Dispatches
Surfaces · Office add-in

Connect Excel models to live data without replacing them

The Athena ribbon in desktop Office. AI formulas and Sheet Queries in your existing workbooks. Attribution on every change, synced both ways.

Built because a lending team wanted its Excel and Power Query models kept exactly as they were, and pointed at live Azure SQL.

=ATHENAQUERY("net charge-offs by vintageVintageQ1Q2Q3Trailing 12MVintage Aprior quarterprior quarterprior quartertrailing 12MVintage Bprior quarterprior quarterprior quartertrailing 12MVintage Cprior quarterprior quarterprior quartertrailing 12MVintage Dprior quarterprior quarterprior quartertrailing 12MVintage Eprior quarterprior quarterprior quartertrailing 12MWHO CHANGED WHATAthenaSheet Query: Azure SQL ·loans_dailyAthenarefreshed 06:00AnalystAthena via Analyst · 09:12
Fig. 01Desktop Excel with Athena ribbon: Sheet Query connects to Azure SQL, formula resolves to a table, every change attributed
  • Excel
  • Word
  • PowerPoint
  • Windows and Mac
  • Power Query linkage preserved
  • Sheet Queries to Azure SQL, Snowflake, Databricks
  • Attribution both ways
  • Tenant-wide O365 consent
The problem

The model is fine. The data is three exports old.

Finance runs on Excel and will keep running on it. The problem is not the spreadsheet; it is the six partner files a supply chain team receives weekly into their shared inbox, the Power Query everyone is careful with, and the 100,000-cell cleanup that is hard to do with formulas.

Replacing Excel is a three-year project nobody wants. Feeding it is a weekly inbox problem everybody has.

Do not replace the model. Connect it, and give it hands.

Weekly exportsLive connectionloans_export_0915.csvloans_export_0922.csvmore exports…Power Query: errorThree exports old, steps brokenSheet Query: liverefreshed 06:00Power Query steps intactSame workbook, live data, no exports
Fig. 02Before: folder of CSV exports and broken Power Query. After: Sheet Query panel shows live data, steps intact
How it works

Install. Connect. Ask. Sync.

  1. Install once, tenant-wide. Touchless O365 admin consent; the ribbon appears for everyone in the group. SSO through your IdP.

  2. Connect the workbook to live data. Sheet Queries pull from Azure SQL, Snowflake, Databricks, the Athena Lakehouse, or a semantic model. Existing Power Query steps stay attached.

  3. Ask in the cell or the panel. =ATHENA for a plain-language question. =ATHENAQUERY through the governed semantic model. The side panel for transformations that would otherwise need VBA: "normalize these 14 department tabs into one table."

  4. Sync when it outgrows the laptop. "Copy to Athena" moves the workbook to Studios for the million-row job or multi-agent workflows; sync brings the result back with every change attributed.

01DesktopExcel · WordAthena ribbon02SheetQueriesAzure SQL ·Snowflake03=ATHENA ·=ATHENAQUERYPlain-languageor governed …04AthenaStudios1M+ rows ·agents05Attributionon every …Both directionsLive data in the workbook you already have, attributed both ways
Fig. 03Install ribbon, connect to live sources, ask in cells or panel, sync when file outgrows laptop

Use cases

Excel and Power Query, kept, pointed at live Azure SQL.

A lending team's models untouched; the data behind them live. Weekly exports gone.

Weekly exportsLive connectionloans_export_0915.csvloans_export_0922.csvPower QueryModels staleLending team refreshes manuallyAzure SQL · livePower Query intactModels currentSheet Queries · refreshed 06:00
Fig. 04The lending team's Excel models unchanged, Power Query preserved, data now live from Azure SQL

The 100,000-cell cleanup.

A transformation Excel cannot express, described in a sentence in the side panel, executed in Python inside the workbook, attributed cell by cell.

cleanup.xlsxName/IDDateStatusFlagNotescombined entrymixed formatactivecombined entrymixed formatactivecombined entrymixed formatactiveduplicateduplicate entrymixed formatreviewflaggedcombined entrymixed formatactiveWHO CHANGED WHATAnalystSplit combined name/IDcolumnAnalyststandardize dates, flagduplicatesAthena98,412 cells changed ·Compare
Fig. 05A 98,412-cell transformation described in a sentence, executed in Python inside the workbook, attributed cell by cell

Forecasting, end to end.

Email to Excel to notebook to Databricks: the request arrives by email, the model updates in Excel, heavy computation runs in a notebook, the result lands in Databricks and back in the workbook.

01EmailRequest arrivesby email02ExcelModel updatesin Excel03NotebookHeavycomputation …04DatabricksResult lands inDatabricks05WorkbookSyncs back withattributionEmail to Excel to notebook to Databricks and back to workbook
Fig. 06Email request flows through Excel model, notebook computation, Databricks, and back to the workbook

Word and PowerPoint, too.

