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
Pivotal×BI Consulting Services

Build-to-Delivery Board over Epicor Kinetic

A no-pressure look at what a production-grade Power BI layer could look like for a low-volume eVTOL manufacturer: WIP by station, on-time build completion, supplier on-time delivery, material shortages and in-service events per aircraft — all from the Epicor modules you already run.

Prepared for Sohare
September 2026
Palo Alto, CA · Helix & BlackFly programs

Aircraft completed per month vs build plan

Epicor Job Management · job close date vs scheduled due · selected window highlighted

Completed on timeCompleted lateBuild plan

What this board answers

Three questions a build meeting actually asks

Station flow — work in process at period end

Epicor Job Management operations by resource group · WIP units vs station capacity · bottleneck = highest load

WIP within capacityLoad ≥ 90% of capacityOver capacity (bottleneck)

Supplier on-time delivery by commodity

Epicor Purchase Management · PO lines received vs promise date · target 92%

≥ target85–92%< 85%92% target

Deliveries by state (cumulative in window)

Epicor Order Management ship-to · aircraft handed over

In-service events per aircraft, by subsystem

Epicor Field Service + Quality · events ÷ fleet in service

Ask the data

Natural-language layer over the same semantic model (Copilot-style, governed by the model's measures)

ST
Answer · grounded in board measures

Where each number comes from

Epicor Kinetic modules → one governed Power BI semantic model

Job ManagementCompletions, on-time %, WIP by station. Job header due dates vs close dates; operations by resource group feed the station flow.
Purchase ManagementSupplier OTD by commodity. PO release promise date vs receipt date (PO line level).
Inventory / MRPOpen shortages. Negative projected on-hand against released jobs, by part class.
Field Service + QualityIn-service events per aircraft. Service calls and NCRs joined to serial number → subsystem.
Order ManagementDeliveries by state / segment. Ship-to state and customer group on the sales order.
Five modules, one refresh, one set of measures — the same numbers whether the question is asked in a build meeting or typed into the panel on the left.
Demonstration · Illustrative data · BI Consulting Services
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

YOUR NETWORK · NOTHING LEAVES THE BUILDING Your files policies · SOPs · contracts reports · ERP exports indexed locally GPU One server, in your building open-weight model · your data only in seconds Cited answers every reply links to the source file and page no cloud AI · no third-party processor
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. 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. 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. 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. 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.

Download the PDF
Private AI on your own server — slide 1 of 14 Private AI on your own server — slide 2 of 14 Private AI on your own server — slide 3 of 14 Private AI on your own server — slide 4 of 14 Private AI on your own server — slide 5 of 14 Private AI on your own server — slide 6 of 14 Private AI on your own server — slide 7 of 14 Private AI on your own server — slide 8 of 14 Private AI on your own server — slide 9 of 14 Private AI on your own server — slide 10 of 14 Private AI on your own server — slide 11 of 14 Private AI on your own server — slide 12 of 14 Private AI on your own server — slide 13 of 14 Private AI on your own server — slide 14 of 14
1 / 14Tap or click a slide to advance · arrow keys work too

Worth a conversation? Book 30 minutes with NicholeBI Consulting Services · powerbiconsultingservices.com