Python AI Tool for Contract Performance Analytics
Budget: £20 – £250 GBP
Project: AI-Powered Clause Evaluation + Q&A Tool (Python)
I want an AI-powered tool built in Python that works with two data sources:
1. A CSV file containing player match data (minutes played, starts, appearances, competitions, seasons).
2. An Excel file containing performance-based contract clauses (e.g. “£10k bonus after 20 league games”).
The goal is to use AI to help interpret and work with these contract clauses, then evaluate them against real performance data.
⸻
Task
Your task is to:
• Merge these two datasets
• Evaluate every clause for every player
• Determine whether each clause has been triggered
• Calculate any financial payout
Then export a final consolidated CSV showing:
• the clause description
• triggered status (TRUE/FALSE)
• payout amount
• supporting metrics (appearances, minutes, date triggered where applicable)
⸻
AI Q&A Component
I also need a lightweight AI Q&A interface on top of this processed dataset.
I want to be able to ask natural-language questions like:
• “How many games did Player X play?”
• “Did Clause Y trigger?”
• “What is our total liability this season?”
• “Which players are close to triggering a clause?”
The system should:
• Use an LLM (OpenAI API or similar) to interpret the question
• Translate the question into queries over the processed data
• Answer only using the data, not by guessing or hard-coding numbers
A simple Streamlit app, Flask app, or CLI tool is fine, as long as it’s clear and easy to run locally with updated CSV/Excel files each season.
⸻
Deliverables
1. A Python script or notebook that:
• loads the CSV player data and Excel clause file
• evaluates all clauses against actual performance
• calculates payouts
• exports a final results CSV
2. An AI-powered Q&A interface that:
• loads the processed dataset
• uses an LLM (OpenAI or similar) to understand free-text questions
• returns answers based strictly on the data
3. A short README explaining:
• setup and required libraries
• how to run the script and Q&A tool
• how to plug in new season files (new CSV/Excel)
4. Verification that:
• sample queries return correct answers
• payout totals match a manual check on a few test examples.
I want an AI-powered tool built in Python that works with two data sources:
1. A CSV file containing player match data (minutes played, starts, appearances, competitions, seasons).
2. An Excel file containing performance-based contract clauses (e.g. “£10k bonus after 20 league games”).
The goal is to use AI to help interpret and work with these contract clauses, then evaluate them against real performance data.
⸻
Task
Your task is to:
• Merge these two datasets
• Evaluate every clause for every player
• Determine whether each clause has been triggered
• Calculate any financial payout
Then export a final consolidated CSV showing:
• the clause description
• triggered status (TRUE/FALSE)
• payout amount
• supporting metrics (appearances, minutes, date triggered where applicable)
⸻
AI Q&A Component
I also need a lightweight AI Q&A interface on top of this processed dataset.
I want to be able to ask natural-language questions like:
• “How many games did Player X play?”
• “Did Clause Y trigger?”
• “What is our total liability this season?”
• “Which players are close to triggering a clause?”
The system should:
• Use an LLM (OpenAI API or similar) to interpret the question
• Translate the question into queries over the processed data
• Answer only using the data, not by guessing or hard-coding numbers
A simple Streamlit app, Flask app, or CLI tool is fine, as long as it’s clear and easy to run locally with updated CSV/Excel files each season.
⸻
Deliverables
1. A Python script or notebook that:
• loads the CSV player data and Excel clause file
• evaluates all clauses against actual performance
• calculates payouts
• exports a final results CSV
2. An AI-powered Q&A interface that:
• loads the processed dataset
• uses an LLM (OpenAI or similar) to understand free-text questions
• returns answers based strictly on the data
3. A short README explaining:
• setup and required libraries
• how to run the script and Q&A tool
• how to plug in new season files (new CSV/Excel)
4. Verification that:
• sample queries return correct answers
• payout totals match a manual check on a few test examples.