Vibe Prospecting - Explorium docs

Overview

Vibe Prospecting combines conversational AI with Explorium’s comprehensive B2B database to deliver:

Natural language prospecting - Ask for what you need in plain English
Smart filtering - AI automatically selects the right filters from 20+ business and prospect attributes
Rich data enrichment - Add firmographics, technographics, contacts, funding data, and more
Event-based targeting - Find companies experiencing specific business events
Bulk operations - Process up to 1,000 entities per query with enterprise-grade performance

Key Features

Intelligent Business & Prospect Discovery

Find companies and decision-makers using any combination of filters:

Company attributes: Industry, size, revenue, location, age, tech stack, funding status
Prospect attributes: Job title, seniority, department, experience, location
Business events: Funding rounds, partnerships, office expansions, hiring trends, leadership changes
Intent signals: Companies showing buying intent for specific topics (premium feature)

Comprehensive Data Enrichment

Enhance your results with detailed information: For Businesses:

Firmographics (company details, size, revenue)
Technographics (complete technology stack)
Funding & acquisitions history
Financial metrics & SEC insights
Workforce trends & department composition
LinkedIn posts & engagement
Website changes & keyword detection
Corporate hierarchies & subsidiaries

For Prospects:

Professional & personal email addresses
Phone numbers (mobile & direct)
Full work history & education
LinkedIn profiles & activity
Role details & tenure

The Hub - Your Data Control Center

Manage all your prospecting data in one place:

View and manage exported datasets
Upload and enrich your own CSV files
Exclude specific entities from future searches
Track credit usage per dataset
Re-import datasets for follow-up searches

Getting Started

Basic Query Structure

Simply tell the AI what you’re looking for:

Find VP of Sales at Series B SaaS companies in California with 100-500 employees

The AI will:

Parse your requirements
Apply appropriate filters
Show you a sample preview with estimated cost
Wait for your confirmation before exporting

Your First Search

Example 1: Finding Decision Makers

Get me CTOs at fintech companies in New York that raised funding in the last 90 days

What happens:

AI identifies entity type: prospects
Filters: job_title (CTO), linkedin_category (fintech), location (New York), events (funding)
Returns sample with estimated export cost
Waits for your approval to export

Example 2: Finding Companies

Show me B2B SaaS companies with 50-200 employees using Salesforce in their tech stack

What happens:

AI identifies entity type: businesses
Filters: industry (SaaS), size (50-200), technology (Salesforce)
Returns company details in sample preview
Shows cost estimate for full export

Use Cases

1. Sales Prospecting

Scenario: Find decision-makers at high-growth companies

Find VPs of Engineering at companies that increased their engineering department by 20%+ in the last 60 days

Why it works: Combines role targeting with hiring signals to identify companies actively scaling their teams.

2. Market Research

Scenario: Analyze market segments

Get me statistics on healthcare software companies in the US with 100-1000 employees, 
broken down by revenue range

Why it works: Uses the statistics endpoint to provide market insights without consuming credits on individual records.

3. Event-Driven Outreach

Scenario: Reach companies during key moments

Find marketing directors at companies that just opened new offices in the last 30 days

Why it works: Targets prospects during organizational changes when they’re more likely to need new solutions.

4. Account Expansion

Scenario: Find new contacts at existing customers

I have a list of 50 companies. Find all C-level executives in the sales and marketing 
departments at these companies.

Why it works: Upload your customer list to the Hub, then use it as a reference to find additional decision-makers.

5. Competitive Intelligence

Scenario: Monitor competitor customers

Find companies using [Competitor Product] with 500+ employees in the enterprise software space

Why it works: Identifies prospects using competitor technology who might be open to switching.

