Built something I'm pretty proud of — Data Detective
An AI-powered anomaly investigation tool that turns dry data analysis into a noir detective case.
Under the hood:
→ Claude + 14 custom MCP tools
→ Isolation Forest for anomaly detection
→ Pearson correlation analysis
→ Results presented as an actual investigation report
No spreadsheets. No jargon. Just: "The suspect is outlier #47. Here's the evidence."
I hit $10K in earnings a few days ago and received so many messages asking what I did differently.
honestly, the only thing that really helped me was stopping the overthinking.I stopped thinking about all the possibilities. Stopped thinking about when it would happen. Stopped...
Recently I completed a very interesting - Quantile, an AI backed Business Analytics Software. Chat with your data - and build dashboards through code. Check it out!
Client had raw sales data (14 rows across UK/USA, split by quarter) and needed it turned into something actually usable. I cleaned it up and built a PivotTable that breaks total sales down by rep and country, with grand totals for both.
What I did:
Structured the raw data into a proper table (consistent headers, currency formatting)
Built a PivotTable summarizing Sum of Sales by Last Name and Country
Used SUMIFS so the totals update automatically if the source data changes — nothing hardcoded
Checked every formula for errors before delivery
Delivered as a working .xlsx file, ready to plug into a bigger report or dashboard.
If you've got messy sales/ops data sitting in a spreadsheet and need it turned into something you can actually read at a glance, this is exactly the kind of thing I can help with.