Closeum, Sales teams
One system from the sales call to the commission
A sales platform that carries call context into lead management, reporting, payments, and commissions.
Built for: Sales organization with setters, closers, managers, and owners
- connected modules
- 13+
- connected modules
- revenue tracked
- $99.5K+
- revenue tracked
- completed transactions
- 32
- completed transactions
- leads managed
- 40+
- leads managed
First agent live in one week. A short call. Your first agent, a fixed quote, and the timeline. No obligation.
Sound familiar?
- “Our call recordings, lead notes, and payment records all live in different places.”
- “Closers rebuild their whole day by hand for the end-of-day report.”
- “Managers only get the real story of a deal after someone reconciles it.”
How the system works.
- Step 1
A pipeline for every role
Setters get lead tracking and appointment booking, closers get their scheduled calls, managers review team performance, and owners manage the workspace and billing.
- Step 2
Recorded calls with AI analysis
Google Calendar triggers Recall.ai recording, and OpenAI reads each transcript for a summary, objections, outcome suggestions, and follow-up context.
- Step 3
Outcomes the closer confirms
AI suggests the interpretation. The closer records closed, no-sale, or no-call, so a person always owns the result.
- Step 4
Reports that fill themselves
Call data flows straight into the end-of-day report, which managers review and approve instead of chasing.
- Step 5
Payments and commissions on the same record
Payment links, transactions, invoices, and commission records sit on the same deal, powered by Stripe Connect.
What changed.
- 13+ connected modules covering leads, calls, AI analysis, reporting, payments, and commissions
- $99,500+ in revenue tracked across 32 completed transactions
- 5 role types working from one shared record of every sale
- The team moves from a scheduled call to recording, analysis, outcome, report, and payment without leaving the product
The AI inside.
OpenAI
Analyzes call transcripts for summaries, objections, outcome suggestions, and follow-up context
Recall.ai
Joins scheduled calls and records them so every conversation has a transcript
The full stack.
Frontend
- Next.js
- React
- Tailwind CSS
Backend
- Node.js
- Express
- JWT and Google OAuth
Data
- PostgreSQL
- TypeORM
- S3-compatible storage
AI and automation
- OpenAI
- Recall.ai
Integrations
- Google Calendar API
- Gmail API
- Stripe Connect
This fits you if...
- Your sales team splits calls between setters and closers and nobody sees the whole deal
- Managers spend evenings reconciling reports, recordings, and payments
- Commissions are calculated in a spreadsheet after the fact
Start with a free Agent Audit. First agent live in one week
We build AI CRM systems like this.
A sales system built around how your team actually sells, with AI doing the follow-up work.
Full project write-upRead itClose
Project overview
Sales calls, follow-up, and commissions in one CRM
Services: AI ERP & CRM ; AI Workflow Automation ; AI Agents
Delivery: Full-stack sales platform for closers, setters, and managers.
Project Snapshot
| Figure | What it represents |
|---|---|
| 13+ modules | Connected product scope |
| $99,500+ | Revenue tracked in the historical portfolio snapshot |
| 32 transactions | Completed transactions in that same snapshot |
| 5 role types | Closer, setter, manager, owner/admin, super admin |
Revenue tracked is money recorded by the platform, not revenue attributed to AI. The financial snapshot comes from existing portfolio records.
The Problem
A setter books the call. A closer conducts it. A manager wants the outcome. If the sale closes, someone needs to record the payment and calculate the commission.
Each person needs a different view of the same sale. When recordings, lead notes, end-of-day reports, and payment records are separate, the team keeps entering the same information and the manager has to reconcile the story afterward.
Closeum's brief was to connect those responsibilities in one product.
What We Delivered
The setter gets a lead pipeline, contact-attempt tracking, and appointment scheduling. The closer gets scheduled calls, recordings, transcripts, AI analysis, and outcome capture. Managers review team performance and approve end-of-day reports. Owners manage the workspace, team, and billing.
The call workflow connects Google Calendar to Recall.ai recording. OpenAI analyzes the transcript for summaries, objections, outcome suggestions, and follow-up context. The closer reviews the result and records a closed, no-sale, or no-call outcome.
Call information also feeds the end-of-day report. That saves the closer from reconstructing the day's conversations in a separate reporting form. Payment links, transactions, invoices, and commission records extend the workflow after the call.
Other delivered areas include products, goals, Gmail-connected communication, tasks, workspace invitations, and platform administration.
Engineering Decisions
Use the call as shared input. The transcript supports several downstream tasks: reviewing the conversation, capturing the outcome, preparing follow-up, and reporting activity.
Keep people in the approval path. AI suggests an interpretation. The closer records the outcome and the manager can review the report.
Separate workspace and role concerns. A closer's own work, a manager's team view, and platform-wide administration require different access and interfaces.
Connect payment state to sales records. Recording a successful call and recording a received payment are separate events. The product gives the team both.
Results
The delivered platform connects more than thirteen modules across the sales operation. The historical portfolio snapshot records $99.5K+ across 32 completed transactions.
The operational change is specific: the team can move from a scheduled call to its recording, analysis, outcome, report, and commercial record inside the same product. No conversion-lift percentage is attributed to that change.
Technology stack
Next.js, React, Tailwind CSS; Node.js and Express; PostgreSQL and TypeORM; OpenAI; Recall.ai; Google Calendar and Gmail APIs; Stripe Connect; JWT and Google OAuth; S3-compatible storage.
Related case studies.
Connexions Recovery
Every admissions call becomes a record staff can act on
AI: OpenAI Realtime, OpenAI Whisper
HubSpot MCP
Every HubSpot deal reviewed and given a clear next step
AI: Model Context Protocol (MCP), AI account synthesis and drafting
Business OS + Antheon
An AI assistant that answers from your real business records
AI: OpenAI, Cartesia
Want this for your team?
Book a short audit call and show us the workflow. You leave with the first agent we would build, a fixed quote, and the timeline.
