Skip to main content

What you’ll build

You’ll build an intelligent sales preparation assistant that researches companies, contacts, and opportunities in parallel, then generates comprehensive meeting prep documents. When a sales rep says “Prepare me for a meeting with Acme Corp,” the workflow automatically researches the company, key contacts, recent news, and potential opportunities, delivering a structured brief within seconds. This workflow demonstrates how to:
  • Automate pre-meeting research that typically takes 30-60 minutes
  • Use parallel agents to gather information from multiple sources simultaneously
  • Integrate web search and CRM data for comprehensive intelligence
  • Generate structured, actionable meeting prep documents
  • Trigger complex workflows from natural language chat

What you’ll build

Your sales team will be able to:
  • Chat: “Prepare me for a meeting with [Company Name]”
  • Get a complete meeting brief including:
    • Company overview and recent news
    • Key contact profiles and backgrounds
    • Open opportunities and deal status
    • Talking points and questions to ask
    • Competitor intelligence
    • Risk factors and concerns

Prerequisites

Before you begin, ensure you have:
  • MagOneAI instance with workflow builder and chat interface access
  • LLM provider configured (GPT-4, Claude 3.5 Sonnet recommended)
  • Web search tool configured (Google Search API, Bing Search, or SerpAPI)
  • CRM integration (optional but recommended) - Salesforce, HubSpot, or similar
  • Sales intelligence tools (optional) - LinkedIn Sales Navigator, ZoomInfo, etc.
This workflow works great even without CRM integration by using web search alone, but connecting your CRM dramatically improves deal context and historical information.

Architecture

The sales intelligence workflow uses parallel research agents to gather comprehensive information quickly:
Chat Trigger ("Prepare me for meeting with [Company]")

Parse Company Name (extract from user input)

Parallel Research Node (4 branches)
    ├── Branch 1: Company Research Agent (web search)
    ├── Branch 2: Contact Research Agent (LinkedIn/web)
    ├── Branch 3: Opportunity Analysis Agent (CRM)
    └── Branch 4: News & Updates Agent (news search)

Synthesis Agent (compile meeting prep document)

Output to Chat (formatted meeting brief)

Why this architecture works

Speed

Four parallel research agents complete in ~15-20 seconds vs. 2+ minutes sequential

Comprehensive

Multi-source research provides complete context: public data, CRM history, and real-time news

Natural Language

Sales reps use natural chat commands - no forms or complex interfaces

Actionable Output

Structured briefs include talking points, questions, and next steps - not just raw data

Step-by-step build

1

Create the research agents

You’ll create five agents: four research specialists and one synthesis agent.

1. Company Research Agent

Name: Company Intelligence Researcher Model: GPT-4 or Claude 3.5 Sonnet Tools: Web SearchPersona:
You are a business intelligence researcher specializing in company analysis.

Given a company name, research and provide:

1. Company Overview
   - Industry and business model
   - Size (employees, revenue if public)
   - Headquarters location and key offices
   - Year founded and ownership structure

2. Products & Services
   - Main offerings
   - Target customers and markets
   - Unique value propositions

3. Recent Developments
   - Major announcements (last 6 months)
   - Product launches
   - Leadership changes
   - Funding/acquisition activity

4. Market Position
   - Key competitors
   - Market share (if available)
   - Industry trends affecting them

Use web search to find current, accurate information. Cite sources.

Output structured JSON:
{
  "company_name": "...",
  "overview": { ... },
  "products_services": [ ... ],
  "recent_developments": [ ... ],
  "market_position": { ... },
  "sources": [ ... ]
}

2. Contact Research Agent

Name: Contact Intelligence Researcher Model: GPT-4 or Claude 3.5 Sonnet Tools: Web Search, LinkedIn (if integrated)Persona:
You are an expert at researching business contacts and decision-makers.

Given a company name, identify and research key contacts:

1. Identify Decision Makers
   - C-suite executives (CEO, CTO, CFO, etc.)
   - Department heads relevant to our solution
   - Known contacts from past interactions (if CRM data provided)

2. For Each Key Contact:
   - Full name and title
   - Professional background and career history
   - Education
   - Tenure at current company
   - Recent activity (posts, articles, speaking engagements)
   - Shared connections (if LinkedIn available)
   - Personal interests or causes (if publicly available)

3. Engagement Strategy
   - Who to target first
   - Relevant talking points based on their background
   - Connection opportunities

Use web search and LinkedIn (if available) to gather information.

