA engineers validating component changes.
Specific Info: You ran retests focused on user-defined filtering controls and overflow states.
Intent: Ensure smooth QA by clearly documenting what was tested, results, and visual/design requirements.
Response Format: Provide a handoff checklist covering tested behaviours, bug flags, and design fidelity expectations.
Add a reminder to link relevant test recordings or Figma comments when needed.
Recommended Tools
- Maze: Great for unmoderated iteration testing with score-based metrics
- Lookback: Lets you compare sessions side-by-side for pre/post iteration review
- Notably: Excellent for synthesising qualitative insights per iteration round
- FigJam + Plugins: To facilitate retest scoring and team prioritisation workshops
- ChatGPT / Claude / Perplexity: Turn transcripts and notes into structured next steps using prompt templates above
