Working prompts you can use immediately
Your AI Prompt Portfolio
What AI is: patterns from data
You can work with AI TODAY
Changes your meaning completely
Amazon suggests stuff you don't want
Chatbot gives completely wrong answers
AI produces nonsensical output
A hospital deployed an AI system to predict which patients needed intensive care. The AI failed dangerously.
Why? The training data had a critical flaw: It only included patients who had already been admitted to the ICU.
The AI learned to predict "who gets admitted" instead of "who NEEDS admission."
Result: The AI missed high-risk patients because the data quality was wrong.
Amazon built an AI to screen job applicants. Within a year, they shut it down.
Why? The training data was 10 years of resumes—mostly from male applicants because tech was male-dominated.
The AI learned to penalize resumes that included the word "women's" (as in "women's chess club captain").
Result: The AI was biased because the training data reflected past bias.
A retail chain used AI to predict inventory needs. First month? Disaster. Stores ran out of popular items, over-ordered unpopular ones.
Why? The data had:
• Duplicate orders (same customer, multiple entries)
• Missing values (no dates on 20% of transactions)
• Inconsistent product names ('iPhone 13' vs 'iphone 13' vs 'Apple iPhone 13')
Result: The AI couldn't predict accurately because it was learning from chaos.
Empty cells, null values, blanks where data should be.
Examples: Empty email, missing phone number, blank purchase date
AI can't learn from nothing. Missing data creates blind spots in the pattern recognition.
Delete the row, fill with placeholder, or estimate based on similar records.
Same record appears multiple times in the dataset.
Examples: Order 1001 listed twice, John Smith with identical data in two rows
AI thinks one customer = two customers. Predictions get skewed and inaccurate.
Remove duplicate rows using Excel's 'Remove Duplicates' feature or equivalent.
Same thing recorded in different ways.
Examples: "iPhone 13" vs "iphone 13" vs "Apple iPhone 13" vs "iPhone-13"
AI treats these as four different products when they're the same. This destroys pattern recognition.
Standardize format using Find & Replace or text cleaning functions.
Values that don't make sense or are extreme errors.
Examples: Age = 450 (impossible), Purchase = $9,999,999 (unrealistic)
AI learns from extremes. One weird value can ruin predictions for the entire dataset.
Investigate why it's there. If it's an error, correct it or remove it.
Data type inconsistency: dates, currency, numbers all over the place.
Examples: "01/15/2024" vs "15-Jan-24" vs "Jan 15" or "$50.00" vs "50" vs "$50"
AI needs consistent formats to calculate and compare values accurately.
Convert all data to one consistent format (same date style, same currency format).
FIND problems. Don't fix yet. Just identify.
Scan every column. Mark every issue. Categorize each one.
Sort columns. Use Find to spot blanks. Look for weird values.
Find 5-10 issues. More is better!
Identify → Fix → Document
Screenshot BEFORE and AFTER every fix
Fix at least 5 issues. More is better!
What you fixed, how, and why it matters
How many did you find? How many fixed?
What % of rows had problems?
Write 1 paragraph reflecting on what you learned
Why would messy data break an AI system?
Screenshots showing 5+ fixes
What you fixed and why it matters
Summary of findings and insights
Worth $60K-$75K starting salary
You're DOING
You're Demonstrating Real Skill
"I can work with messy real-world data"
$60K+ Data Analyst skill
Why data quality makes or breaks AI
Real messy data like at work
At least 5 data quality issues
Your work professionally