How autonomous agents will support data exploration
summary
An LLM-powered coding agent runs inside Google Colab on a Data Commons table (solar panel installs, median household income, rainfall), automatically creating and executing cells, using Pandas to drop missing values, detecting outliers via standard deviation and asking permission before removal. It parses date fields, recomputes correlations, and builds a correlation heatmap that previously showed blanks. The agent prints the Python it runs so code is editable, reproducible, and the visualization and flagged correlations appear immediately.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 0:30What are autonomous agents
- 1:37Features
- 3:07Demo
- 7:49Summary
- 8:19Building more agents
- 8:57Keeping you in the flow
related talks
41mBuilding LLM Agents – Challenges and Learnings
01h 29mBuild Your Own Data Science AI Agents
59mMaking the most of artificial and human intelligence for data science
43mGetting started with AI for free
04h 02mHands-on Session on Data Science for Beginners
36mVibing with Data -- Multi-Agent Data Modeling and Constructi...
58mAI-Enhanced Big Data: Integrating Private LLMs and Vector Databases
48mAI Coding Agents and how to code them