Sales Automation
MongoDB needed to stop sales reps from spending 4 to 6 hours per account or deal cycle manually stitching together customer context from Salesforce, email, meeting transcripts, and documents before they could plan outreach or prepare for meetings.
Reported impact
MongoDB cut outbound prospecting research time by about 95%, reduced meeting and outreach preparation from hours to minutes, and created a single agentic interface that is rolling out across sales, account development, commercial growth, and solutions architecture teams.
MongoDB built Holly, an internal AI workspace, on Atlas Agent Engine so go-to-market teams could work from one governed system of action instead of hopping across disconnected sales tools. Atlas Agent Engine supplies the production runtime, memory, security, identity, orchestration, state, observability, and lifecycle controls for Holly's agents. Holly connects business systems including Salesforce, Google Calendar, Google Drive, Zoom, and Salesloft, then uses that context to generate account and opportunity briefs, highlight unanswered discovery questions, capture insights from meeting transcripts, and update CRM records after conversations. Rather than treating prompts as generic research requests, the workspace grounds each task in MongoDB-specific sales methodology and account context, turning fragmented prep and follow-up work into a single agent-driven workflow.
Customer and account context from Salesforce, Google Calendar, Google Drive, Zoom, and Salesloft is brought into Holly through Atlas Agent Engine, where agents synthesize the information into meeting briefs, discovery prompts, research outputs, and CRM updates for MongoDB's sales teams.
“Atlas Agent Engine provides the foundation for operating Holly's agents in production, including runtime, memory, security, identity, orchestration, state, observability, and lifecycle management.”
“Holly also connects a number of systems—including Salesforce, Google Calendar and Drive, Zoom, and Salesloft—and brings their information and capabilities into a shared workspace.”
“MongoDB account executives spent an average of 4 to 6 hours on administrative work, per account/deal cycle.”
“Powered by Atlas Agent Engine, Holly—MongoDB's internal AI workspace—cuts sales prospecting research time by 95%.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
MongoDB Sample Aug 11, 2026 Scalestack Scalestack needed to unify first-party, third-party, and zero-party go-to-market data so sales teams could stop manually researching prospects and act on AI-generated recommendations faster. Customers saw a 40% increase in rep productivity. MongoDB Atlas MongoDB Sample May 18, 2026 LekoTech LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds with its existing search system. LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds… MongoDB Atlas · MongoDB Atlas Search · MongoDB Atlas Vector Search MongoDB Sample Apr 29, 2026 Tenali AI Tenali AI needed to help enterprise sellers answer deeply technical questions during live calls in under one second by searching Slack, PDFs, CRM data, and prior meeting content without the latency and synchronization… After switching embedding models, sales reps actively using Tenali's answers on live calls increased by over 40%. MongoDB Atlas · MongoDB Vector Search · Voyage AI 