Summary

Adding a new cookbook entry called "Bridging the Predictive Gap in Agents with KumoRFM MCP"

Includes:
Notebook entry: bridging-the-predictive-gap-in-agents.ipynb
Example script: predictive_insurance_agent.py, README.md, requirements.txt

Motivation

Current AI agents primarily handle information retrieval and analysis of existing data, but many business workflows require predicting future outcomes like customer churn, product recommendations, or risk assessment. Integrating traditional ML models into agent workflows typically involves complex prediction services, feature engineering pipelines, and separate model training/deployment infrastructure that creates significant development overhead.

This cookbook explores using KumoRFM MCP (https://github.com/kumo-ai/kumo-rfm-mcp/) to add prediction capabilities directly to agents through a simple tool interface, treating predictions as naturally as database queries or API calls. The approach demonstrates how agents can work with multi-table relational data for predictions without requiring separate ML engineering or custom model development.

The cookbook presents a general pattern that can be reused across many agentic applications and highlights an insurance churn/cross-sell example.

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.