Study · November 8, 2026
What would an AI have to guess?
We ran FactCraft's audit on 53 public Power BI semantic models from GitHub: 1,404 tables, 6,374 measures, 1,424 relationships, read as metadata. What a model declares is what an agent can read about a measure: its name, its description, its DAX. Most of these models say very little.
48 of 53
models came back Not ready for AI: Copilot has no AI instructions to follow.
44 of 49
models with visible measures leave some of them undescribed.
13
models carry measures with identical DAX. Some of those are wrong numbers.
The verdicts
A good score does not make a model ready.
48 Not ready for AI
1 Fix before plugging in AI
4 Ready for AI
81Median score 81 / 100
Rule by rule
What the audit found.
| Rule | Models affected | Findings |
|---|---|---|
| Visible technical columnFC-LIS-05 · minor | 50 of 53 | 2,148 findings |
| AI instructions missingFC-IA-04 · blocking | 48 of 53 | 48 findings |
| Visible measure without a descriptionFC-LIS-01 · important | 44 of 49 | 4,572 findings |
| Missing or automatic date tableFC-STR-02 · important | 37 of 53 | 147 findings |
| Same generic column name in several tablesFC-COH-04 · important | 34 of 53 | 506 findings |
| Visible measure without a formatFC-LIS-06 · minor | 28 of 49 | 496 findings |
| Visible table with no relationshipFC-STR-05 · minor | 28 of 53 | 127 findings |
| Measure and column with the same nameFC-COH-03 · important | 24 of 49 | 162 findings |
| Bidirectional relationshipFC-STR-01 · important | 23 of 53 | 121 findings |
| Implicit measures allowedFC-IA-01 · blocking | 22 of 52 | 247 findings |
| Cryptic name on a visible objectFC-LIS-03 · important | 20 of 53 | 437 findings |
| Two measures with the same DAXFC-COH-01 · important | 13 of 48 | 52 findings |
| Several filter paths between two tablesFC-STR-03 · blocking | 13 of 53 | 53 findings |
| Description that says nothingFC-LIS-02 · important | 4 of 19 | 84 findings |
| No figure definedFC-IA-06 · blocking | 4 of 53 | 4 findings |
| Visible copy or obsolete objectFC-LIS-04 · important | 3 of 53 | 9 findings |
| Calculated column that aggregatesFC-STR-04 · important | 3 of 12 | 7 findings |
Every bar uses the same scale: the full width is all 53 models. The solid bar shows the models a rule affects, the faint bar the models it applies to.
What stands out
Four patterns behind the numbers.
- 01
Almost no model tells Copilot what to do.
48 of 53 models carry no AI instructions: no business terms, no measure behind each key figure, no default date. They are the piece that moved Copilot's answers when we tested it.
- 02
The meaning is missing.
4,572 of 6,055 visible measures have no description (76%). 30 of the 49 models with visible measures describe none of them. The 5 that describe them all are demos and portfolio projects. Copilot does not use these descriptions to answer, but an agent reading the model has little else.
- 03
A description is not always an answer.
Of the 19 models with descriptions to read, 4 carry 84 descriptions that say next to nothing: they repeat the name of the measure, or stop at three words or fewer.
- 04
Duplicates can hide wrong numbers.
13 models have measures with identical DAX (52 findings). We read about ten cases by hand. Most are two names for one total. Some are wrong numbers: a two-year comparison that returns last year's gap, a margin that returns the profit amount. The formula runs without error, so Power BI has nothing to report.
How to read this
What these numbers can and cannot say.
This is not a random sample.
GitHub code search found 999 models in repositories under a permissive license, forks left out. We picked 53 by hand for variety: sectors, languages, sizes. Some we picked because they are well described, and 4 because they ship AI instructions, which makes both look more common here than they may be. Many are demos, samples or portfolio projects. Company models may look better or worse: these figures describe these 53 models, not the market.
What we tested on Copilot.
These 53 models never went through Copilot: this page shows what they declare, not what Copilot answered. Separately, we asked Copilot 15 questions on one fictional model in four versions, once each, on a paid F2 capacity (November 2026). Right figures out of 15: 11 with no preparation, 10 with descriptions only, 13 with AI instructions, 13 with descriptions, instructions and an AI schema. One model, one pass, and instructions written knowing the questions: a direction, not a rate. It matches Microsoft's documentation (July 2026): Copilot's answers about a model depend on the AI schema, verified answers and AI instructions; descriptions only count for search and DAX queries.
The rules are FactCraft's own.
So are the score and the verdict, and FactCraft sells what comes after the audit. Keep that in mind, and run the audit on your own model to judge the rules for yourself.
Metadata only.
The audit reads declarations: names, types, descriptions, DAX, relationships. It never reads data. It looks for AI instructions in the model's linguistic schema, where Power BI Desktop saves them, and in the project's Copilot folder: instructions kept elsewhere are not seen.
No model is named.
The figures on this page describe the set as a whole. The models were under the MIT or Apache 2.0 license, read as text and never run. Audited on November 8, 2026.
Run the same audit on your model.
It is free and runs in your browser: your model never leaves your machine.