Max Rautenkranz · max_rautenkranz.xls
File
← Projects

CFB Sharp Private

A college football analytics platform with an LLM data pipeline and an MCP server for AI analysts.

What I built

  • Built 17 scheduled Python jobs that feed an eight-factor model.
  • Wrote an LLM pipeline that turns injury news into structured data, validated with Pydantic.
  • Shipped an MCP server that lets AI analysts query data and run experiments, with every write requiring human approval.
  • Saved every AI analyst session as a transcript, which keeps sessions available for later evaluation.

How it works

How the parts connect
the platform’s data17 scheduledPython jobsEight-factormodelInjury newsLLM pipelineStructured datavalidated with PydanticMCP serverAI analystsSessiontranscriptsHumanapprovalfeedquery data, run experimentsevery writeonce approvedevery session saved
How the parts connect
the platform’s data17 scheduledPython jobsEight-factormodelInjury newsLLM pipelineStructured datavalidated with PydanticMCP serverAI analystsSessiontranscriptsHumanapprovalfeedquery data,run experimentsonce approvedevery writeevery session saved

At a glance

TypeIndependent
StatusPrivate
StackPython, FastAPI, TypeScript, Pydantic, MCP, Linux

Launch

='[cfb_sharp.xls]Board'!A1

This cell links to another workbook, and that workbook is private.

Open linked workbook

Ask me for a walkthrough

Last updated