In Short: A Useful Assistant on a Good Model, a Confident Liar on a Bad One
Copilot in Power BI does four distinct jobs: it drafts report pages from a prompt, summarises what visuals show, answers natural-language questions against your semantic model, and helps authors write and understand DAX. Used on a clean, well-described model, each of those saves real time. Used on the average inherited dataset, it produces fluent answers that are wrong in ways a casual reader cannot detect.
That is not a reason to avoid it. It is a reason to treat Copilot readiness as a data quality project rather than a licence purchase. The switch is easy to turn on; the trust is earned in the semantic model.
What Copilot Actually Does Today
Report drafting. Give Copilot a prompt like "create a page summarising sales performance by region and channel" and it produces a first-cut report page using the fields and measures in your model. The output is a starting point: layouts are serviceable, visual choices are reasonable, and an experienced author will still rearrange most of it. As a way past the blank page, it works.
Summaries and narratives. Copilot generates plain-language summaries of a visual, a page or a whole report: trends, outliers, notable movements. For executives who receive reports by email and want the reading done for them, this is quietly one of the most-used features. The summaries describe what the data shows; they do not know why, and they occasionally emphasise the wrong thing.
Data Q&A. Viewers can ask questions in natural language and get answers resolved against the semantic model, including simple visuals generated on the fly. This is the feature that inherits every strength and weakness of your model, and the one connected to the broader Fabric IQ grounding story that carries the same answers into Teams and Outlook.
Update, 29 September 2026: Microsoft announced at FabCon Europe 2026 that Power BI content in Microsoft 365 Copilot - Fabric IQ in Copilot Chat and Copilot Cowork - is generally available, with Copilot inferring which report or semantic model is right for each question. Microsoft also says the same Microsoft Copilot experience is coming to Copilot in Power BI, using Microsoft 365 data for richer responses. On governance, sensitivity labels, DLP policies and information protection controls now flow into Microsoft Copilot experiences, and a Restrict from Copilot control lets administrators decide which semantic models can participate in AI experiences. More in our FabCon Europe 2026 recap.
Update, 30 September 2026: Microsoft's Power BI September 2026 feature summary fills in the detail. Microsoft 365 Copilot integrated into Power BI and Fabric is in preview, behind a new Fabric admin portal setting that is off by default and independent of the standalone Copilot setting; the initial preview needs a Microsoft 365 Copilot licence, with a broader audience to follow at no stated date. In report view, viewers can also enable Fabric IQ from the Copilot pane for multi-step answers that show reasoning steps and the underlying DAX query. A new per-model setting lets users with write permission block read-only users from reaching a semantic model through Copilot and Microsoft's MCP tools - Microsoft's sources describe it differently from the administrator-level Restrict from Copilot control, as we explain in Microsoft 365 Copilot in Power BI and controlling AI access.
Update, 8 October 2026: The older Q&A feature is on its way out. Microsoft has moved the retirement of Power BI Q&A, its legacy natural-language experience including the Q&A visual and Q&A Setup, to February 2027. After that, existing reports that contain Q&A visuals will show an error in place of the visual. Copilot is the recommended replacement, and Microsoft says Copilot is now available across all Fabric capacities starting at F2, with Fabric Copilot Capacity also available on F2 and above. There are no plans for a Copilot replacement for Q&A in embedded (PaaS) scenarios. Our guide to the Power BI Q&A retirement maps each Q&A surface to its replacement.
DAX and modelling assistance. In Power BI Desktop, Copilot writes measures from a description, explains what an unfamiliar measure does, and suggests descriptions for model objects. For developers this is the least glamorous and most reliably useful capability: explaining an inherited model's 400-line measure is exactly the kind of work machines should do.
Where It Falls Short
A candid list, from experience across client estates.
