← Back to projects
AI · Finance Automation

Revenue Intelligence Agent

Weekly revenue reporting takes 8+ hours of manual SQL pulls, Excel reconciliation, and narrative writing. This agent does it in under 2 minutes.

PythonSQLClaude APIn8nStreamlitPlotly
Live Demo →View on GitHub
Case Study

Revenue Intelligence Agent

Problem → Approach → Results

1

The Problem

Manual weekly revenue reporting consumed 8+ hours per cycle. Finance teams were spending more time assembling data than interpreting it. Leadership visibility was delayed by days.

2

The Data Layer

Built a simulated multi-product revenue dataset. Wrote SQL pipelines using CTEs and window functions to compute actuals vs. plan, week-over-week delta, and 4-week rolling trends.

3

The AI Layer

Engineered a structured prompt that passes variance data to the Claude API and returns a 3-sentence exec summary, top 3 drivers, key risk flag, and recommended action.

4

The Automation Layer

Orchestrated the end-to-end pipeline in n8n: weekly trigger → data pull → Python analysis → Claude API call → formatted report output.

5

The Results

8h → 2m
Reporting time eliminated
10+
Scenarios tested
3 roles
Target JDs addressed
The goal wasn't to replace the analyst. It was to give the analyst their week back.