OpenAI has launched ChatGPT for Excel, a new add-in that embeds ChatGPT directly inside Microsoft Excel workbooks, allowing users to build financial models, analyze data, and update spreadsheets using natural-language prompts. The tool is designed to help users do more in Excel, enable power users to move faster, and improve consistency across teams working with complex spreadsheet models.

For many organizations that rely on spreadsheets for financial modeling and operational planning, the announcement raises a practical question: should AI assistants now be integrated directly into spreadsheet workflows instead of relying on manual modeling and analysis?

The feature runs on GPT-5.4 Thinking, OpenAI’s newest reasoning model optimized for financial workflows, and launches alongside new financial data integrations connecting ChatGPT to market-data platforms including Dow Jones Factiva, Moody’s, MSCI, S&P Global, LSEG, and FactSet.

The update primarily affects financial analysts, accountants, strategists, and enterprise teams who rely on Excel for modeling, forecasting, and operational decision-making.

In short: ChatGPT for Excel is an AI-powered assistant embedded inside Microsoft Excel that helps financial teams build models, analyze data, and run scenarios.

ChatGPT for Excel is a new AI-powered spreadsheet assistant that allows financial professionals to build, analyze, and update Excel models using natural-language prompts powered by OpenAI’s GPT-5.4 reasoning model.

The new Excel add-in places a ChatGPT panel directly inside spreadsheets, allowing users to interact with their data using natural-language prompts.

Instead of manually constructing models or debugging formulas, users can describe what they want in plain language. ChatGPT then generates or updates spreadsheet models using the same formulas and workbook structures teams already rely on in Excel. Analysts, strategists, researchers, and accountants can use the tool to move faster, reduce manual work, and spend less time writing formulas, tracing links, or fixing models.

Build and update spreadsheet models faster.
Rather than constructing models or running scenario analysis step by step, users can describe the outcome they need and let ChatGPT generate or update the spreadsheet directly in Excel. Teams can perform tasks such as data analysis, reporting, inventory tracking, and budgeting while preserving the formulas, assumptions, and structure of an Excel-native workbook.

Get insights from large spreadsheets without manual reconciliation.
ChatGPT can analyze large or complex workbooks, understanding how sheets and formulas connect across a model. It can explain why outputs change, trace and fix calculation errors, and show how assumptions affect results. This can be especially helpful when users inherit existing spreadsheet templates, need to quickly understand a model, or want to test assumptions before making decisions.

Follow the logic and trust the outputs.
As it works, ChatGPT explains the steps it is taking and references the exact spreadsheet cells involved. Because calculations still run natively inside Excel, teams can audit formulas, trace assumptions, and verify how results were produced using the same spreadsheet logic they already trust. Before modifying a workbook, ChatGPT asks for confirmation, allowing users to review or undo edits if needed.

The feature is rolling out in beta to ChatGPT Business, Enterprise, Edu, Teachers, Pro, and Plus users in the United States, Canada, and Australia. In Enterprise, Edu, and Teacher workspaces, access is disabled by default and must be enabled by administrators.

OpenAI also said ChatGPT for Google Sheets is planned next, extending the AI spreadsheet assistant beyond Microsoft’s ecosystem.

The Excel integration is powered by GPT-5.4 Thinking, OpenAI’s newest reasoning model optimized for financial analysis and spreadsheet workflows.

GPT-5.4 Thinking is also available in ChatGPT, Codex, and the OpenAI API. OpenAI says the model was refined with input from finance professionals to improve real-world financial analysis workflows, helping teams move faster and maintain greater consistency across their work.

According to OpenAI, the model was tested on real-world financial tasks such as:

In OpenAI’s internal investment banking benchmark, GPT-5.4 Thinking achieved the highest score among the models shown:

The benchmark evaluates real-world investment-banking workflows, such as building three-statement financial models with proper formatting, calculations, and citations.

For teams working in financial workflows, OpenAI is expanding how ChatGPT connects to professional data sources. With GPT-5.4, ChatGPT can also process longer context and handle more complex financial analysis tasks, helping teams move faster on company research, model updates, and producing cited outputs used in valuation, due diligence, underwriting, and related workflows.

Organizations can build their own apps using Model Context Protocol (MCP) to connect proprietary datasets and internal research, allowing market data, company information, and internal analysis to be brought together into a single workflow inside ChatGPT.

Alongside MCP support, OpenAI is introducing new financial data integrations that allow ChatGPT to access professional research and market-data providers directly.

New connectors include:

These integrations allow analysts to move from gathering information to analysis inside the same workflow, rather than manually exporting data between research tools, spreadsheets, and reporting documents—helping teams spend less time assembling inputs and more time producing cited outputs such as earnings summaries, valuation snapshots, and credit memos.

With access to both external market data and internal datasets, teams can generate structured outputs such as:

Teams can also use research apps inside ChatGPT to pull information from filings, transcripts, investor decks, and spreadsheets to generate structured, cited outputs that can be exported to formats such as PDF or Microsoft Word. OpenAI says recent updates also give users more control over the research process, including the ability to focus analysis on specific data sources, adjust the research plan during a run, and review citations in a redesigned workspace.

OpenAI says the integrations are designed to help financial professionals spend less time assembling data inputs and more time producing analysis and decision-ready outputs.

OpenAI emphasized that ChatGPT Enterprise includes security, governance, and access controls designed for organizations operating in regulated or data-sensitive environments.

Enterprise capabilities include:

OpenAI says that data shared with ChatGPT Enterprise is not used to train or improve its models by default.

In Enterprise, Edu, and Teacher workspaces, ChatGPT for Excel is disabled by default and must be enabled by administrators.