Output structured JSON:
{
  "key_contacts": [
    {
      "name": "...",
      "title": "...",
      "background": "...",
      "tenure": "...",
      "recent_activity": "...",
      "engagement_notes": "..."
    }
  ],
  "recommended_approach": "..."
}

3. Opportunity Analysis Agent

Name: Deal Intelligence Analyst Model: GPT-4 or Claude 3.5 Sonnet Tools: CRM API (if integrated)Persona:
You are a sales operations analyst specializing in opportunity analysis.

Given a company name and CRM data (if available), analyze:

1. Open Opportunities
   - Deal names and stages
   - Expected close dates
   - Deal values
   - Products/services involved
   - Key decision factors

2. Historical Context
   - Past purchases or engagements
   - Contract history
   - Previous deal outcomes (won/lost/why)
   - Lifetime value

3. Relationship Strength
   - Engagement frequency
   - Sentiment from past interactions
   - Support ticket history
   - Product adoption metrics (if customer)

4. Risk Factors
   - Stalled deals
   - Competitive threats
   - Budget constraints
   - Timeline pressures

If no CRM data is available, output:
{
  "status": "NO_CRM_DATA",
  "recommendation": "First-time engagement - focus on discovery"
}

Otherwise, output structured JSON:
{
  "open_opportunities": [ ... ],
  "historical_context": { ... },
  "relationship_strength": "STRONG | MODERATE | WEAK | NEW",
  "risk_factors": [ ... ],
  "opportunity_insights": "..."
}

4. News & Updates Agent

Name: News Intelligence Monitor Model: GPT-4 or Claude 3.5 Sonnet Tools: News Search API, Web SearchPersona:
You are a business news analyst monitoring company developments.

Given a company name, find and analyze recent news (last 30 days):

1. Company-Specific News
   - Press releases
   - Product announcements
   - Executive moves
   - Financial results
   - Partnerships or deals

2. Industry News
   - Sector trends affecting this company
   - Regulatory changes
   - Competitor news

3. Relevance Analysis
   - Which news items create sales opportunities?
   - Which create risks or concerns?
   - Suggested talking points based on news

Use news search to find recent, relevant articles. Prioritize high-quality sources.

Output structured JSON:
{
  "company_news": [
    {
      "headline": "...",
      "date": "...",
      "source": "...",
      "summary": "...",
      "relevance": "HIGH | MEDIUM | LOW",
      "sales_angle": "..."
    }
  ],
  "industry_news": [ ... ],
  "talking_points": [ ... ]
}

5. Synthesis Agent

Name: Meeting Prep Coordinator Model: GPT-4 or Claude 3.5 SonnetPersona:
You are an expert sales strategist who creates comprehensive meeting preparation briefs.

You receive research from four specialist agents:
- Company intelligence
- Contact intelligence
- Opportunity analysis
- News & updates

Create a meeting prep document that includes:

1. Executive Summary (2-3 sentences)
   - Who they are, what we're discussing, key context

2. Company Quick Facts
   - Industry, size, location
   - What they do in plain language

3. Key Contacts
   - Who you're meeting with
   - Their background and priorities
   - Suggested talking points per person

4. Opportunity Context
   - Open deals and their status
   - Historical relationship (if any)
   - What we're trying to achieve

5. Recent News & Developments
   - Top 3 most relevant news items
   - How they create opportunities or affect the conversation

6. Suggested Agenda
   - Topics to cover
   - Questions to ask
   - Points to emphasize

7. Potential Concerns & Objections
   - Anticipated pushback
   - How to address

8. Next Steps & Success Metrics
   - What defines a successful meeting
   - Concrete next actions to propose

Format the output in clean Markdown suitable for displaying in chat.
2

Configure tools and integrations

Set up the external tools your agents will use.

Web Search Tool

  1. Navigate to Tools in your MagOneAI project
  2. Add Web Search Tool
  3. Configure with your search API:
    • Google Custom Search API
    • Bing Search API
    • SerpAPI
    • Or use MagOneAI’s built-in search if available
  4. Test the search tool with a sample query

CRM Integration (Optional)

  1. Add CRM Tool or HTTP API Tool
  2. Configure authentication for your CRM:
    • Salesforce: OAuth 2.0
    • HubSpot: API key
    • Other: API credentials
  3. Create API endpoints for:
    • Search accounts by company name
    • Get open opportunities for account
    • Get contact history
  4. Test the integration
If CRM integration isn’t available initially, the workflow still provides value through web and news research. You can add CRM later without rebuilding the workflow.