Best Practices

Writing Effective Queries

Be Specific About What You Need ✅ Good: “Find CTOs at Series B fintech companies in San Francisco with 50-200 employees” ❌ Avoid: “Find some tech people” Combine Multiple Criteria ✅ Good: “Sales directors at SaaS companies that raised funding in the last 90 days and use Salesforce” ❌ Avoid: Making separate searches that could be combined Use Natural Language ✅ Good: “Companies that recently expanded their engineering teams” ❌ Avoid: Trying to write filter syntax manually

Understanding Entity Types

Vibe Prospecting works with two entity types: Choose “Prospects” when you need:

Individual people/contacts
Email addresses or phone numbers
Specific job titles or roles
Decision-makers at companies

Choose “Businesses” when you need:

Company information only
Firmographics or technographics
Market research data
Lists of organizations

The AI automatically determines entity type, but mentioning “people,” “contacts,” or “executives” will ensure prospect results.

Optimizing Credit Usage

1. Start with statistics Before running expensive prospect searches:

What's the market size of cybersecurity companies with 100-500 employees in the US?

This helps validate your target market without using credits. 2. Review samples before exporting Always check the sample preview to ensure:

Results match your expectations
Data quality meets your needs
Cost is acceptable for your budget

3. Use exclusion lists Prevent duplicate spending:

Find new prospects, but exclude entities I've already exported

4. Be precise with enrichments Only request enrichments you’ll actually use:

Enrich with contacts only

vs.

Enrich with everything available

Handling Large Datasets

For queries returning 1,000+ results: The system caps at 1,000 results per query. To get more:

First query: "Find SaaS companies in California with 100-500 employees"
Second query: "Find SaaS companies in New York with 100-500 employees"

Split by geography, industry subcategory, or company size.

Working with Enrichments

When to Enrich

Enrichments add detailed information but consume additional credits. Request them when:

You need contact information: Always use enrich-prospects-contacts for emails/phones
You need company details: Use enrich-business-firmographics for basic company info
You need technology insights: Use enrich-business-technographics for full tech stack
You need funding data: Use enrich-business-funding-and-acquisitions for investment history

Enrichment Examples

Getting Email Addresses

Find marketing managers at fintech companies, and get their email addresses

AI automatically applies: enrich-prospects-contacts Getting Company Technology Stack

Show me which technologies are used by top e-commerce companies

AI automatically applies: enrich-business-technographics Multiple Enrichments

Find CTOs at recently funded companies and get their emails, plus company funding details

AI applies both: enrich-prospects-contacts and enrich-business-funding-and-acquisitions

Understanding Costs

Credit System

Vibe Prospecting uses Explorium credits:

Base fetch: ~1 credit per entity
Enrichments: Additional credits per enrichment type per entity
Events: Additional credits when fetching detailed event information

Cost Estimation

Before any export, you’ll see:

Export Cost: 450 credits

Sample Preview (5 of 150):
[Table with sample data and cost_in_credits column]

Ready to Export? Get all 150 prospects with full details
👉 Say "export" to download the complete dataset as CSV 👈

Never auto-exports - you always approve costs first.

Using The Hub

Accessing The Hub

[IMAGE PLACEHOLDER: Hub dashboard showing datasets, credit usage, and upload button] The Hub is your central workspace for managing all prospecting data.

Managing Exported Datasets

View Your Datasets All exported data appears in the Hub with:

Dataset name (auto-generated based on search)
Entity count
Export date
Credit cost
Status (ready, processing, error)

Re-Import Previous Searches

Load my dataset from last week about SaaS CTOs

The AI will:

Search your Hub for matching datasets
Show available options if multiple matches
Load the data into your current session
Allow you to enrich, filter, or export again

Excluding Entities

Automatic Exclusion Every export automatically adds entities to your exclusion list, preventing duplicates in future searches. Manual Exclusion

Exclude all prospects from my "Q4 2024 Outreach" dataset

Using Exclusion Lists

Find new VPs of Sales at fintech companies, but exclude anyone I've already contacted

AI automatically applies your default exclusion list.

