Dispatches
Customer story

Deal sourcing agents

A private-equity team recorded a conversation and had a running sourcing agent 48 hours later.

48 hoursFrom coffee conversation to running sourcingagentRecording to workflow with approval gatesBeforeAfterCRM for dealsMarket intelligencePartner's laptop filesTakes a coffeeThree disconnected sourcesOne sourcing agentEvery source citedUnified and automatedDeal team sourcing lived in CRM, market intelligenceSo we pull targets fromSalesforce, layer inPitchBook data, checkmy notes...I'll unify Salesforce,PitchBook, and yourlocal files into oneworkflow.coffee_recording…iPhone recordingSourcing processSalesforcePitchBookLocal filesAthena reads the iPhone transcript and unifies three sourcesOutreach draft: Series B targetsWe noticed your recent expansion into enterprise andthought you might be interested in exploring growthOur firm has backed three companies in adjacentverticals through similar inflection points.Would you be open to a brief conversation next week?PitchBookRecent expansionSalesforcePortfolio overlapDrafted by AthenaAgent researches company, drafts outreach, cites every sourceAthena wants toSend outreach email to targetsResearch pulled from PitchBook and SalesforceOutreach drafted with portfolio contextPartner reviews targets and messageWAITING FOR A PERSONApproved · emails queued to sendPartner approval required before sendPartner approves targets and message—and what to plan forsourcing_results.xlsxCompanyContactSentOpenedReplyTarget AFounderMon morningYesInterestedTarget BCFOMon morningYes—Target CCEOMon morningNo—Target DFounderMon morningYesMeeting bookedWHO CHANGED WHATAthenaSent approved emailsAthenaLogged opens and repliesto SnowflakePartnerReviews results in CRMEmails sent, results written back to Snowflake, every step loggedHit sendathenaintel.com
Fig. 02The story in 22 seconds, from the old way to “Hit send.”
Before · what we did · after
  1. Before

    A deal team's sourcing process lived in three places: the CRM, a market-intelligence subscription, and a partner's laptop. Describing it took a coffee.

  2. What we did

    Recorded the coffee on an iPhone. Athena read the transcript, unified Salesforce, PitchBook, and the local files, and drafted the workflow: research the company and contacts, write the outreach, hold for approval, send, write results back to Snowflake.

  3. After

    48 hours later the sourcing agent was running. Every email approval-gated. Every source cited.

01Read coffeetranscriptUnified Salesforce,PitchBook02Research company& contactsDraft outreach emailwith sources cited03Hold forapprovalPartner reviews draftand targetsa person approves04Send & writebackResults logged toSnowflakeSourcing agent running in 48 hours, every email approval-gated
Fig. 01From iPhone recording to workflow: research, draft, gate, send, log
How long it takes · what to plan for

The agent drafts. The partner still decides who gets the email.

You do not need point solutions for enrichment or outreach. You need to hit send.

Example workflow

Coffee chat to sourcing agent

SURFACES INWHAT COMES INTHE PLATFORMWHAT GOES OUTDELIVERED BACKWebText (SMS)EmailSlack · TeamsChromeOffice add-inMeeting botMeetingsWordPowerPointSheetsFiles · PDFsDataAppsLibrarySessionsSpacesStudiosMeetingsLakehouseSemantic modelsDatabaseDashboardsWordPowerPointSheetsDashboardsData · APIsApps · portalsWebMobile · voiceText (SMS)Slack · TeamsChromeOffice add-inMeeting botMobile · voice1Workflows (AOPs)2Agents3Email41 INPartner records coffeedescribing sourcingprocess on iPhone2 BUILDAthena reads transcript,unifies CRM, marketintelligence, and laptopfiles, drafts the workflow3 RUNAgent researches companyand contacts, writesoutreach, holds forapproval, sends4 OUTPartner approves eachemail; results writtenback to Snowflake withfull citation
Fig. 03The route on the system map: Mobile · voice → Workflows (AOPs) → Agents → Email. Connectors: Salesforce, PitchBook, Snowflake
What it runs on
What customers say
“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
“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
“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
“A lot of people are telling us that, oh, I sold in this package because of this info... I secured this distribution because of the selling assistance help.”
Sales enablement lead · A global CPG provider
“I am not a programmer. I cannot read a line of program in SQL or anything... The only thing that I'm doing is just writing prompts.”
Manufacturing analyst · A global manufacturer
“I finally got a chance to play around with the computer asset and build out the chatbot you mentioned. It was really impressive.”
Marketing lead · An AmLaw 100 firm
“So we use the SDK, and we write that in Python, and it calls Athena majority by API. The results appear in the interface itself.”
Legal technology team · A global law firm
“You guys are functioning better because the harness is tested for a longer period of time against enterprise customers.”
Analytics lead · A Fortune 500 retailer

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.