News Search (Optional)

  1. Add News API Tool or use web search with news filters
  2. Configure with news API credentials if using dedicated service
  3. Set search parameters to prioritize recent news (last 30 days)
3

Build the workflow

Construct the workflow in the MagOneAI workflow builder.
  1. Add Chat Trigger
    • Type: Chat Trigger
    • Configure trigger patterns:
      • “Prepare me for a meeting with [company]”
      • “Meeting prep for [company]”
      • “Research [company] for meeting”
      • “Brief me on [company]”
    • Extract company_name from user input
  2. Add Company Name Extraction (Optional)
    • If your platform supports it, add a simple agent to parse company name
    • Or use regex extraction in trigger configuration
    • Store in variable: company_name
  3. Add Parallel Research Node
    • Drag a Parallel Node onto the canvas
    • Connect to trigger
    • Configure four parallel branches
4

Configure parallel research branches

Set up four research branches that execute simultaneously.Branch 1 - Company Research
  • Agent Node: Company Intelligence Researcher
  • Input: {{trigger.company_name}}
  • Enable tools: Web Search
  • Timeout: 30 seconds
Branch 2 - Contact Research
  • Agent Node: Contact Intelligence Researcher
  • Input: {{trigger.company_name}}
  • Enable tools: Web Search, LinkedIn API (if configured)
  • Timeout: 30 seconds
Branch 3 - Opportunity Analysis
  • Agent Node: Deal Intelligence Analyst
  • Input: {{trigger.company_name}}
  • Enable tools: CRM API (if configured)
  • Timeout: 20 seconds
  • Handle errors gracefully: If no CRM data, return empty state
Branch 4 - News & Updates
  • Agent Node: News Intelligence Monitor
  • Input: {{trigger.company_name}}
  • Enable tools: News Search API or Web Search
  • Timeout: 30 seconds
Set timeouts generously (30s) for agents that use web search, as external API calls can add latency. The parallel execution means total time is still fast.
5

Add synthesis agent

After parallel research completes, synthesize results into meeting prep document.
  1. Add Agent Node: Meeting Prep Coordinator
  2. Configure inputs:
    Company Name: {{trigger.company_name}}
    Company Research: {{parallel.branch1.output}}
    Contact Research: {{parallel.branch2.output}}
    Opportunity Analysis: {{parallel.branch3.output}}
    News & Updates: {{parallel.branch4.output}}
    Sales Rep Name: {{$user.name}}
    Meeting Date: {{trigger.meeting_date}} (if provided)
    
  3. Output format: Markdown
  4. Timeout: 30 seconds
6

Output to chat

Display the meeting prep document in the chat interface.
  1. Add Output Node or let the workflow auto-return to chat
  2. Format output:
    # Meeting Prep: {{trigger.company_name}}
    
    {{synthesis_agent.output}}
    
    ---
    *Prepared by MagOneAI Sales Intelligence • {{$now}}*
    
  3. Add option to save: Include buttons like “Save to CRM” or “Email to me”
Consider adding a final step that automatically creates a note in your CRM with the meeting prep document for future reference.
7

Test the workflow

Test with various company names and scenarios.Test Case 1: Well-known public company
  • Command: “Prepare me for a meeting with Microsoft”
  • Expect: Rich public information, recent news, executive profiles
  • Verify: All research branches complete successfully
Test Case 2: Private/smaller company
  • Command: “Meeting prep for [local business]”
  • Expect: Less public data, still useful overview and news
  • Verify: Agents handle limited data gracefully
Test Case 3: Existing CRM account
  • Command: “Brief me on [existing customer]”
  • Expect: CRM data enriches the brief with deal history
  • Verify: Opportunity analysis includes actual CRM data
Test Case 4: Misspelled/ambiguous name
  • Command: “Research Amazn for meeting” (typo)
  • Verify: Agents interpret correctly or ask for clarification
Monitor:
  • Parallel execution timing (should be ~15-30s total)
  • Agent output quality and relevance
  • Proper error handling when data isn’t available
  • Markdown formatting in chat output
8

Add enhancements

Improve the workflow with additional features.Save to CRM
  • Add a button: “Save this brief to CRM”
  • Create a CRM note/activity with the meeting prep content
  • Link to the company record
Email the brief
  • Add a button: “Email this to me”
  • Format as HTML email
  • Include attachments (if any news articles or reports)
Schedule follow-up
  • Add button: “Set follow-up reminder”
  • Create calendar event or task
  • Include key talking points in event description
Competitor intelligence
  • Add optional 5th parallel branch
  • Research mentioned competitors
  • Compare positioning and recent news

Key concepts demonstrated

Chat-Initiated Workflows

Trigger complex multi-agent workflows from natural language chat commands

Web Search Integration

Use search APIs to gather real-time public information from across the web

Parallel Research

Execute multiple research agents simultaneously for 4x faster results

CRM Integration

Enrich AI research with structured data from your CRM system

Structured Output

Generate consistent, formatted meeting prep documents from AI synthesis

Graceful Degradation

Workflow delivers value even when some data sources are unavailable

Example meeting prep output

Here’s what a completed meeting prep document looks like:
# Meeting Prep: Acme Corporation

## Executive Summary
Acme Corporation is a mid-market SaaS company ($50M ARR, 200 employees) specializing in project management software for construction companies. They're experiencing rapid growth (40% YoY) and recently announced Series B funding. We have one open opportunity ($120K ARR) currently in negotiation stage.