- It cannot fix a bad model. Copilot resolves your words against the model's names and relationships. Cryptic names, missing descriptions and wrong relationships produce wrong answers delivered with total confidence
- Summaries lack business context. A revenue dip caused by a known contract timing issue will be narrated as a concerning trend, because Copilot does not know what you know
- Report drafts are generic. Useful scaffolding, but they follow no design system and ignore your organisation's reporting conventions
- Capacity dependency. Copilot consumes Fabric capacity units. Heavy use on a small capacity competes with refreshes and queries, and the accounting surprises teams that have not planned for it, something we cover in what Copilot in Fabric costs
- Non-determinism. The same question can produce differently phrased answers on different days. For governed reporting where numbers must be reproducible, that property needs managing
The Preparation That Makes It Work
Every improvement that helps Copilot also helps humans, which is why we recommend the preparation regardless of AI plans.
- Rename tables, columns and measures into the language the business actually uses
- Write descriptions on every measure that matters: what it means, how it is calculated
- Verify relationships and keep the model a proper star schema, per our star schema guide
- Hide keys, technical columns and deprecated objects so Copilot cannot select them
- Test row-level security under a viewer account, because Copilot answers respect RLS and a misconfiguration becomes very visible
The full checklist, including linguistic tuning and endorsement, is in our guide to preparing your semantic model for AI.
Should You Turn It On?
For most organisations on paid Fabric capacity: yes, for authors first. The DAX and documentation assistance carries near-zero risk and immediate productivity value. Viewer-facing Q&A and summaries deserve a staged rollout: pick two or three models you trust, prepare them properly, enable Copilot for a pilot group, and review what people ask and what they were told. Expand on evidence, not enthusiasm. Restrict from Copilot, announced at FabCon Europe 2026, is the natural mechanism for that staging: keep unprepared models out of AI experiences until they are ready.
The teams that regret Copilot are almost always the ones that switched it on estate-wide against unprepared models and spent the next quarter explaining discrepancies. The technology was fine. The foundations were not.
Sources and Further Reading
- Copilot for Power BI introduction
- Copilot in Fabric overview
- Row-level security in Power BI
- Power BI's next chapter: The evolution of business intelligence (Microsoft)
- Power BI September 2026 Feature Summary (Microsoft)
Frequently asked
Four things in practice: draft report pages from a prompt, summarise what a visual or report shows in plain language, answer data questions against the semantic model, and help authors write and explain DAX measures. Authoring features live in Power BI Desktop and the service; consumption features appear for report viewers.
Yes. Copilot features are billed against Fabric capacity, and your tenant needs a paid capacity with Copilot enabled by an administrator. The original F64 requirement has gone: Microsoft says Copilot is now available across all Fabric capacities starting at F2, and Fabric Copilot Capacity can also be created on F2 and above, with consumption metered against capacity units.
Yes. Microsoft is retiring the legacy Power BI Q&A experience, including the Q&A visual and Q&A Setup, in February 2027, after which reports containing Q&A visuals will show an error in place of the visual. Copilot is the recommended replacement for each Q&A surface, except embedded (PaaS) Q&A, for which Microsoft has no Copilot replacement planned.
It is as accurate as the semantic model it queries. Against a well-named, correctly related model with described measures, answers are generally reliable because they resolve to real queries. Against a cryptic or poorly modelled dataset, Copilot guesses at meaning and can produce confident, wrong answers.
No. It accelerates a developer - drafting DAX, explaining unfamiliar measures, producing first-cut report layouts - but the judgement work of modelling, performance tuning and understanding the business question remains human. Treat it as a productivity multiplier, not a replacement.
The usual reasons: your workspace is not on a paid Fabric capacity, an administrator has not enabled Copilot in the admin portal, your region requires cross-geo processing consent that has not been granted, or the feature is limited for your capacity size. Work through those in order.
Rename tables and measures into business language, add descriptions, verify relationships, hide technical clutter and test row-level security. Microsoft also lets you mark preferred (endorsed) models. The same preparation improves human self-service, so none of the effort is wasted.
