There’s a pattern to how new technology reaches the world. Wave after wave, from the PC to the relational database to the cloud, new technology reaches developers first, and finance is often next. For finance professionals, a better tool is an edge and the job is to model reality a little more precisely than you could yesterday. For decades, that tool has been Excel: where the quarter gets closed and the forecast gets argued line by line, where every number traces back to a source.
So when AI enters finance, it has to clear the same bar: showing its work, using trusted data and tracing every calculation. Plenty of AI tools claim to be built for finance; Microsoft 365 Copilot in Excel is proving it in practice.
Across Financial Planning and Analysis (FP&A), Accounting, Tax, Compliance, and Treasury, Microsoft Finance runs Copilot in Excel in real workflows, spending less time hunting for information and rebuilding analyses, and freeing teams to spend time applying judgement to decisions. They shape it as much as they use it, telling us where it falls short and pushing the product toward the standard their own work demands. By the time it reaches you, it has already been pressure-tested by a finance organization operating at the frontier.
Today, we’re introducing new features built for financial professionals to continue doing that with skills for repeatable workflows, new financial connectors for trusted data, and improved capabilities for traceability.
Before new Copilot capabilities ship in Excel, we evaluate them across graded levels of task complexity and benchmarks that reflect the work finance teams do every day, ensuring it can deliver multi-step workflow with a trusted and verifiable result rather than just complete a single task. For more on how we test, get an inside look at our evaluation framework, benchmarks, and domain-specific approach for finance.
Meeting the high bar of professional finance work isn’t something we’ve done alone. We’ve also partnered with Financial Modeling Institute (FMI), the global body that credentials the industry’s most demanding modelers. Its library of real-world financial modeling cases has become a foundational part of how we evaluate Copilot in Excel for finance work.
Today, we’re introducing skills that let teams define how Copilot should complete common processes such as building a DCF, closing the books, refreshing a monthly reporting model, or preparing a variance analysis. Instead of starting from scratch each time, a skill guides Copilot through the steps, applying the right structure and formatting, and helping produce an output that is easier to review, reuse, and trust.
A library of sample finance skills is now available, and you can build your own custom skills using an open-standard markdown file. Save a SKILL.md file in your OneDrive, and Copilot will pick it up to build a three-statement model or a board package using the process you define for it. Learn more on how to create, use, and manage skills here.
Developers and partners can soon build and deploy skills through Microsoft Marketplace and Microsoft 365 Admin Center. We’ve already begun working with a first wave of partners, including finance and ERP solutions like LSEG, Ramp, Rogo, Samaya AI, Velixo, and Vena.
Copilot can also adapt to how you like to work in Excel. With Personalization, you can set preferences once and have Copilot apply them consistently, while workbook rules capture structure, naming, and formula conventions as a sheet in the workbook that follows the file.
Copilot in Excel connects directly to the data financial professionals rely on, bringing market data, fundamentals, and research directly into the workbook so analysis starts from the latest sources instead of manual data pulls. In addition to the LSEG and Moody’s connectors we released in May, today we’re expanding your options with more financial data connectors for bringing public and private market data into Copilot in Excel.
Note: Third-party connectors and data providers may require separate licensing or subscriptions from the respective provider. Learn more here. FactSet is in preview and will be generally available in July.
Combined with Work IQ for grounding in work context, these features unlock real scenarios finance teams work on every day. A few example prompts you can now try with Work IQ, skills and connectors (Note: external data mentioned in the below prompts may require one or more connectors).
In finance, the answer alone isn’t enough. You need to know how you got there. Whether updating a forecast, refreshing a board reporting model, or reviewing changes before quarter close, finance teams need the same things they’ve always demanded from Excel: visibility into what changed, confidence in the methodology, and a clear trail.
That’s why you can now choose to Plan with Copilot before taking action, outlining which ranges, worksheets, formulas, and assumptions it intends to update along with clarifying questions. Once changes are made, every edit remains traceable, with links back to affected cells and changes are now attributed to Copilot alongside the work of collaborators in the Show Changes pane.
The result is a Copilot that works more like a trusted analyst: proposing a path forward, explaining its approach, and making every change transparent and reviewable.
Personalization, workbook rules, pre-built skills, federated Copilot connectors, Plan with Copilot, and Copilot attribution in Show Changes are generally available for Microsoft 365 Copilot customers across Excel for Web, Windows, and Mac.
Custom skills are available today via the Insiders channel for Windows and Mac, and rolling out to general availability across Excel for Web, Windows, and Mac next month.
Partner-built skills are coming in Q3 2026. Learn more here about building and deploying skills.
The features described in this post are rolling out progressively to Microsoft 365 Copilot customers. Specific availability, supported regions, and licensing requirements may vary.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。