Adding predictive insurance agent example using claude-code-sdk-python
and kumo-rfm-mcp
#192
+953
−0
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello 👋🏻! Blaz from Kumo here :)
We've recently built an MCP server to interact with our foundation model for machine learning (KumoRFM) which allows agents to make predictions with just a few simple tool calls. We are very excited to use the MCP tools to build a new generation of predictive agents for which predictions are a core part of their workflow.
This notebook demonstrates a very simple insurance agent, which generates both a churn prediction as well as personalized recommendations for users with expiring policies and compiles emails for outreach. The solution uses our MCP along with
claude-code-sdk-python
.Super happy to make any changes/improvements needed to meet the quality bar for this repository.