Sales Call Summary Agent

An AI-powered agent that automatically summarizes sales calls using Vercel's Sandbox architecture. The agent analyzes call transcripts and generates structured summaries with objections, action items, and insights.

Template Note: This template uses Gong as a starting example for call transcript integration. You can adapt it to work with other call recording platforms (Zoom, Google Meet, etc.) by modifying the webhook handler and transcript fetching logic.

Features

• Structured Summaries - AI-generated summaries with tasks, objections, and key insights
• Sandbox Agent - Uses Vercel Sandbox for secure code execution and file exploration
• bash-tool - Generic bash tool for AI agents, compatible with AI SDK
• Demo Mode - Works out of the box with mock data (no Gong credentials needed)
• Objection Tracking - Identifies and scores how well objections were handled
• Slack Integration - Optional notifications to your team channel
• Salesforce Integration - Optional CRM context enrichment
• Durable Workflows - Built with Vercel Workflow DevKit for reliability

One-Click Deploy (Demo Mode)

You can deploy to Vercel and try it immediately with demo data with one click:

Demo mode is enabled by default - no Gong credentials required to test!

Local Development (Demo Mode)

1. Clone and Install

1
git clone https://github.com/vercel-labs/call-summary-agent
2
cd call-summary-agent
3
npm install

2. Link to Vercel (creates .env.local automatically)

1
vercel link
2
vercel env pull

Or manually create .env.local:

1
AI_GATEWAY_API_KEY=your_ai_gateway_api_key

3. Run

1
npm run dev

4. Test

1
# Check status (should show demoMode: true)
2
curl http://localhost:3000/api/gong-webhook
3

4
# Trigger the agent with demo data
5
curl -X POST http://localhost:3000/api/gong-webhook \
6
  -H "Content-Type: application/json" \
7
  -d '{}'

Production Setup (Real Gong Data)

To use real Gong API data instead of demo data:

1. Set Environment Variables

Add these to your Vercel project settings or .env.local:

1
AI_GATEWAY_API_KEY=your_ai_gateway_api_key
2
USE_REAL_DATA=true
3
GONG_ACCESS_KEY=your_gong_access_key
4
GONG_SECRET_KEY=your_gong_secret_key

2. Configure Gong Webhook

1. Go to your Gong settings > Integrations > Webhooks
2. Create a new webhook with:
   • URL: https://your-app.vercel.app/api/gong-webhook
   • Events: Select "Call completed"
3. Save and test the webhook

Architecture

Environment Variables

Demo Mode Details

Demo mode uses realistic mock data including a sample 20-minute product demo call. The demo files are organized in the /demo-files folder:

1
demo-files/
2
├── webhook-data.json              # Mock Gong webhook payload
3
├── transcript.json                # 20-minute call transcript
4
└── context/
5
    ├── gong-calls/previous/       # Historical calls
6
    │   ├── demo-call-000-discovery-call.md
7
    │   └── demo-call-intro-initial-call.md
8
    ├── salesforce/                # CRM context
9
    │   ├── account.md
10
    │   ├── opportunity.md
11
    │   └── contacts.md
12
    ├── research/                  # Background info
13
    │   ├── company-research.md
14
    │   └── competitive-intel.md
15
    └── playbooks/
16
        └── sales-playbook.md

These files are loaded into the sandbox for the agent to explore.

Configuration

AI Model

By default, the agent uses claude-sonnet-4-20250514. You can change this via:

1
AI_MODEL=anthropic/claude-sonnet-4
2
# or
3
AI_MODEL=openai/gpt-4o

Custom System Prompt

Override the default system prompt:

1
AGENT_SYSTEM_PROMPT="You are a sales call analyst..."

Slack Integration

Enable Slack notifications by setting:

1
SLACK_BOT_TOKEN=xoxb-your-bot-token
2
SLACK_CHANNEL_ID=C0123456789

The agent posts:

1. Main summary message
2. Thread reply with details
3. Objections breakdown
4. Action items list

To add multiple channels: Modify lib/slack.ts to route based on call properties.

Salesforce Integration

Enable CRM context by setting Salesforce credentials. The agent will enrich summaries with account data.

See CRM Customization for details on customizing fields or adding other CRMs.

