SAMPLE AND DEMONSTRATION ONLY. Illustrative analysis of publicly available information, prepared by BI Consulting Services. Not affiliated with, endorsed by or produced for any company shown.
Demonstration · Illustrative data · BI Consulting Services
Cardinal Health × BI Consulting Services
Environmental Health & Safety · Site-safety scorecard prototype
Prepared for Caleb · Environmental Health & Safety
September 2026 · Snowflake → Power BI · role-based access EHS COMMAND BOARD · v0.9 PROTOTYPE
One board for TRIR, DART, near misses and audits — across every Cardinal Health site, refreshed from Snowflake, not Excel.
Every tile, chart and sentence below recalculates when you change Region, Business segment or Period. This is the 4–5 page report described in the April 2025 proposal, compressed to a single page so you can feel how it behaves.
Region
Segment
Period
Incident trend
Monthly recordables and rolling-12 TRIR vs industry benchmark
US facility map — each dot is a site, coloured by TRIR band
TRIR < 2.02.0 – 3.5> 3.5Dot size = hours worked
Site ranking
Highest TRIR sites in scope
Near-miss funnel
Reported → investigated → closed
Safety pyramid
Leading vs lagging indicators in scope
Audit completion
Completed vs planned EHS audits
Ask the data · AI layer (mock)
Natural-language questions over the same Snowflake model
Answers cite the visuals above
Which sites drove the Q2 2026 rise in recordables?
Show DART by segmentSites with overdue auditsNear-miss closure > 30 daysCompare to same period last year
Illustrative interface. In production this runs against governed Power BI semantic models with the same row-level security as the report pages, so a regional EHS lead only ever sees their own sites.
Also from BI Consulting Services
Private AI on your own server
The "ask the data" panel above is built to run on a GPU server inside your own network: an open-weight model over your own documents, with every answer citing the file it came from. No per-seat licence, works offline, and nothing leaves the building.
How it sits in your environment
One appliance-class server on your rack or in a secured closet. Your files are indexed where they already live; the model runs locally; answers come back with the source page attached.
What that means in practice
1
Your data only, on your hardwareAn open model over your own documents and exports. No third-party AI processor, no data-transfer agreement to review.
2
Every answer cites its sourceReplies point to the file and page they were drawn from, so people check the answer instead of trusting it blind.
3
No per-seat licenceThe whole team can ask questions. Cost is the server and our build, not a monthly number that grows with headcount.
4
Works offlineIf the internet connection goes down, the answers still come. Nothing depends on a vendor's uptime or pricing changes.
The short deck
14 slides on how a private AI server is scoped, secured and rolled out. Click through, or take the PDF.
