MillerKnoll AI
AI Analytics

Data Assistant

ProductionMichael Pietrangelo

Ask the AI Analytics Dashboard a question. The Data Assistant knows which tab you’re on, answers from the dashboard’s own figures, and never makes up a number.

Executive Summary

The story, in brief.

The AI Analytics Dashboard shows leaders what AI costs and who is using it. The Data Assistant lets them ask it questions. It knows which tab they’re on, it knows how MillerKnoll is organized, and it answers from the dashboard’s own numbers, fast enough to use in the middle of a meeting.

~6s
Warm answer, streamed as it’s written
47–150s
The same answers through the old Power Automate flow
Page-aware
Reads the tab on screen, including the forecast
0
Invented numbers — every figure is sourced
Architecture

How it’s built.

The assistant lives in a panel on every tab of the AI Analytics Dashboard. Each question goes out with a snapshot of what’s on screen and the monthly figures the page has already loaded. The model answers straight from those when it can. When it can’t, it calls one of six narrow tools over the dashboard’s own data files, and the answer streams back as it’s written.

AI Leverage

What AI actually does here.

Flow → Function
47–150s → ~6s

From minutes to seconds

Moving the hot path off Power Automate and streaming the answer turned a wait people would abandon into a conversation.

Page-aware
the tab on screen

Context without a prompt

The assistant already knows what you’re looking at, so questions can be as short as “why did this jump?”

Sourced figures only
no estimates

Trust by construction

Every number is traceable to the dashboard, and arithmetic shows its inputs — the property that makes an assistant usable by a leadership team.

Collaborators

Built with the business, not for it.

Michael Pietrangelo
Director, AI Enablement & Knowledge — built the dashboard and the Data Assistant.
Andrew Stoddard
Enterprise Apps — co-built the AI Analytics Dashboard and its data feeds.
Cory Whipple
Enterprise Apps — stood up the Azure Function App, its Key Vault access and monitoring, then linked it behind the dashboard’s sign-in so only signed-in users can reach the assistant.
Mark Buikema
CTO — business stakeholder for the AI Analytics Dashboard.