ai-data-science-team 0.0.0.9017

ai-data-science-team v0.0.0.9017

Released on December 20, 2025

This release introduces the flagship AI Pipeline Studio app and brings major advancements in agent capabilities, security, multi-agent coordination, and workflow planning. We've also completed the migration to LangChain 1.0+ message-first APIs, added sandboxed code execution for safety, and introduced a new supervisor-led data science team.

🚀 New Features

• AI Pipeline Studio (Flagship App)
  A visual, pipeline-first Streamlit app for building reproducible data science workflows.

  • Visual editor with lineage tracking
  • Table, Chart, EDA, Code, Model, Predictions, and MLflow views
  • Multi-dataset handling and merging
  • Project save/load (metadata-only or full-data modes)
  • Run with: streamlit run apps/ai-pipeline-studio-app/app.py

• Supervisor-Led Data Science Team
  New multi-agent workflow with a supervisor that routes tasks across specialized agents for end-to-end data science pipelines.

• Workflow Planner Agent
  Generates structured, ordered plans with prerequisites and questions for missing information (e.g., target variable).

• Model Evaluation Agent
  Deterministic holdout evaluation of H2O models with standardized metrics, confusion matrices, ROC curves, and residual plots.

• Sandboxed Code Execution
  All generated code now runs in an isolated subprocess with blocked dangerous imports, network access disabled, and configurable timeouts/memory limits.

• Python 3.13 Support
  The package now officially supports Python 3.13.

🔧 Enhancements & Fixes

• LangChain 1.0.0 Compatibility
  Full refactor to message-first APIs across all agents for better multi-agent and supervisor integration.

• Security Fixes

  • Fixed potential vulnerability in load_pickle operations (#64)
  • Fixed "human in the loop" error in certain workflows (#53)

• Agent Upgrades

  • Data Cleaning, Wrangling, Visualization, Feature Engineering, and SQL agents: upgraded to conversational/message-first interfaces
  • H2O ML Agent: improved reliability and MLflow integration
  • EDA Tools Agent: enhanced reporting
  • Data Loader Tools Agent: added conversational interface and better file handling
  • MLflow Tools Agent: expanded capabilities

• Theme & UI Updates
  Updated Streamlit config for improved dark mode theming.

• Documentation & Examples

  • Major README overhaul with clearer structure and app screenshots
  • Updated examples for all agents reflecting new message-first usage
  • New planning docs and package review notes included

📦 Package

• Version bump to 0.0.0.9017
• Still in beta — breaking changes may occur before v0.1.0

Install the latest version:

pip install ai-data-science-team --upgrade

Or from GitHub for the bleeding edge:

pip install git+https://github.com/business-science/ai-data-science-team.git --upgrade

Thank you for starring the repo and trying out the AI Data Science Team! ⭐

We're rapidly iterating — stay tuned for more agents and apps.

— Matt Dancho & Business Science

Full Changelog: 0.0.0.9016...0.0.0.9017

0.0.0.9016

Enhancements

• Exploratory Data Analysis Agent: New dtale tool integration
• Exploratory Data Analysis Copilot App: New dtale tool integration

Full Changelog: 0.0.0.9015...0.0.0.9016

ai-data-science-team 0.0.0.9015

New Apps

• Open Pandas AI Data Analyst App: This application allows you to upload an Excel or CSV file and use the AI agent to perform analysis and create data visualizations to help you interpret the data and gain insights.

Full Changelog: 0.0.0.9014...0.0.0.9015

ai-data-science-team 0.0.0.9014

New Multi-Agent

• PandasDataAnalyst(): Combines Pandas Data Wrangling and Plotly Data Visualization Agents for performing data analysis and data visualization in a single agent.
• SQLDataAnalyst(): Includes a preprocessor that helps plan the steps and get better performance from SQLDatabaseAgent and DataVisualizationAgent.

