Empowering Technicians Throughout Each Retailer
7‑Eleven’s upkeep technicians preserve shops operating easily by servicing a variety of apparatus — from meals service home equipment and refrigeration items to gas dispensers and Slurpee machines. Every restore depends on the technician’s information and speedy entry to supporting paperwork, corresponding to service manuals, wiring diagrams, and annotated pictures.
Making a Unified and Quicker Manner for Technicians to Discover Tools Info
Over time, gear documentation has developed to incorporate a number of codecs, unfold throughout varied areas. This makes it more durable for Technicians to find the knowledge they want rapidly. Furthermore, when encountering unfamiliar gear, elements, and so on., Technicians would usually depend on chat or e-mail to get help from their friends.
As such, a chance to streamline how info is accessed, shared, and so on. was recognized; in the end leading to extra constant help for retailer operations.
Constructing the Technician’s Upkeep Assistant (TMA)
To sort out these challenges, 7‑Eleven envisioned an AI‑powered assistant that would:
- Retrieve exact solutions from upkeep paperwork.
- Establish gear elements from pictures and counsel associated supplies.
- Combine seamlessly inside Microsoft Groups.
Partnering with Databricks, 7-Eleven developed the Technician’s Upkeep Assistant (TMA), an clever resolution that integrates doc retrieval, imaginative and prescient fashions, and collaboration right into a streamlined workflow.
Doc Storage and Indexing
All related upkeep paperwork have been uploaded to a Unity Catalog Quantity, which manages permissions for non-tabular knowledge, corresponding to textual content and pictures, throughout cloud storage.
Utilizing Databricks Vector Search, the event staff carried out Delta Sync with Embeddings Compute. They generated vector embeddings utilizing the BAAI bge-large-en-v1.5 mannequin, and served them by way of a Vector Search endpoint for high-speed, low-latency retrieval.
Microsoft Groups Integration
Technicians entry TMA straight by way of Microsoft Groups. A Groups Bot routes every question by way of an API layer that orchestrates calls to Databricks Mannequin Serving. The assistant supplies contextual solutions, matches documentation hyperlinks, and suggests related elements straight within the chat window.
Routing Agent and Sub‑Agent Design
A Routing Agent determines whether or not a technician’s question is document-based or image-based, directing it to the right sub-agent:
- Doc Query and Reply Agent
- Technicians can use pure language queries inside Groups. With Claude 3.7 Sonnet by way of Databricks Mannequin Serving, the system converts these queries into vector embeddings, searches the index, and returns context-aware solutions utilizing Retrieval-Augmented Technology (RAG). Technicians obtain responses immediately, even from lengthy manuals or gear guides.
- Picture Identification Agent
- Early variations used simple textual content extraction by way of Claude 3.7 Sonnet however yielded uneven outcomes. Engineers enhanced efficiency by tailoring prompts to technician workflows — masking product numbers, producer particulars, specs, security warnings, and certification dates.
- The extracted knowledge maps on to Delta Desk fields, linking visible references to the right paperwork within the vector index. This refinement produced extra correct and dependable half recognition.
Logging and Analytics
To take care of transparency and knowledge governance, all interactions — routing, queries, and picture requests — are logged in Amazon DynamoDB. A each day Databricks Job extracts these logs, shops them in Delta tables, and powers a devoted AI/BI Dashboard.
The dashboard offers 7‑Eleven visibility into:
- Every day/Weekly/Month-to-month (see under) question quantity by technician.
- Most regularly looked for or serviced gear.
- Chatbot decision traits and latency.
- Correlation between TMA adoption and improved first‑time‑repair charges.
Migration from AWS to Databricks
The primary proof of idea utilized AWS elements, together with SageMaker, FAISS, and Bedrock, to host massive language fashions corresponding to Claude 3.7 Sonnet and Llama 3.1 405B. Whereas practical, this setup required handbook reindexing, a number of indifferent providers, and launched latency.
To simplify its infrastructure, 7-Eleven migrated to a completely Databricks Agent Bricks resolution, end-to-end, which resulted in accelerated response occasions.
Key enhancements:
- Automated vector indexing with Databricks Vector Search.
- Unified knowledge governance and compute administration.
- Decrease latency and simplified observability by way of a single lakehouse structure.
Delivering Operational Affect
“From what I’ve skilled to date, the Technician’s Upkeep Assistant has the potential to significantly enhance the pace, accuracy, and consistency with which our technicians entry crucial documentation for preventive upkeep and gear restore,” mentioned James David Coterel, Company Upkeep Coach at 7‑Eleven.
By streamlining doc retrieval and lowering dependency on peer help, the TMA enhances technician confidence, improves first-time-fix charges, and cuts search time from minutes and even hours to seconds; straight lowering downtime and accelerating retailer readiness.
In parallel, shifting retrieval, embeddings, and inference from AWS to Databricks eradicated FAISS upkeep and EC2 load, decreasing infrastructure overhead and bettering latency, which compounded into measurable operational financial savings and a extra constant buyer expertise.
Whereas the precise greenback influence continues to be being measured, the mixture of sooner first-time decision, fewer handbook escalations, and decrease infrastructure overhead creates clear value avoidance on labor hours and unplanned gear downtime, each of which correlate strongly with retailer income safety and buyer expertise stability.
Future Enhancements
7‑Eleven plans to increase TMA’s capabilities by way of:
- Video-based upkeep guides for visible and fingers‑on studying.
- Multilingual help for world upkeep groups.
- Knowledge‑pushed suggestions loops to repeatedly refine response accuracy and relevance.
Uncover how Databricks allows enterprises like 7-Eleven to construct clever assistants that combine knowledge, paperwork, and imaginative and prescient fashions on a single platform.