Skip to content

Getting Started

This guide walks you through signing in to BI Pixie, exploring the BI Pixie portal, and getting ready to add Pixies to your first Power BI reports. You can start tracking in minutes.

Step 1: Sign In

  1. Go to app.bipixie.com.
  2. Select Sign in with Microsoft.
  3. Sign in with your Microsoft work or school account (the same account you use for Power BI).
  4. If this is your first time, BI Pixie will provision your account automatically. You will be redirected to the Overview page.

Note: BI Pixie uses Microsoft Entra ID (Azure AD) for authentication. There is no separate registration form. Your account is created when you first sign in.

When you return later, BI Pixie shows "Welcome back" on the sign-in page, and you can sign in again in one step.

If your organization's policy blocks sign-in

Some organizations restrict which applications users can sign in to. If you see an error like "Need admin approval" or "AADSTS65001", your Microsoft Entra ID tenant requires an administrator to approve BI Pixie before you can use it. To resolve this:

  1. Send your IT administrator Permissions and Data Access, which lists every permission BI Pixie requests with the reason it is needed, and states what BI Pixie reads, writes and stores. That page is written to be read on its own by somebody with no BI Pixie account.
  2. If your organization uses the Microsoft Entra admin consent workflow, you can request approval from the screen that showed the message. Your administrator reviews the request under Enterprise applications > Admin consent requests.
  3. Once your administrator approves BI Pixie under your organization's process, sign in again.

None of the permissions BI Pixie requests requires an administrator. This approval is needed only because your organization's own policy requires it. If you need more help, contact us.

Step 2: Explore the Overview Page

After signing in, you land on the Overview page. This is your home base in the BI Pixie portal, and it opens with two sections:

Welcome Guide

The Welcome Guide is a collapsible set of cards that explain what BI Pixie is and how it works. It includes a table that compares what BI Pixie tracks with what native Power BI tracks (page views, visual clicks, filter selections, bookmarks, tooltips, drill-through, and more). You can close the Welcome Guide and reopen it any time with the "Show Welcome Guide" link.

The Welcome to BI Pixie guide on the Overview page of the BI Pixie Portal, with its AI Readiness section open. The section describes three problems: optimizing semantic models at scale, wrong answers that look like right ones, and staying correct as semantic models change. It then shows the three steps BI Pixie offers, which are Assessments, Optimizations, and Benchmarks.

Getting Started Checklist

The Getting Started checklist lists the steps of your initial setup. Its first steps are:

  1. Connect to Power BI: Links to the Add Pixies page where you connect your Power BI account.
  2. Add Pixies to your first report: Links to the Add Pixies page to add Pixies to a report.
  3. Install BI Pixie Dashboard: Install the Power BI template app to analyze your data.

After you add Pixies to your first report, the checklist expands with additional steps like enabling feedback controls, adding surveys, enabling RLS tracking, and inviting team members. BI Pixie adapts the checklist to your plan and role.

Where to See Your Usage

To see your usage metrics, open the Account page from the left sidebar and select the Usage tab. On the Usage tab you see your plan, followed by your metrics organized into sections: License (plan allowances), AI Readiness (assessment and benchmark allowances), Limits (daily quotas), and Activity (engagement data and trends):

  • Tracked Items: How many of your plan's tracked items are in use. A tracked item is a report with Pixies, or a semantic model or data agent you are preparing for AI; see What Counts as a Tracked Item for the full definition.
  • Sessions: Your sessions this period against your plan's fair-use allowance. A session is one person using one report on one day. Sessions are never billed; see Data Retention at Extreme Usage for how the allowance works and what happens far beyond it.
  • Benchmark runs and Free first-look assessments: Your AI Readiness allowances and how much of each you have used.
  • Data Refreshes: How many data refreshes your BI Pixie Dashboard used today.
  • Active Users (30 days): Unique users interacting with your reports in the rolling 30-day window.
  • Tracked Reports: How many of your reports with Pixies have received event data.
  • Latest Activity: When the most recent event was received.
  • Retention: How many days of event history you are storing.
  • Data Captured: Total size of your stored event data.
  • Daily Average: Average data captured per day across your tracking period (shown when data spans multiple days).

Step 3: Connect to Power BI and Add Pixies

To start tracking, you need to connect your Power BI account and add Pixies to at least one report.

  1. From the Overview checklist, select Connect to Power BI.
  2. Select Connect to Power BI to sign in and grant BI Pixie access to your workspaces.
  3. Select a workspace and choose which reports to track.
  4. Choose whether to download the report definitions as a ZIP for testing or use auto-save to write directly to your workspace. See Add Pixies to Your Reports for more details.
  5. Select "Download with Pixies" or "Save to Power BI" to add Pixies to the selected reports.

See Add Pixies to Your Reports for the complete walkthrough.

Step 4: Score Your First Semantic Model

With report tracking, you see how people use your reports once they have used them for a few days. With AI Readiness, you learn something different right away: how well prepared your semantic models are for Copilot and for Fabric data agents. An assessment needs no report activity, so this is the fastest useful thing you can do on your first visit.

  1. Open AI Readiness from the left sidebar.
  2. Select Start assessment and pick a semantic model. You can select several and assess them in one run.
  3. Read the AI Readiness score, 0 to 100, with its band. One score covers Copilot and Fabric data agents alike, and your descriptions, AI Instructions, and AI data schema all count toward it.
  4. Open Why this score? for the points BI Pixie deducted for each dimension, then open Optimize semantic model below the score card to review the fixes BI Pixie can write for you.

Scoring is read-only: nothing is written to your semantic model. Once the semantic model's reports are tracked and have collected some usage, you can reassess the semantic model. BI Pixie then grounds the score in what people actually click, and both the score and the order of the findings become sharper.

What's Next