Project 01  ·  LLM tooling

AI Data Analyst
Agent

PythonOpenAI APIPandasPostgreSQLDocker

A question-answering layer over tabular data that refuses to guess. The model decides what to compute; Pandas does the computing, so every number in an answer is traceable to an executed operation.

10+
Deterministic operations
50K+
Rows per dataset
5+
Chart types
75+
Queries validated

What I built

  1. i.

    Built an AI analytical agent using LLM function calling and Pandas, supporting 10+ deterministic data operations across datasets with up to 50K+ rows.

  2. ii.

    Designed a tool-augmented reasoning architecture that combines LLM decision-making with Pandas execution engines to perform aggregations, trend analysis, anomaly detection, and data exploration with verifiable outputs.

  3. iii.

    Developed structured-response and visualization pipelines supporting 5+ chart types and validated end-to-end behavior across 75+ analytical queries, automatically producing computed insights, tables, and visualizations from user requests.