Compliance monitoring · Production

Philadelphia Union builds GenAI RAG chatbot for MLS roster management on Databricks

The problem

MLS Roster Composition Rules and Regulations are extensive and filled with legalistic details, slowing down the Philadelphia Union front office's decision-making during roster planning and transfer market activity.

Workflow diagram · grounded in source
1
Front office submits query
trigger
“The chatbot is accessed through a no-code, ChatGPT-like interface deployed via Databricks Apps”
2
Roster rule PDFs ingested
integration
“a continuous ingestion mechanism was set up to load roster rule PDFs into Databricks Volumes, a fully governed store for semi-structured and unstructured data on Databricks”
3
Embeddings generated
ai_action
“Text is then extracted, and numerical representations (or embeddings) are generated using Embedding Models from the Databricks Foundation Model API”
4
Vector Search retrieval
ai_action
“These embeddings are indexed and served by Vector Search for fast and efficient search and retrieval, enabling rapid access to relevant information”
5
DBRX Instruct generates response
ai_action
“Philadelphia Union also utilized Databricks' own DBRX Instruct model, a powerful open source LLM based on a Mixture of Experts (MoE) architecture”
6
Human feedback and validation
human_review
“The framework also includes a review app and built-in Evaluations, which were invaluable for collecting human feedback and validating the effectiveness of the RAG solution prior to deployment”
7
Roster regulation interpretation output
output
“enables zero-shot interpretation of roster regulations in seconds”
Reported outcome

The GenAI chatbot enables zero-shot interpretation of roster regulations in seconds, accelerating decision-making and allowing the front office to focus on strategic tasks while maintaining compliance with MLS guidelines.

Reported metrics
Roster regulation interpretation speedzero-shot interpretation of roster regulations in seconds
Decision-making speedaccelerates decision-making
Front office time savingssaves valuable time
Operational efficiencystreamlines operations and improves efficiency
Reported stack
Databricks Data Intelligence PlatformDatabricks AppsRAGVector SearchDatabricks VolumesDatabricks Foundation Model APIDBRX InstructAgent Bricks Custom Agents
Source
https://www.databricks.com/blog/philadelphia-union-genai
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The GenAI chatbot enables zero-shot interpretation of roster regulations in seconds, accelerating decision-making and allowing the front office to focus on strategic tasks while maintaining compliance with MLS guideli…

What tools did this team use?

Databricks Data Intelligence Platform, Databricks Apps, RAG, Vector Search, Databricks Volumes, Databricks Foundation Model API, DBRX Instruct, Agent Bricks Custom Agents.

What results were reported?

Roster regulation interpretation speed: zero-shot interpretation of roster regulations in seconds; Decision-making speed: accelerates decision-making; Front office time savings: saves valuable time; Operational efficiency: streamlines operations and improves efficiency (source-reported, not independently verified).

How is this compliance monitoring AI workflow structured?

Front office submits query → Roster rule PDFs ingested → Embeddings generated → Vector Search retrieval → DBRX Instruct generates response → Human feedback and validation → Roster regulation interpretation output.

Related compliance monitoring cases