## Company Quick Facts
- **Industry:** Construction Technology (ConTech)
- **Size:** 200 employees, $50M ARR
- **Headquarters:** Austin, TX
- **Founded:** 2018
- **What they do:** Cloud-based project management and collaboration platform for construction teams

## Key Contacts

### Sarah Chen - VP of Engineering (Your meeting contact)
- **Background:** Former Amazon engineer, joined Acme 2 years ago
- **Focus:** Scaling engineering team (doubled in last year), improving platform reliability
- **Recent activity:** Spoke at ConstructTech Summit about scaling challenges
- **Talking points:**
  - Our observability platform's construction industry expertise
  - How we've helped similar high-growth teams scale
  - Integration with their existing AWS infrastructure

### Michael Torres - CTO
- **Background:** Co-founder, technical visionary
- **Tenure:** Since founding (2018)
- **Priorities:** AI/ML capabilities, mobile experience, real-time collaboration

## Opportunity Context

**Open Opportunity:** "Acme Corp - Enterprise Observability Platform"
- **Stage:** Negotiation
- **Value:** $120K ARR (3-year contract)
- **Close Date:** End of Q1 2026
- **Champion:** Sarah Chen (VP Engineering)
- **Decision Factors:** ROI timeline, integration complexity, support SLA

**Historical Context:**
- First engagement: 3 months ago (inbound demo request)
- Previous demos: 2 (well-received)
- Trial period: Completed successfully (positive feedback)
- Main concern: Price vs. alternatives

**Relationship Strength:** MODERATE
- Regular engagement, positive sentiment
- Trial went well but no contract signed yet
- Competitor evaluation in parallel (Datadog mentioned)

## Recent News & Developments

1. **Series B Funding Announcement (2 weeks ago)**
   - Raised $30M led by Sequoia Capital
   - Plans to double engineering team
   - **Sales Angle:** Perfect timing - they have budget and hiring plans align with needing better observability

2. **Partnership with Autodesk (1 month ago)**
   - Integrating Acme with Autodesk Construction Cloud
   - Significant technical complexity increase
   - **Sales Angle:** Our platform can help manage complexity of new integration

3. **Industry Award (3 weeks ago)**
   - Named "Construction Tech Innovator of the Year"
   - Increased market visibility and customer growth
   - **Sales Angle:** With growth comes monitoring challenges - we scale with them

## Suggested Agenda

1. **Opening (5 min)**
   - Congratulate on Series B funding and Autodesk partnership
   - Recap trial period feedback

2. **Address Concerns (15 min)**
   - ROI modeling: Show how customers see ROI within 6 months
   - Integration: Live demo of AWS integration (their stack)
   - Pricing: Discuss volume discounts, multi-year options

3. **Value Alignment (15 min)**
   - How we support high-growth engineering teams
   - Construction industry specifics (we have 12 ConTech customers)
   - Support SLA and partnership approach

4. **Competitive Differentiation (10 min)**
   - vs. Datadog: Better cost structure at their scale, superior ML anomaly detection
   - Customer testimonials from similar companies

5. **Next Steps (5 min)**
   - Propose pilot with expanded team during Autodesk integration
   - Timeline to decision
   - Introduce customer success team

## Potential Concerns & Objections

**"Your pricing is higher than Datadog"**
→ True for base tier, but our pricing scales better. At your projected growth (2x team size), we're actually 30% cheaper. Plus, include ROI calculator showing downtime prevention value.

**"We need to see more construction industry expertise"**
→ We have 12 ConTech customers including [competitor names]. Offer reference calls. Highlight construction-specific dashboards and alerting templates.

**"Integration complexity concerns"**
→ Our AWS integration takes under 2 hours. Offer to do integration live during trial extension. Customer success team available throughout.

**"Can you meet our SLA requirements?"**
→ Yes - 99.9% uptime SLA standard, 99.99% available for Enterprise tier. Discuss their specific requirements.