Uploading CSV Files

Use Cases for CSV Upload:

Enrich your existing data: Upload company names/domains to get firmographics, tech stack, contacts
Find contacts at your accounts: Upload customer list to find decision-makers
Clean and standardize data: Upload messy data to get standardized Explorium IDs and enriched fields

How to Upload [IMAGE PLACEHOLDER: CSV upload interface with drag-and-drop area] Step 1: Prepare Your CSV Your CSV should contain: For businesses:

company_name,domain
Explorium,explorium.ai
Anthropic,anthropic.com

For prospects:

full_name,company_name,email
John Smith,Acme Corp,john@acme.com
Jane Doe,Acme Corp,jane@acme.com

Step 2: Upload to Hub

Click “Upload CSV” in the Hub
Drag and drop your file or click to browse
Map your CSV columns to Explorium fields
Review mapping and confirm upload

Step 3: Process Your Data Once uploaded, tell the AI what you want:

Find all C-level executives at the companies in my uploaded list

Or:

Enrich my uploaded companies with technographics and funding data

Step 4: Export Results Review the sample, approve costs, and export as usual.

Working with Referenced Data

Refining Previous Searches

From my last search of SaaS companies, find only those in California

AI uses businesses_reference_table to filter previous results without re-fetching. Cross-Referencing Datasets

Find prospects at companies from my "Series B SaaS" dataset who joined in the last 6 months

Combines company data from one search with prospect filtering in another.

Advanced Features

Business Events

Target companies experiencing specific moments: Available Event Types: Growth & Expansion:

new_funding_round
ipo_announcement
new_office
new_partnership
new_product

Organizational Changes:

increase_in_engineering_department
increase_in_sales_department
increase_in_marketing_department
hiring_in_[department]_department
employee_joined_company

Challenges & Opportunities:

cost_cutting
closing_office
merger_and_acquisitions
lawsuits_and_legal_issues
outages_and_security_breaches

Example:

Find companies that raised Series B funding in the last 60 days and are hiring 
aggressively in engineering

Intent Signals (Premium)

Target companies showing buying intent:

Find companies with high intent for "cybersecurity solutions" in the finance industry

Intent levels:

emerging_intent: Early research stage
high_intent: Active evaluation
very_high_intent: Near purchase decision

Prospect Events

Track individual career changes: Available Prospect Event Types:

prospect_changed_role: Promoted or changed positions
prospect_changed_company: Moved to a new company
prospect_job_start_anniversary: Tenure milestones

Example:

Find VPs who were recently promoted in the last 30 days at enterprise software companies

Statistics & Market Insights

Get aggregated data without consuming credits on individual records:

Show me the distribution of SaaS companies by revenue range in the US

Perfect for:

Market sizing
TAM analysis
Industry research
Investment thesis validation

Query Examples by Industry

SaaS & Technology

Find product managers at B2B SaaS companies with 100-500 employees that use React 
and are hiring in engineering

Financial Services

Show me CFOs at fintech companies that raised Series A or B in the last year with 
$10M-$50M in revenue

Healthcare

Find CTOs at healthcare technology companies with 200+ employees using AWS and 
HIPAA compliance tools

E-commerce & Retail

Get marketing directors at D2C e-commerce brands with $5M-$25M revenue that recently 
expanded to new offices

Manufacturing & Industrial

Find operations directors at manufacturing companies with 500-2000 employees that 
recently invested in automation technology

Troubleshooting

No Results Found

If your search returns zero results:

Broaden your criteria: Try removing one or two filters
Check geography: Ensure location codes are correct (use “US” not “USA”)
Verify timing: Events older than 90 days may not be captured
Try statistics first: Validate your target market exists

Example: Instead of:

Find CTOs at Series B fintech companies in Austin using React, Python, and Kubernetes

Try:

Find CTOs at fintech companies in Texas using React

Understanding Sample vs. Export

Sample Preview:

Shows 5-10 example results
For events: shows up to 3 events per entity
Includes cost estimate
Does NOT consume credits

Full Export:

Returns ALL matching results (up to 1,000)
For events: returns ALL events per entity (often 10-100+ per entity)
Consumes credits as shown in estimate
Generates downloadable CSV

Important: The sample preview is NOT the full dataset. Always export to get complete data.

