This is an old revision of the document!
Standard Operating Procedure for generating AI Health and AI Monitoring Performance reports from the Affirm Power BI tenant.
| Field | Value |
|---|---|
| Document Owner | MS Cloud AI team |
| Applies to | Affirm Power BI Tenant — Synergist Technologies, LLC |
| Version | 1.0 |
| Classification | Internal |
—-
This Standard Operating Procedure (SOP) defines the end-to-end steps for generating, validating, and delivering Power BI reports for Affirm clients from the Affirm Power BI tenant. It covers two report templates published under the Synergist Technologies, LLC workspace:
This document is intended to standardize the report generation process so that any qualified operator can produce consistent, accurate, audit-ready outputs without ad-hoc decisions.
| Term | Meaning |
|---|---|
| Tenant | A Microsoft 365 / Power BI organizational boundary. The Affirm tenant is accessed by switching from your default tenant to Synergist Technologies, LLC. |
| AI Asset | An AI/LLM-powered solution being monitored, e.g., CloudGenie - Chat, Jenkins AI Copilot, SOW Analyzer. |
| Evaluator | A metric family used to measure an AI asset (Hallucination, Groundedness, Prompt Relevance, Response Relevance, Readability, Latency, Throughput, Toxicity, etc.). |
| Method | The specific technique used by an evaluator: LLMaJ (LLM-as-Judge), FRES, SMOG, Fluency, Parallel, Sequential, etc. |
| Normalized Score | An evaluator score rescaled to a comparable 0–100 range for cross-metric reporting. |
| Trending Days | Lookback window (in days) used to compute the trend % shown on AI Health snapshots. |
| Snapshot | A single row of evaluator output for a specific date, asset, and method. |
Before starting this procedure, confirm ALL of the following are in place. If any item is missing, stop and contact the Tenant Administrator.
This section is common to both reports. Complete steps 6.1 through 6.4 before moving to Section 7 or Section 8.
<note important>Important: If the link opens but reports are not visible, you are still in your default tenant. Continue to step 6.2 to switch tenants.</note>
On the Home page you should see the following two reports listed under the Recommended section and in the Recent list:
<note>Both reports use the same filter pattern.
AI Health Report and AI Monitoring Performance Report share a near-identical filter pane: Organization Name, AI Asset Name, Evaluator Name, Method Name, and a Date / Date Range filter. Mastering the filter pane once applies to both reports. The differences are summarized in Section 7 (performance) and Section 8 (health).</note>
Use this report to evaluate the performance of one or more AI assets across selected evaluators and methods, over a specific reporting period.
The Date filter controls the reporting window. Power BI offers four filter types; pick the one that best fits the request.
Use when the requestor provides explicit start and end dates.
is, is not, is after, is on or after, is before, is on or before, is blank, is not blank.is on or before for the end date).Use when the requestor needs to cherry-pick specific calendar dates.
Use for rolling windows that should auto-shift each time the report is regenerated.
is in the last, is in this, or is in the next.days, weeks, months, years, calendar months, or calendar years.Use only for intra-day reports. Resolution is hours or minutes.
is in the last, is in this, or is in the next.hours or minutes.<note warning>Date filter caveat: Mixing filter types on the same field is not supported in a single render. If you switch from Advanced to Basic, the previous values are cleared. Confirm the date range with the requestor before switching.</note>
The Organization Name identifies the client whose data is being reported. The document uses “CDW Internal” as the example client.
<note warning>Always confirm exactly one organization is selected. Selecting multiple organizations will mix client data into the same report. This is a data-confidentiality violation. Reviewer must verify in Section 10.</note>
Select the AI Assets in scope. The report renders separate views per asset selected.
Choose which evaluators (metric families) should appear in the report.
Each evaluator can be computed by one or more methods. For example, Readability supports FRES and SMOG.
<note>Method–Evaluator pairing: Some methods only apply to specific evaluators (e.g., FRES and SMOG only apply to Readability). Selecting an irrelevant method has no effect on the report but adds clutter to the filter audit trail. Pick only the methods aligned to the chosen evaluators.</note>
The AI Health Report shares the Organization / AI Asset / Evaluator / Date filter pattern with the Performance Report, plus two additional filters specific to health monitoring: Trending Days and is_normalized.
Apply the following filters in order, using the same procedures as for the AI Monitoring Performance Report:
Trending Days defines the lookback window used to compute the Trend % column shown in the AI Health Snapshots table. The default value is 0.
is, then enter the desired number of days (e.g., 7, 14, 30).<note>Choosing Trending Days: Pick a window proportional to the report's date range and the volatility of the metric. 7 days suits high-volume daily monitoring; 30 days suits low-volume monthly review. Avoid windows longer than the date range itself — the trend will be meaningless.</note>
is_normalized determines whether the Actual Normalized Score column on the AI Health Snapshots page uses normalized values.
<note>When to use normalized scores: Use normalized scores (True) when comparing different evaluators or metrics that have different native scales (e.g., comparing Latency in milliseconds against Readability scores). Use raw scores (False) when the requestor needs the original measurement values.</note>
Navigate to the 2- AI Health Snapshots page. The table shows one row per Evaluator × Method × Data Type combination.
Columns to verify:
Follow the same export procedure as Section 6.8. PDF is the default delivery format unless the requestor specifies otherwise.
Following are the details of Affirm support, in case of any Power BI Access Issue or Technical issue. Teams Channel: CDW AFFIRM Support Chat