Case study · AI agent · Live demo
Data Analyst Agent
Ask your data questions in plain English: reports, anomalies and forecasts.
A conversational data analyst: upload a CSV and ask questions in plain English. It writes and runs the analysis, then answers with charts.
- Type
- AI agent with a live demo
- Built by
- Maarij Aqeel
The challenge
Answering questions about a dataset usually means writing pandas by hand, and chat tools that can't run code lose track of your data between questions.
What I built
- An LLM writes pandas and matplotlib code and runs it in a persistent Jupyter kernel, so follow-ups like "now filter that to free apps" just work.
- EDA reports, anomaly detection (IQR, Z-score, Isolation Forest) and forecasting.
- Charts render inline, answers stream live, and a show-the-code toggle keeps it transparent.
- Each session gets its own isolated kernel; FastAPI backend, Next.js front end, deployed with Docker.
Results
- Live demo you can try with your own CSV
- Multi-turn memory across questions
Tools
- FastAPI
- Next.js
- pandas
- Jupyter
- OpenRouter
Want something similar? See ai automation & agents →
More case studies
Voice AI · MelonLabs
WordBuddy AI
Shipped to Google Play with 80% lower conversational-AI costs.
Read the case study
AI automation · 16x9.ai
AI Content Automation Engine
Cut content production time 95% with four chained n8n workflows.
Read the case study
Voice AI · Web app
Intervue AI
Real-time AI interviews with 80% lower voice costs and 30% faster setup.
Read the case study