How It Works

1. Webhook Received: Gong sends call data when a call completes (or mock data in demo mode)
2. Workflow Started: The durable workflow begins processing
3. Transcript Fetched: Call transcript is retrieved from Gong API (or mock data)
4. Sandbox Created: A secure sandbox is created with call files
5. Agent Runs: The AI agent explores transcripts using bash-tool
6. Summary Generated: Structured output with tasks, objections, insights
7. Notifications Sent: Optional Slack messages posted

Workflow Steps

Each step uses the "use step" directive for:

• Automatic retries on failure
• State persistence
• Observability in Vercel dashboard

Sandbox Tools

The agent uses bash-tool for exploring call transcripts via shell commands:

1
# List call files
2
ls gong-calls/
3

4
# Search for pricing discussions
5
grep -r "pricing" gong-calls/
6

7
# View call metadata
8
cat gong-calls/metadata.json
9

10
# Find objections
11
grep -i "concern\|issue\|problem" gong-calls/*.md

All bash commands are logged for observability:

1
[bash-tool] INFO: Bash command starting { command: 'grep -r "pricing" gong-calls/' }
2
[bash-tool] INFO: Bash command completed { command: '...', exitCode: 0, stdoutLength: 605 }

Output Schema

The agent generates structured output:

1
{
2
  summary: string,           // Comprehensive call summary
3
  tasks: [{
4
    taskDescription: string,
5
    taskOwner: string,
6
    ownerCompany: 'internal' | 'customer' | 'partner'
7
  }],
8
  objections: [{
9
    description: string,
10
    quote: string,
11
    speaker: string,
12
    speakerCompany: string,
13
    handled: boolean,
14
    handledAnswer: string,
15
    handledScore: number,    // 0-100
16
    handledBy: string
17
  }],
18
  slackSummary: string,      // TL;DR for Slack
19
  slackDetails: string       // Detailed thread reply
20
}

Customization

Custom Playbooks

Add playbook detection by configuring config.playbooks in lib/config.ts.

CRM Customization

The agent supports optional CRM integration to enrich call context. By default, Salesforce is supported, but you can customize fields or add other CRMs.

Adding a Different CRM (HubSpot, Pipedrive, etc.)

1. Create a new CRM module (e.g., lib/hubspot.ts):

1
export function isHubSpotEnabled(): boolean {
2
  return !!process.env.HUBSPOT_API_KEY;
3
}
4

5
export async function getAccountData(companyId: string): Promise<{
6
  accountData: Record<string, unknown> | null;
7
}> {
8
  // Implement your CRM's API calls
9
}

1. Add config in lib/config.ts:

1
hubspot: {
2
  enabled: !!process.env.HUBSPOT_API_KEY,
3
  apiKey: process.env.HUBSPOT_API_KEY || '',
4
},

1. Update sandbox context in lib/sandbox-context.ts:

1
import { getAccountData, isHubSpotEnabled } from './hubspot';
2

3
// In generateFilesForSandbox():
4
if (isHubSpotEnabled() && options.hubspotCompanyId) {
5
  const { accountData } = await getAccountData(options.hubspotCompanyId);
6
  // Write to sandbox...
7
}

1. Extract CRM IDs from Gong context in workflows/gong-summary/index.ts:

1
// Gong may include CRM context from integrations
2
const hubspotCompanyId = data.callData.context
3
  ?.find((c) => c.system === 'HubSpot')
4
  ?.objects?.find((o) => o.objectType === 'Company')?.objectId;

Disabling CRM Integration

Simply don't set the SF_* environment variables. The integration checks isSalesforceEnabled() before making any API calls.

Development

1
# Install dependencies
2
npm install
3

4
# Run development server
5
npm run dev
6

7
# Build for production
8
npm run build

Project Structure

1
sales-call-summary-agent/
2
├── app/
3
│   ├── api/gong-webhook/    # Webhook endpoint
4
│   ├── layout.tsx
5
│   └── page.tsx             # Status page
6
├── demo-files/              # Demo mode files
7
│   ├── webhook-data.json
8
│   ├── transcript.json
9
│   └── context/             # Additional context files
10
├── lib/
11
│   ├── agent.ts             # ToolLoopAgent configuration
12
│   ├── config.ts            # Centralized configuration
13
│   ├── gong-client.ts       # Gong API helpers
14
│   ├── mock-data.ts         # Demo mode loader
15
│   ├── salesforce.ts        # Optional Salesforce integration
16
│   ├── slack.ts             # Optional Slack integration
17
│   ├── sandbox-context.ts   # File generation for sandbox
18
│   ├── tools.ts             # Agent tools (bash-tool)
19
│   ├── types.ts             # TypeScript types
20
│   └── logger.ts            # Logging utility
21
└── workflows/
22
    └── gong-summary/
23
        ├── index.ts         # Main workflow
24
        └── steps.ts         # Workflow steps

API Reference

POST /api/gong-webhook

Receives Gong webhook payloads and triggers the summary workflow.

Request Body: Gong webhook payload or empty {} in demo mode.

Response:

1
{
2
  "message": "Workflow triggered",
3
  "callId": "1234567890"
4
}

GET /api/gong-webhook

Health check endpoint.

Response:

1
{
2
  "status": "ok",
3
  "service": "sales-call-summary-agent",
4
  "demoMode": true,
5
  "configValid": true,
6
  "configErrors": []
7
}

Output

The function returns output in the format agentOutputSchema (detailed in agent.ts). You can save this output in Slack.

Contributing

Contributions are welcome! Please open an issue or submit a pull request.