7-Eleven’s Knowledge Documentation Dilemma
7-Eleven’s knowledge ecosystem is huge and sophisticated, housing 1000’s of tables with lots of of columns throughout our Databricks atmosphere. This knowledge types the spine of our operations, analytics and decision-making processes. Historically, 7-Eleven’s knowledge dictionary and documentation lived in Confluence pages, meticulously maintained by our knowledge crew members who would manually doc desk and column definitions.
We confronted a essential roadblock as we started exploring the AI-powered options on the Databricks Knowledge Intelligence Platform, together with AI/BI Genie, clever dashboards and different purposes. These superior instruments rely closely on desk metadata and feedback embedded immediately inside Databricks to generate insights, reply questions on our knowledge, and construct automated visualizations. With out correct desk and column feedback in Databricks itself, we have been primarily leaving highly effective AI capabilities on the desk. For instance, when Genie lacks column definitions, it will possibly misread the that means of bespoke columns, requiring finish customers to make clear. As soon as we enriched our metadata, Genie’s contextual understanding improved dramatically—precisely figuring out column functions, surfacing the proper tables in response to pure language queries, and producing way more related and actionable insights. Merely put, Genie, like all AI brokers, will get extra considerate and extra useful when it has higher metadata to work with.
The hole between our well-documented Confluence pages and our “metadata-light” Databricks atmosphere was stopping us from realizing the complete potential of our knowledge platform funding.
Handbook Migration’s Unimaginable Scale
Once we initially thought of migrating our documentation from Confluence to Databricks, the size of the problem grew to become instantly obvious. With 1000’s of tables containing lots of of columns every, a guide migration would require:
- Time-intensive labor: Tons of of person-hours to repeat and paste documentation
- Handbook metadata updates: Crafting 1000’s of particular person SQL statements to replace metadata or going to every desk UI
- Challenge oversight: Implementing a monitoring system to make sure all tables have been correctly up to date
- High quality assurance: Making a validation course of to catch inevitable human errors
- Ongoing maintenance: Establishing an ongoing upkeep protocol to maintain each techniques in sync
Human error could be unavoidable even when we devoted important assets to this effort. Some tables could be missed, feedback could be incorrectly formatted, and the method would probably must be repeated as documentation developed. Furthermore, the tedious nature of the work probably results in inconsistent high quality throughout the documentation.
Most regarding was the chance value. Whereas our knowledge crew targeted on this migration, they couldn’t work on higher-value initiatives. On daily basis, we confronted delays in strengthening our Databricks metadata, leaving untapped potential within the AI/BI capabilities already at our fingertips.
The Clever Doc Processing Pipeline
To resolve this problem, 7-Eleven developed a classy agentic AI workflow powered by Llama 4 Maverick, deployed by means of Mosaic AI Mannequin Serving, that automated the complete documentation migration course of by means of an clever multistage pipeline:
- Discovery part: The agent makes use of Databricks APIs to get all tables, desk names and column buildings.
- Doc retrieval: The agent pulls all related knowledge dictionary paperwork from Confluence, making a corpus of potential documentation sources.
- Reranking and filtering: Implementing superior reranking algorithms, the system prioritizes essentially the most related documentation for every desk, filtering out noise and irrelevant content material. This essential step ensures we match tables with their correct documentation even when naming conventions aren’t completely constant.
- Clever matching: For every Databricks desk, the AI agent analyzes potential documentation matches, utilizing contextual understanding to find out the right Confluence web page even when names don’t match precisely.
- Focused extraction: As soon as the right documentation is recognized, the agent intelligently extracts related descriptions for each tables and their columns, preserving the unique that means whereas formatting appropriately for Databricks metadata.
- SQL technology: The system mechanically generates correctly formatted SQL statements to replace the Databricks desk and column feedback, dealing with particular characters and formatting necessities.
- Execution and verification: The agent runs the SQL updates and, by means of MLflow monitoring and analysis, verifies that metadata was utilized accurately, logs outcomes, and surfaces any points for human assessment.
- Monitoring and insights: The crew additionally makes use of the AI/BI Genie Dashboard to trace mission metrics in actual time, guaranteeing transparency, high quality management, and steady enchancment.
This clever pipeline remodeled months of tedious, error-prone work into an automatic course of that accomplished the preliminary migration in days. The system’s means to grasp context and make clever matches between otherwise named or structured assets was key to attaining excessive accuracy.
Since implementing this answer, we plan emigrate documentation for over 90% of our tables, unlocking the complete potential of Databricks’ AI/BI options. What started as a frivolously used AI assistant has developed into an on a regular basis device in our knowledge workflows.. Genie’s means to grasp context now mirrors how a human would interpret the info, because of the column-level metadata we injected. Our knowledge scientists and analysts can now use pure language queries by means of AI/BI Genie to discover knowledge, and our dashboards leverage the wealthy metadata to offer extra significant visualizations and insights.
The answer continues to offer worth as an ongoing synchronization device, guaranteeing that as our documentation evolves in Confluence, these adjustments are mirrored in our Databricks atmosphere. This mission demonstrated how thoughtfully utilized AI brokers can remedy complicated knowledge governance challenges at enterprise scale, turning what appeared like an insurmountable documentation activity into a chic automated answer.
Wish to be taught extra about AI/BI and the way it might help unlock worth out of your knowledge? Be taught extra right here.
