The interrogation phase: data quality
AI for Data Analysts
Andy Cotgreave
Author and Speaker, Former Technical Evangelist at Tableau
The usual suspects
The harder problems AI unlocks
Fuzzy duplicates
Traditional
: hand-craft rules, maintain
forever
AI
: writes the matching logic and brings
semantic understanding
Output → a query or grouping you can read and adjust
Time-order violations
Traditional
: write SQL that compares timestamps
AI
: describe what shouldn't happen → AI
writes the query
Logical inconsistencies
Traditional
: reference tables — someone has to
maintain
them
AI
:
world knowledge
, no reference data required
Interrogate the AI's work
AI isn't magic — it's generating queries, code, or rules
That work can be
wrong
: bad regex,
hallucinated
business rule
Fixing the issues
Let's practice!
AI for Data Analysts
Preparing Video For Download...