Dataset Not Ready

If you see “dataset is processing”:

Wait 30-60 seconds - Large datasets take time
Check status - “Ready” means you can export
Try again - Processing usually completes quickly

Credit Management

Check Your Balance:

How many credits do I have?

Estimate Before Exporting: Always review the cost estimate before approving export. The system shows:

Total credits required
Cost breakdown by enrichment type
Whether you have sufficient credits

Partial Exports: If you lack credits for a full export, the system may return partial results proportional to your available balance.

Tips & Tricks

1. Layer Your Search

Start broad, then refine:

Step 1: "Find SaaS companies with 100-500 employees"
Step 2: "From those results, show me only ones using Salesforce"
Step 3: "Now find CTOs at those companies"

2. Combine Signals

Stack multiple indicators for higher quality:

Find VPs of Sales at companies that:
- Raised funding in the last 90 days
- Are hiring in sales department
- Use Salesforce and Outreach
- Have 50-200 employees

3. Use Exclusions Strategically

Create segments:

Query 1: "Find fintech prospects" (exports 500, all excluded)
Query 2: "Find fintech prospects" (returns 500 NEW prospects)

4. Leverage Reference Tables

Build on previous work:

Step 1: Find target companies
Step 2: Enrich with firmographics
Step 3: Use those companies to find multiple personas (CTO, VP Eng, Head of Product)

5. Validate Before Scaling

Test with small samples:

"Find 50 prospects matching [criteria]"
Review data quality
If good: "Find 1000 prospects matching [criteria]"

API Access

Vibe Prospecting is also available via the AgentSource API for programmatic access. Visit the API documentation for:

Authentication & setup
Endpoint reference
Code examples in Python, Node.js, and cURL
Webhook integration
Rate limits & quotas

Support & Feedback

Getting Help

In-app: Use the chat to ask questions about features or troubleshoot issues
Documentation: Visit developers.explorium.ai for guides and API reference
Support: Contact support@explorium.ai for technical assistance

Providing Feedback

Help us improve Vibe Prospecting:

Share feature requests with your account manager
Report bugs or data quality issues to support

What’s Next?

Now that you understand Vibe Prospecting, try these next steps:

Run your first search: Start with a simple query to get familiar
Explore the Hub: Upload a small CSV to test enrichment
Set up exclusions: Configure your default exclusion list
Try different use cases: Experiment with events, intent signals, and statistics
Scale up: Once comfortable, run larger searches and build your prospecting workflow

Happy prospecting! 🎯

​Overview

​Key Features

​Intelligent Business & Prospect Discovery

​Comprehensive Data Enrichment

​The Hub - Your Data Control Center

​Getting Started

​Basic Query Structure

​Your First Search

​Use Cases

​1. Sales Prospecting

​2. Market Research

​3. Event-Driven Outreach

​4. Account Expansion

​5. Competitive Intelligence

​Best Practices

​Writing Effective Queries

​Understanding Entity Types

​Optimizing Credit Usage

​Handling Large Datasets

​Working with Enrichments

​When to Enrich

​Enrichment Examples

​Understanding Costs

​Credit System

​Cost Estimation

​Using The Hub

​Accessing The Hub

​Managing Exported Datasets

​Excluding Entities

​Uploading CSV Files

​Working with Referenced Data

​Advanced Features

​Business Events

​Intent Signals (Premium)

​Prospect Events

​Statistics & Market Insights

​Query Examples by Industry

​SaaS & Technology

​Financial Services

​Healthcare

​E-commerce & Retail

​Manufacturing & Industrial

​Troubleshooting

​No Results Found

​Understanding Sample vs. Export

​Dataset Not Ready

​Credit Management

​Tips & Tricks

​1. Layer Your Search

​2. Combine Signals

​3. Use Exclusions Strategically

​4. Leverage Reference Tables

​5. Validate Before Scaling

​API Access

​Support & Feedback

​Getting Help

​Providing Feedback

​What’s Next?