{"id":"pm-accessibility-audit-summary","audience":"product-managers","category":"summarizing","track":"productivity","technique":"format","title":"Summarize an accessibility audit in three labeled lines","free":false,"task":"Your director wants a quick read on the accessibility audit. Write exactly 3 lines labeled Still failing:, Fixed:, and Next:, each with counts from the audit, plain text, under 70 words. Use the re-test results, and don't add technical jargon or fixes the team didn't commit to.","materialLabel":"Audit notes (attached to your prompt automatically)","material":"Accessibility audit - Fieldnote web app (outside auditor, Sept)\n\nFindings: 12 issues total.\n- 5 color contrast issues on buttons and labels.\n- 4 images without text descriptions.\n- 2 forms where errors are shown by color only.\n- 1 keyboard trap in the date picker (can't tab out).\n\nRe-test (Oct 8, after sprint 31):\n- Contrast: all 5 fixed.\n- Images: 3 of 4 fixed (1 left, the onboarding illustration).\n- Forms: 0 of 2 fixed.\n- Keyboard trap: fixed.\nSo: 9 fixed, 3 still failing.\n\nCommitted next (sprint 32, ends Oct 24): fix both color-only form errors and the last image description.\nIdea, NOT committed: full screen reader audit next year.\n\nDirector's ask: \"Counts and what's next. No jargon, I'm forwarding it.\"","rules":[{"type":"maxWords","max":70},{"type":"plainText"}],"mistakes":[{"title":"Asking to 'summarize the audit'","why":"The AI writes a report with headings, standards codes and every finding.","fix":"Show the shape: \"3 lines labeled Still failing:, Fixed:, Next:. Plain text.\"","checks":["r0","plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total word limit and it often lands over it.","fix":"Cap each line instead: \"each line under 20 words.\"","checks":["maxWords"]},{"title":"Using the original findings","why":"The first list shows 12 open issues, and the re-test is below it.","fix":"Add: \"Use the Oct 8 re-test: 9 fixed, 3 still failing.\"","checks":["r1"]},{"title":"Jargon and extras","why":"The AI adds WCAG codes and suggests a full audit.","fix":"Add: \"Plain words, no jargon. Only committed next steps.\"","checks":["r2"]}],"promptHints":[{"label":"Shows the labels","patterns":["still failing","fixed:","next:"]},{"label":"Uses the re-test","patterns":["re.?test","oct(ober)? 8","9 fixed"]},{"label":"Bans jargon","patterns":["jargon","wcag","plain words"]},{"label":"Only committed work","patterns":["committed","screen reader","not committed"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)"]}],"hint":"Directors forward summaries, so they must be current and jargon-free. Give the AI the three labels, the re-test numbers, and what's committed.","rubricLabels":["Has exactly 3 lines labeled Still failing:, Fixed: and Next:, in that order","Still failing gives 3 of 12 (2 color-only form errors and 1 image description); Fixed gives 9 of 12 (contrast, 3 images, keyboard trap); Next is fixing the 2 form errors and the last image in sprint 32, ending Oct 24","Mentions no uncommitted work (no screen reader audit) and avoids standards jargon like WCAG, alt text or ARIA (plain words like 'image descriptions' or 'keyboard trap' are fine)"]}