> ## Documentation Index
> Fetch the complete documentation index at: https://developers.explorium.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Best Practices

### Writing Effective Queries

**Be Specific About What You Need**

✅ **Good**: "Find CTOs at fintech companies in San Francisco with 50-200 employees"

❌ **Avoid**: "Find tech people in us"

**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. Use 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 before commiting to a full list creation.

**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 email only
```

vs.

```
Enrich with contacts
```

***

### 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:

1. **You need contact information**: Always enrich with `contacts` for emails/phones
2. **You need company details**: Use`firmographics`for basic company info
3. **You need technology insights**: Use`technographics` for full tech stack
4. **You need funding data**: Use`funding-and-acquisitions` for investment history

### Enrichment Examples

**Getting Email Addresses**

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

AI automatically enrich with contacts

**Getting Company Technology Stack**

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

AI automatically applies technographics

**Multiple Enrichments**

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

AI applies both contacts and funding-and-acquisitions

***

## Understanding Costs

### Credit System

Vibe Prospecting uses 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.

***

##