## Success Metrics & Next Steps

**This meeting is successful if:**
- ✅ Address pricing concerns with ROI modeling
- ✅ Secure commitment to decision timeline (2 weeks)
- ✅ Get introduced to CTO (Michael Torres) for technical deep-dive
- ✅ Agree on extended trial with Autodesk integration as test case

**Proposed Next Steps:**
1. Extended trial (2 weeks) with full team during Autodesk integration
2. Technical deep-dive with CTO next week
3. Reference calls with 2 ConTech customers
4. Custom proposal with volume pricing by end of week
5. Final decision meeting with CFO in 2 weeks

---
*Prepared by MagOneAI Sales Intelligence • 2026-02-10 08:30 AM*

Customization ideas

Extend this workflow to match your sales process:
Connect deeply with your CRM for complete context:
  • Salesforce: Use Salesforce API to pull account, opportunity, and contact data
  • HubSpot: Query deals, companies, and contact timeline
  • Custom CRM: Build API integration with REST/GraphQL endpoints
Enhanced data to pull:
  • Complete interaction timeline (emails, calls, meetings)
  • Support ticket history (if customer)
  • Product usage analytics (if available)
  • Sentiment analysis from past communications
  • Win/loss analysis from similar deals
Implementation:
  • Add “CRM Context Enrichment” agent before parallel research
  • This agent queries CRM and structures data for other agents
  • Include CRM data in all relevant research branches
Monitor social signals for additional context:
  • LinkedIn: Company updates, employee posts, job listings
  • Twitter/X: Company announcements, sentiment, customer feedback
  • Glassdoor: Employee sentiment (indicates company health)
Add 5th parallel branch: Social Media Monitor
  • Research social media activity
  • Identify sentiment trends
  • Flag concerning patterns (layoffs, negative press)
  • Find shared connections for warm introductions
Value: Social signals often reveal insights missing from formal channels
Research competitive landscape:
  • Add 6th parallel branch: Competitive Intelligence Agent
  • Research competitors mentioned in CRM notes
  • Find recent competitor news and product updates
  • Compare positioning and messaging
  • Identify competitive wins/losses in similar deals
Output includes:
  • Competitor strengths and weaknesses
  • Recent competitive news
  • Differentiation talking points
  • Battle cards and objection handling
Proactive meeting preparation:
  • Integrate with calendar (Google Calendar, Outlook)
  • Monitor calendar for new meetings with external companies
  • Automatically trigger research workflow 24h before meeting
  • Send meeting prep via email or Slack
  • Include “Review before meeting” reminder
Implementation:
  • Add calendar webhook trigger
  • Parse meeting invitations for company names
  • Schedule workflow execution for 24h before meeting time
  • Add notification node to deliver prep document
Customize research by industry vertical:
  • Create industry-specific research agents:
    • Healthcare: HIPAA compliance, patient outcomes data
    • Financial Services: Regulatory news, compliance requirements
    • SaaS: Tech stack, integrations, scaling challenges
    • Manufacturing: Supply chain, production capacity
Implementation:
  • Add “Industry Classifier” agent at workflow start
  • Route to industry-specific parallel branches
  • Include industry-specific talking points
  • Reference vertical-specific case studies
Share intelligence across your sales team:
  • Save prep documents to shared repository
  • Tag by company, industry, opportunity stage
  • Enable search: “Show me past briefs on SaaS companies”
  • Collaborative annotations: Team members add notes
  • Feedback loop: Mark “useful” vs “not useful” insights
  • Learn over time: Train synthesis agent on what works
This builds institutional knowledge and improves over time.
Stay informed about customer developments:
  • Create monitoring workflow (separate from prep workflow)
  • Monitor news, social media, CRM activity for key accounts
  • Send alerts when significant events occur:
    • Funding announcements
    • Executive changes
    • Major partnerships
    • Negative news
  • Include suggested actions: “Reach out to congratulate on funding”
Implementation:
  • Scheduled workflow (daily or real-time via webhooks)
  • Monitor priority accounts
  • Filter for high-relevance events
  • Send Slack/email alerts to account owners

Best practices for sales intelligence

Ensure accurate, relevant research:
  • Validate company names before research (handle typos, abbreviations)
  • Use high-quality sources (official websites, major news outlets)
  • Include source citations for fact-checking
  • Flag low-confidence information clearly
  • Update research periodically (don’t rely on stale data)
  • Handle data gaps gracefully (don’t hallucinate information)

Next steps

Now that you’ve built a sales intelligence assistant, explore related cookbooks:
Want to add advanced features like sentiment analysis, competitive battle cards, or predictive deal scoring? Contact our solutions team for guidance.