SAMPLE: Dexis Portfolio Ledger · Prepared for Meghan

Portfolio Ledger — QMS, version two.

The QMS model already running in your Power BI tenant scores every project on CPAR, QQCCI, PPP and the Employee Thermometer. This board joins those scores to the Controller's numbers — funded value, period of performance, burn vs plan, revenue by agency, indirect rate and unbilled AR — through the same Project Name Mapping dimension, so one filter drives both.

Where the portfolio sits

Contracts and funded value by region

Trend · 24 months

Monthly revenue recognized vs. plan

Revenue recognizedPlan (funded ÷ months of PoP)Selected period

What this board answers

Three questions a Controller asks at month-end

Signature view · Period-of-performance burn ribbons

Funds burned vs. time elapsed, by contract

Funds burnedRemaining funded valueToday (Sep 2026)▲ overburn >5pp▼ underburn >5pp

Contract · agency

Period of performance (Oct 2022 → Sep 2030)

Burned vs elapsed

Table view · all contracts in this view

Breakdown · by client agency

Revenue in period, with portfolio QMS score

QMS scores · the model you already have

CPAR · QQCCI · PPP · Employee Thermometer

AI layer

Auto-drafted month-end note & ask-the-data

YOU ASKED ·

Answers are computed from the filtered model on this page · in production: Copilot / Fabric AI skill over the DexisOnlineDataModel semantic model, grounded in the same measures.

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.