Improvements

• Agents are all now imported at top level of ai_data_science_team. Users can now do from ai_data_science_team import SQLDatabaseAgent
• Agents now support langgraph checkpointer for state memory
• Agents now have name attribute

Full Changelog: 0.0.0.9013...0.0.0.9014

ai-data-science-team 0.0.0.9013

New App

• Exploratory Data Analysis Copilot: This application uses the EDAToolsAgent() to help the user create EDA Reports, Correlation Analysis, Missing Value Analysis, and general exploratory analysis. See App Here

Enhancements

• EDAToolsAgent(): New tool explain_data that returns a human-readable analysis of the data with statistical summary and various analysis that are common in exploratory data analysis.
• Tool Calling Agents now return state graphs with tool_calls captured as a list. This change helps the developer determine which tool was called last and how to handle the artifacts. This affectsEDAToolsAgent(), DataLoaderToolsAgent(), and MLflowToolsAgent().

Breaking Changes

• EDAToolsAgent():
  • The tool artifact dictionary keys have been updated. See Full Changelog below.
  • Sweetviz reports are not opened automatically unless the user specifies to do so.
  • Sweetviz reports are saved in a temporary directory.

Full Changelog: 0.0.0.9012...0.0.0.9013

ai-data-science-team 0.0.0.9012

New Agent

• EDA Tools Agent: Performs automated exploratory data analysis (EDA) with EDA Reporting, Missing Data Analysis, Correlation Analysis, and more. See Example

Full Changelog: 0.0.0.9011...0.0.0.9012

ai-data-science-team 0.0.0.9011

New Agents

• Data Loader Tools Agent: Loads data from various sources including CSV, Excel, Parquet, and Pickle files. See Example

Full Changelog: 0.0.0.9010...0.0.0.9011

ai-data-science-team 0.0.0.9010

New Agents

• MLflowToolsAgent: This agent has 11+ tools for managing models, ML projects, and making production ML predictions with MLflow.
• New Example: MLflow Agent See Example

New AI Apps

• Created app/ directory: Houses AI applications that demonstrate usage of the AI Data Science Team
• SQL Database Agent App: Connects any SQL Database, generates SQL queries from natural language, and returns data as a downloadable table. See Application

Internal Changes

• Refactored utils, parsers, and tools to make it more clear the function roles
• Async updates

Full Changelog: 0.0.0.9009...0.0.0.9010

ai-data-science-team 0.0.0.9009

New Agents:

• H2OMLAgent(): The first in a series of ML agents designed to make Machine Learning Models with AI. This AI Agent is trained in h2o AutoML and is capable of creating 100's of ML models in seconds.
• New Example: https://github.com/business-science/ai-data-science-team/blob/master/examples/ml_agents/h2o_machine_learning_agent.ipynb

Improvements

• Workflow Summary Report: The explain code step was replaced with a much faster step for documenting the agentic workflow. A get_workflow_summary() method returns formatted summary reports of every step taken in the agentic workflow.
• Smart Schema Pruning: SQL Database Agent gained a new parameter, smart_schema_pruning, which uses an extra LLM call to prune tables and columns. This is useful when database schemas are very large. Pruning is based on Uber QueryGPT blog article which implements a Column Prune Agent. Read more here: https://www.uber.com/blog/query-gpt/

Full Changelog: 0.0.0.9008...0.0.0.9009

ai-data-science-team 0.0.0.9008

New Features

1. New Object-Oriented Programming Framework (Experimental): OOP Framework provides a Pythonic interface to agents, improved methods, and more features beyond LangGraph methods. New classes include DataCleaningAgent(), FeatureEngineeringAgent(), SQLDatabaseAgent() and more.
2. Multi-Agents: A new multiagents module was created. This supports common LangGraph multi-agent architectures, which will be a big focus going forward.
3. New SQLDataAnalyst Multi-Agent: Combines the SQLDatabaseAgent and DataVisualizationAgent() in a multi-agent workflow with conditional routing to the data visualization agent. Perfect for Business Intelligence and Data Analysis applications.

New Examples

1. How to Build SQL Data Analysis Agents: https://github.com/business-science/ai-data-science-team/blob/master/examples/multiagents/sql_data_analyst.ipynb
2. Human In The Loop (new workflow): https://github.com/business-science/ai-data-science-team/blob/master/examples/advanced_topics/human_in_the_loop.ipynb

Enhancements

• New BaseAgent() Class: Used to make common methods available to all OOP agents.
• New Human-In-The-Loop Workflow: Allows applications to include human review and modification. Perfect for iteratively improving AI functions.

Full Changelog: 0.0.0.9007...0.0.0.9008