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
NH
Program Impact Dashboard · Board exhibit set
New Hampshire Housing × BI Consulting Services
Homeownership, Rental Assistance and Developer Financing in one board-ready view — every exhibit recalculates from the filters below.
Prepared for Alexsandra
September 2026 · Illustrative build
Fiscal years run July 1 – June 30
Exhibit 1 · Signature view
Households served per 1,000 residents, by county
Choropleth of New Hampshire's 10 counties. Top three labeled. Click a county to filter the whole board.
Ranked · per 1,000 residents
Households served per 1,000
00
What this board answers
Three questions the board asks every quarter
Answers are computed live from the current filter scope.
MethodNeed index = county share of cost-burdened renter households relative to the state (1.00 = state average; illustrative here, sourced from HUD CHAS in production). Underserved = need above 1.00 and households served per 1,000 residents more than 5% below the state rate. County activity is stacked from the same rows that feed every exhibit, so the answers always reconcile to the KPI row.
Exhibit 2 · Trend
Homebuyer loans closed by month — FY2026 vs FY2025
24 months, July through June. Solid = selected fiscal year; dashed = prior fiscal year.
Exhibit 3 · By program
Households served by program
Homebuyer loans, Housing Choice Voucher households, multifamily units financed or preserved.
Exhibit 4 · By county
Households served by county, ranked
Bars are stacked by program; the pale marker shows each county's share of state population for comparison.
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.
