A tool for analysing Google Ads and Meta Ads exports with AI.
The problem
Advertising exports use different naming conventions, structures and numeric formats. Without an audit layer, the risk is drawing conclusions from incomparable data or ending up with fragmented, disconnected observations.
The solution
I separated facts from reasoning: deterministic parsing, normalization and calculations provide a clear, comparable view of the data and periods under review; the model receives structured context to interpret relevant signals.
What I built
I built a React and Vite application with a Node and Express backend to import CSV files, detect platforms and available fields, remove aggregate rows, and calculate KPIs and account benchmarks.
How it works
CSV exports > data analysis > field taxonomy > normalized metrics > benchmarks > signals > AI interpretation.
Engineering choices
Field taxonomy and localized number parsing are deterministic. OpenAI explains signal limitations and priorities rather than replacing calculations.
Outcome
A repeatable flow that turns fragmented exports into output closer to an analyst's work.