AI Agent System
An LLM-driven roster recommendation and scouting workflow built around team need diagnosis, player strength vectors, and fit ranking.
Original tools
A-C
need, strength, ranking
Recorded pool
236
eligible players in notebook
Mode
CSV-gated
live with NBA_DATA_PATH
overview
The backend wraps the original Colab-style NBA project. When the required NBA CSV files are available through NBA_DATA_PATH, it recomputes the original Tool A, Tool B, and Tool C pipeline. Without those CSVs, it displays the captured original notebook output for the published Warriors demo query.
role
Original project authoring and portfolio integration: exposed parsing, need diagnosis, player vectors, fit ranking, and scouting-summary outputs through a structured backend response.
backend runner
Calls /api/nba/run on the FastAPI wrapper at http://localhost:8000.
natural language query
Recorded mode only returns the original notebook output for this exact query. Live recomputation requires the missing NBA CSV files through NBA_DATA_PATH.
backend contract
Start the backend with uvicorn backend.main:app --reload --port 8000. The UI displays mode and provenance so recorded artifacts are clearly distinguished from live computation.
Configure the inputs and run the backend to display the original project trace and outputs here.
architecture flow
The live pipeline trace appears in the backend runner after execution. This section shows the original project components that the backend wraps.
planner
Converts the natural-language roster request into team, goal, top-k, recent-game window, and availability filters.
analytics
Uses recent team statistics and league z-scores to compute a need-weight vector.
features
Builds player strength vectors from box-score features and standardized skill indicators.
ranker
Matches team need weights against player strengths to produce top recommendations and best-match labels.
tools and models
planner
Converts the natural-language roster request into team, goal, top-k, recent-game window, and availability filters.
analytics
Uses recent team statistics and league z-scores to compute a need-weight vector.
features
Builds player strength vectors from box-score features and standardized skill indicators.
ranker
Matches team need weights against player strengths to produce top recommendations and best-match labels.
example input
Recommend top 5 players for the Warriors to improve interior defense using the last 10 games. Only include players with at least 20 games and 18 average minutes.
final result
The original notebook demo recommends Anthony Davis, Rudy Gobert, O.G. Anunoby, Nikola Jokic, and Joel Embiid as the top statistical fits for the Warriors interior-defense request.
limitations