Answer a workplace question with data
Calculating a percentage is easy—how do you state the denominator and scope honestly?
Saying “75% were satisfied” can mislead if the denominator is hidden: is it the target headcount, actual attendees, or returned surveys? Answering with data means stating denominators, picking honest charts, and bounding your claims.
Answering “Is 9 people high?”: show the 9/12 survey denominator and choose a clear bar breakdown
Left: clear bar funnel from Target (20) to Returned Surveys (12) and Yes (9 = 75%). Right: misleading pie mixing denominators and budget.
Use 12 Returned Surveys + State 15 Attended & 3 Unreturned
Avoids diluting against the 20 target or hiding the 3 unreturned questionnaires.
Same-Unit Bars: Target 20 · Present 15 · Returned 12 · Yes 9
Shows every funnel step in the same unit (people) so 75% is immediately grounded.
Never Mix Headcount and CNY 2,000 Budget Cap in One Pie
People and currency cannot share a pie; do not extrapolate to the whole company.
The method: three small steps
In this scenario: target attendance is 20, actual attendance is 15, and 12 surveys were returned, with 9 wanting a follow-up session. The 75% figure is 9 of 12 respondents (or 9 of 15 attendees, with 3 unreturned). Claiming “75% of the whole company wants another session” oversteps the evidence.
Write the numerator, denominator, and non-respondents together
Write “9 of 12 returned surveys (75%) want a next session; 3 of the 15 attendees did not submit feedback.” With small numbers, showing the raw fraction is clearer than a bare percentage.
Pick a simple chart that shows the breakdown
Use a simple bar chart comparing target (20), attendance (15), surveys returned (12), and positive intent (9). Never plot a budget cap as an actual spending pie chart.
State what the data supports and what remains unknown
The data supports positive interest among survey respondents, while the views of non-respondents and actual spending remain unknown.
WORKED EXAMPLE
See how to improve a result
Prepared example: state denominators and bound your claims
The requests and responses are prepared teaching examples, not live model output.
Read the example sources
Source A · Event notice
The team exchange event is scheduled for November 6, 14:00–16:00, in the third-floor meeting room. Sign up by November 3, 18:00. The target is 20 attendees; actual registrations have not yet been counted. No registration method, link, or event contact is provided.
Source B · Budget and equipment
The budget cap is CNY 2,000. No actual spending has been recorded. A projector is available in the meeting room.
Source C · Preparation notes
Catering and remote access are unconfirmed. Lin will organize the agenda before November 2; Zhou will confirm the attendee list before November 3. The photography owner and deadline remain unconfirmed.
The request
From 15 attendees, 12 returned surveys, and 9 wanting a next session, write a punchy takeaway.
Example response
A full 75% of team members strongly demand a follow-up session at just CNY 133 per person—a huge success!
What to noticeThis is a prepared problem example. It hides the 12-survey denominator, extrapolates 9 people to the whole team, and divides the CNY 2,000 budget cap as if it were actual spend.
Your turn: what would you ask next?
Try it yourself with different material
Try another dataset: evaluate a knowledge-base pilot
Copy the material and task into your usual tool to practice. Then review your work against the checks.
Material
Fictional data: 30 team members total; 20 visited the knowledge base during the pilot week; 10 submitted feedback (7 said “easier to find than before,” 3 said “search is still slow”); 10 visitors submitted no form, and 10 did not visit.
Task
Write a feedback summary with explicit fractions, a recommended chart type, and the scope boundary.
Review your work
- State 7/10 among feedback forms (or 7/20 visitors) found it easier, while 3/10 reported slow search.
- Note that 10 visitors did not submit feedback and 10 team members did not visit.
- Recommend a simple bar breakdown showing total team (30), visitors (20), respondents (10), and feedback split.
Check the denominator, chart type, and conclusion scope for the post-event feedback data in the workspace, then write a bounded interpretation.
These materials describe a fictional event. No AI model is called. Selections are checked against explicit rules; you review your own writing against the sources.
Read the original exercise materials
The team exchange event is scheduled for November 6, 14:00–16:00, in the third-floor meeting room. Sign up by November 3, 18:00. The target is 20 attendees; actual registrations have not yet been counted. No registration method, link, or event contact is provided.
The budget cap is CNY 2,000. No actual spending has been recorded. A projector is available in the meeting room.
Catering and remote access are unconfirmed. Lin will organize the agenda before November 2; Zhou will confirm the attendee list before November 3. The photography owner and deadline remain unconfirmed.
State denominators and bound your data claims
Target attendance: 20 | Actual attendance: 15 | Returned surveys: 12 (9 “would join next session,” 3 “depends on topic”; 3 attendees did not submit) | Budget cap: CNY 2,000 (actual spend unrecorded).
Take your work with you
Drafts stay only on this page and are not restored after refreshing or leaving. Copy or download what you want to keep. Switching language does not delete your writing.
Always pair percentages with their numerator and denominator, and never extrapolate a small sample to everyone.
Try it in your own AI tool
- Open an AI chat tool you already have access to, start a new conversation, and paste the complete task sheet into its input box before sending. Use only the fictional text here; no work files, passwords, or personal details are needed.
- Check whether AI calculated “CNY 2,000 ÷ 15 = CNY 133 actual cost per person.” If so, remind it that CNY 2,000 is a cap, not actual spend.
- Verify that every percentage includes its fraction and base, such as “(9/12 returned surveys).”
- Save this “Fraction + Chart Choice + Scope Boundary” format for weekly updates and retrospectives.
Complete the checks above to record your progress. This records example practice; try a different task independently to test your skill.
Explanations, cases, and exercises are authored by Reallier. Links provide further learning. The workplace activity and people are fictional.