OpenAI says it is working closely with financial institutions as they deploy ChatGPT across workflows such as research, underwriting, auditing, client engagement, code modernization, and operations. Across banks, asset managers, and insurance firms, the company says the technology is already being applied to tasks including due diligence, client experience, and investment research as organizations expand their AI deployments.

Amr Ellabban, Head of AI at Hg, said ChatGPT has accelerated research and due-diligence workflows across the firm:

“ChatGPT has materially accelerated our research and due diligence workflows—from financial analysis and market research to legal review and writing internal memos—while improving consistency across teams. It has expanded our team’s capacity, freeing our investment professionals to focus more time on judgment, debate, and conviction. We’re excited to be early adopters of new capabilities and to help shape how AI transforms financial services in the years ahead.”

Daniel Swiecki, Head of AI Solutions at Walleye Capital, said GPT-5.4 significantly improved performance in financial modeling tests:

“On our toughest internal finance and Excel evaluations, GPT-5.4 outperformed prior models, improving accuracy by 30 percentage points. This step change in reliability materially expands our automation of model updates and scenario analyses for fundamental investors.”

Morito Emi, Group Chief Data Officer, said the company is using AI to rethink how teams and decision-making processes operate:

“Together with OpenAI, we’re moving beyond incremental digital transformation to become AI-native—redesigning processes, teams, and decision-making with AI as a foundation. While maintaining strong security and governance, we’re boosting execution and productivity and accelerating value creation across the organization.”

Organizations including banks, asset managers, and insurance companies are already applying ChatGPT across workflows such as investment research, underwriting, auditing, and client engagement.

OpenAI says organizations can learn more about its enterprise-grade security, privacy, and compliance programs through its documentation and developer resources.

Enterprise customers can build directly with OpenAI or work with consulting and implementation partners such as Accenture, Bain, Boston Consulting Group (BCG), McKinsey & Company, and PwC to integrate AI into existing data systems, applications, and operating models.

OpenAI’s move into spreadsheets comes as AI companies compete to embed assistants directly into workplace software.

Microsoft’s Copilot is already integrated across Excel and the broader Microsoft 365 ecosystem, offering AI-assisted spreadsheet analysis and formula generation.

At the same time, companies such as Anthropic are expanding Claude into developer tools and productivity environments, while AI agents are increasingly being used to automate spreadsheet-based analysis and financial workflows.

These developments reflect a broader push across the AI industry to bring generative AI directly into the software tools where business data already lives.

Q: What is ChatGPT for Excel?
A: ChatGPT for Excel is a Microsoft Excel add-in from OpenAI that embeds ChatGPT directly inside spreadsheets, allowing users to build financial models, generate formulas, analyze datasets, and run scenario analysis using natural-language prompts.

Q: How does ChatGPT interact with Excel spreadsheets?
A: ChatGPT works through a panel inside Excel workbooks where users can describe tasks in plain language. The AI can generate formulas, analyze data across sheets, explain model assumptions, and update spreadsheet structures while calculations continue to run inside Excel.

Q: Which AI model powers ChatGPT for Excel?
A: The feature runs on GPT-5.4 Thinking, OpenAI’s newest reasoning model optimized for financial modeling, spreadsheet analysis, and data extraction.

Q: Who can use ChatGPT for Excel today?
A: The beta is rolling out to ChatGPT Business, Enterprise, Edu, Teachers, Pro, and Plus users in the United States, Canada, and Australia, with administrators controlling access in enterprise environments.

Q: Does ChatGPT replace traditional Excel formulas?
A: No. ChatGPT can generate and explain formulas, but calculations still run directly inside Excel so users can audit formulas, trace assumptions, and verify outputs.

Spreadsheets remain one of the most widely used decision tools in business, powering financial modeling, forecasting, and operational planning across organizations. Because so many financial and operational decisions are still modeled in spreadsheets, embedding AI directly into those environments could accelerate how quickly organizations move from raw data to analysis and decisions.

The key point: OpenAI is embedding AI directly into spreadsheets—the tool that already sits at the center of how companies analyze data and make financial decisions.

Financial analysts, investment professionals, accountants, and operations teams rely on Excel for valuation models, budgeting, forecasting, and scenario analysis that influence major business outcomes.

Embedding AI directly into these workflows could significantly change how organizations interact with their data.

Who should care:
Financial analysts, accountants, investment teams, corporate strategists, and operations leaders who rely on spreadsheets for modeling and decision-making—because these roles spend significant time building models, auditing formulas, reconciling datasets, and explaining assumptions inside Excel.

Why it matters now:
AI tools are moving beyond standalone chat interfaces and into the applications where business data already lives. Spreadsheets represent one of the most widely used analytical environments in companies worldwide, making them a natural entry point for enterprise AI adoption.

What decision this affects:
Organizations may soon need to decide whether AI should become a standard layer inside spreadsheet workflows—helping analysts build models, explain outputs, and run scenarios—or whether those workflows should remain primarily manual and human-driven.

Competition is also intensifying. Microsoft Copilot is already integrated into Excel and Microsoft 365, while companies such as Anthropic are expanding Claude into productivity environments. Across the industry, AI agents are increasingly being used to automate spreadsheet-based analysis, financial modeling, and operational reporting.

In short: AI is moving from external tools into the core software environments where business decisions are made.

The organizations that combine AI reasoning with the structured data already stored inside spreadsheets may gain a meaningful advantage—not just because AI models are improving, but because the analysis itself becomes faster, easier, and more accessible inside the tools professionals already use every day.

Editor’s Note: This article was created by Alicia Shapiro, CMO of AiNews.com, with writing, image, and idea-generation support from ChatGPT, an AI assistant. However, the final perspective and editorial choices are solely Alicia Shapiro’s. Special thanks to ChatGPT for assistance with research and editorial support in crafting this article.