← All work
TransData · 2024 to present
Agent-based BI report generation
Role: ML Engineer
12 hours → 45 minutes (-94%)
3× reporting capacity
The problem
Business reports took ~12 hours of manual analysis per cycle.
The approach
- ▹LangGraph workflow with specialized agents for extraction, comparative analysis, insight generation and report compilation across CSV, PDF, Word and Excel, deployed on AWS with monitoring.
The impact
- ✓12 hours → 45 minutes (-94%)
- ✓3× reporting capacity
Trade-off, said plainly
The extraction agents assume fairly consistent report formats across cycles. A source format that changes a lot needs a schema update first. This is not a system that parses any random document with zero setup.
Stack
LangGraphMatplotlibPlotlyDockerAWSCloudWatch
Want to see it working?
Run the live demo, or send an inquiry to talk about your version of this.