Dispatches
Customer story

Automated executive reporting

Every Monday at 7:00 AM, an AOP queries Snowflake, fills the PowerPoint template slide by slide, writes headlines, and emails the deck by 7:30 AM.

7:30 AMWhen the weekly executive deck arrivesMonday morning · every weekSunday eveningMonday 7:00 AMQuery SnowflakePull numbersFill PowerPoint slidesWrite headlinesEmail deckFP&A analyst · slide by slide · every weekDeck in every inboxAnalyst reads with coffeeAOP runs the procedureBefore: FP&A analyst spent Sunday evening pulling numbersAthenaSnowflakeSemantic modelPowerPointEmailAOP on Monday 7:00 AM schedule · query through fill to sendAOP queries Snowflake, fills template, writes headlinesWeekly Executive DeckGenerated Monday 7:00 AM · slides—Revenue vs. plan—EMEA margin flags—Inventory turns up—Headcount on targetCOMPARESlidesAthenaHeadlinesAthenaCitationsAthenaCitations attached to every number · template filledAthena fills slides, writes headlines, attaches citationsAthena wants toSend weekly executive deck to allexecutivesSlides filled from SnowflakeHeadlines drafted for each slideCitations attached to every numberWAITING FOR A PERSONCFO edits one headline most weeksHeadlines are drafts · numbers do not changeHeadlines are drafts; CFO edits one most weeksSESSIONWeekly executive deck ready · 7:30 AMExecutive Deckslides · headlines · citationsIn every executive's inbox7:30 AM: deck is in every executive's inboxBeforeAfterSunday evening workAnalyst pulls numbersSlide by slideEvery weekAnalyst reads with coffeeSpends Monday on the whyA global CPG provider runs this todayAnalyst reads with coffee, spends Monday on the whyData to deck.athenaintel.com
Fig. 02The story in 26 seconds, from the old way to “Data to deck.”
Before · what we did · after
  1. Before

    An FP&A analyst spent Sunday evening pulling numbers into the weekly executive deck. Slide by slide. Every week.

  2. What we did

    An Agent Operating Procedure (AOP) on a Monday 7:00 AM schedule: query Snowflake through the semantic model, fill the company's PowerPoint template slide by slide, write the headlines, attach citations (source links to the Snowflake query for each number), email it.

  3. After

    7:30 AM, it is in every executive's inbox. The analyst reads it with coffee like everyone else and spends Monday on the why. A global CPG provider runs this today.

Weekly Executive DeckMonday 7:30 AM · Generated by AOP—Revenue vs. plan—EMEA margin flags yellow—Inventory turns improved—Headcount on targetCOMPARESlidesAthenaHeadlinesAthenaCitationsAthenaHeadline 7CFOAOP · Monday 7:00 AM schedule · Snowflake → semantic model → PowerPoint
Fig. 01The deck arrives AM with headlines, citations, and template filled slide by slide
How long it takes · what to plan for

The headlines are drafts. The CFO edits one headline most weeks. The number under it does not change.

Data to deck.

Example workflow

Monday 7:00 AM schedule → deck in every executive's inbox

SURFACES INWHAT COMES INTHE PLATFORMWHAT GOES OUTDELIVERED BACKWebMobile · voiceText (SMS)Slack · TeamsChromeOffice add-inMeeting botMeetingsWordPowerPointSheetsFiles · PDFsDataAgentsAppsLibrarySessionsSpacesStudiosMeetingsLakehouseDatabaseDashboardsWordSheetsDashboardsData · APIsApps · portalsWebMobile · voiceText (SMS)EmailSlack · TeamsChromeOffice add-inMeeting botWorkflows (AOPs)1Semantic models2PowerPoint3Email41 RUNAOP triggers Monday 7:00AM: query the semanticmodel for weekly numbers2 BUILDQuery Snowflake throughthe semantic model; returnrevenue, margin,inventory, headcount3 ANSWERFill the companyPowerPoint template slideby slide; write headlines;attach citations4 OUTEmail the deck at 7:30 AM;FP&A analyst andexecutives read it withcoffee
Fig. 03The route on the system map: Workflows (AOPs) → Semantic models → PowerPoint → Email. Connectors: Snowflake · email · PowerPoint template
What it runs on
What customers say
“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
“This combination is a winning combination for us, and this is where we see maximum traction, which is how do you apply all the intelligence that you have within [our data platform] and not worry about how you render that output.”
Analytics lead · A global CPG provider
“I envision Athena and [our data platform] as the combination... that's the stack for me.”
Analytics lead · A global CPG provider
“This is where the puck's going and this is where the moat is for an enterprise.”
AI Council lead · A Fortune 50 retailer
“So you gave her three sentences. And she spit out that.”
Analytics lead · A Fortune 500 retailer
“I'm very excited. This is something that I have been piecemealing with the limited tools that analysts get... rather than me at nine PM getting a failure email and deciding I'll just do it myself.”
DC Ops Data & Analytics lead · A Fortune 500 retailer
“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
“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

Verbatim from customer calls. Customers anonymized.

Related

Related products and stories

See this on your own work

Bring one recurring task, a sample input, and an example of work you would accept.