Draft a memo section from the workbook's numbers with citations back to the cells. Build the deck from the sheet in the company template, from inside PowerPoint.

Q3 ReviewBuilt from Forecast.xlsx with template and citations—Revenue trailing 12M—Net charge-offs—Forecast revised—All figures citedCOMPARETitle slideAthenaRevenue chartAthenaCitationsAthenaAthena pane: Build Q3 review from Forecast.xlsx · use template · cite figures
Fig. 07PowerPoint with Athena pane: build the deck from the sheet, use the company template, cite figures back to cells

"It is Excel."

The reaction from a mid-market accounting firm when they saw the ribbon. Nothing to learn.

model.xlsxAthenaHomeInsertFormulasDataSheet QueriesPower QueryPivotRefreshConnections=ATHENA()Get DataChartPropertiesQueries=ATHENAQUERY()TransformTableEdit LinksAnalysisCopy to AthenaClose & LoadFormatSortToolsWHO CHANGED WHATAthenaRibbon tab visibleAthenaSheet Queries panel ready
Fig. 08The accounting firm's reaction: the ribbon is Excel, so there is nothing new to learn
What customers say
“It's good to understand the capability of the platform. That how far, and how quickly you guys can get these things going [...] that has been impressive overall.”
VP-level AI leader · A Fortune 500 retailer
“Lets us get a lot more out of our data than [...] We can sit on top of all of the data in [our data warehouse] as opposed to just, like, our little ingested, you know, three gigabytes semantic models. I think we have a lot of power here.”
Analytics lead · A Fortune 500 retailer
“Gave Athena the spreadsheet, explained which column I was trying to figure out, and then ten secs it told me... exactly how the calculation was based on the other data.”
Analyst · A global manufacturer
“He wrote the entire stuff. By itself. And I was there, and I was thinking, alright. If I had to write all this stuff, I mean, I would've spent days, days, days.”
Manufacturing analyst · A global manufacturer
“I send that to the programmer and he said, alright. I read your file. I copied the section of the code because he has the right interface, and it works. Wow. Just like magic.”
Manufacturing analyst · A global manufacturer
“One workspace. All different, let's say, avatars of their output data. Right? Suddenly, it's dashboard. Excel is here. PowerPoint is when it's all together. It's very impressive.”
Global Sustainability lead · A global manufacturer
“Use the Athena platform probably closer to the concept and how it was designed, like, with the spaces architecture where you've got a set of primitives and capabilities, and you bring together the right set of capabilities to solve a task.”
Audit lead · A global professional services firm
“Digital worker, it gets spun up, it gets given access to the toolkits that it needs. It gets given access to the data that it needs. Just exists for the period it needs to exist to perform the task. And then it gets torn back down again afterwards.”
Audit lead · A global professional services firm
“I like that direction, that concept of the agent is the agent. It becomes an entity in its own right with its own ownership and its own missioning, and you get rid of the gray area and the blurry lines.”
Audit lead · A global professional services firm
“It was PowerPoint... there was no kind of distinction between the two. So that was killer. And I literally had a meeting on it today, and people said how great it was.”
Sales analyst · A global CPG provider

Verbatim from customer calls. Customers anonymized.

Build

One platform, three ways to build

Agents answer in the cell. Workflows (Agent Operating Procedures) refresh the workbook on schedule and email it. Applications turn the finished sheet into a dashboard the rest of the company opens without Excel or a license.

Integration

How it fits your stack

Microsoft 365 with tenant-wide admin consent. Windows and Mac desktop Office. Azure SQL, Snowflake, Databricks, SharePoint-hosted workbooks. Runs against managed cloud or your VPC.

What to plan for

The add-in brings Athena into Excel; it does not make Excel handle a million rows. When the file outgrows the laptop, "Copy to Athena" is the answer, and the sync back is attributed so nothing is lost in the round trip.

FAQ

What does the add-in do?

Brings the agent into Excel, Word, and PowerPoint, working with your own files and live data.

Do we have to rebuild our models?

No. Keep them and connect them to live data.

How is it deployed?

Centrally by your admins.

One platform underneath

AGS · Athena Governance System

Records every change by a person or an agent, rolls back one contributor's edits without losing anyone else's, and keeps the model, instructions, and sources behind each agent action.

Palladium · deployment

How the platform is deployed: Athena's managed cloud, your cloud on AWS, GCP, or Azure, on-prem, air-gapped, or GovCloud. Same platform in every option.

How it fits together

Build, Work, and Data on top; 150+ connectors and every surface in and out; one map of the whole platform.

The rest of the platform

Related products and stories

Open the workbook you refresh by hand every Monday.

We will connect it to the source, leave your Power Query alone, and show you the attribution.