Lead Hand - OpenFang

Overview

Lead Hand is an AI-powered lead generation engine that continuously discovers prospects, enriches their profiles with business intelligence, and delivers qualified leads on your schedule. Category: Data
Icon: 📊

What It Does

Define Target Profile

Configure your ideal customer profile (industry, role, company size, geography)

Discover Leads

Multi-source web research to find decision-makers matching your criteria

Enrich & Score

Gather company data, growth signals, and score each lead by fit

Deduplicate

Cross-reference against your existing database to avoid duplicates

Deliver Reports

Generate CSV/JSON/Markdown reports on your schedule (daily, weekly, etc.)

Configuration

Target Profile

Setting	Description	Example
Target Industry	Industry vertical to focus on	`SaaS`, `fintech`, `healthcare`
Target Role	Decision-maker titles	`CTO`, `VP Engineering`, `Head of Product`
Company Size	Filter by employee count	`startup` (1-50), `smb` (50-500), `enterprise` (500+)
Geographic Focus	Region to prioritize	`US`, `Europe`, `APAC`, `global`

Lead Discovery

Setting	Options	Description
Lead Source	`web_search`, `linkedin_public`, `crunchbase`, `custom`	Primary discovery method
Leads Per Report	10, 25, 50, 100	Number of leads per report
Delivery Schedule	`daily_7am`, `daily_9am`, `weekdays_8am`, `weekly_monday`	When to generate reports

Enrichment Settings

Setting	Depth	What You Get
Basic	Quick	Name, title, company
Standard	Balanced	+ company size, industry, tech stack
Deep	Thorough	+ funding, recent news, social profiles

Activation

Basic Setup

openfang hand activate lead

Configure your target profile:

openfang hand config lead \
  --set target_industry="SaaS" \
  --set target_role="CTO, VP Engineering" \
  --set company_size="smb" \
  --set geo_focus="US" \
  --set delivery_schedule="daily_9am"

Example Workflow

Target: SaaS companies (50-500 employees) in the US
Role: CTOs and VP Engineering
Delivery: Daily at 9 AM, 25 leads per report

> Find leads for B2B SaaS dev tools targeting engineering leaders

Lead Hand will:

Construct 5-10 search queries combining your criteria
Execute web research across multiple sources
Discover 50-75 raw leads (2-3x your target)
Enrich each lead with company data
Score and rank by fit
Deduplicate against existing database
Generate lead_report_2026-03-06.csv with top 25 leads

How It Works

1. Target Profile Construction

Builds an Ideal Customer Profile (ICP) from your settings:

{
  "industry": "SaaS",
  "roles": ["CTO", "VP Engineering", "Head of Product"],
  "company_size": {"min": 50, "max": 500},
  "geography": "US",
  "signals": ["hiring", "funding", "product launch"]
}

Stored in the knowledge graph for consistency across runs.

2. Lead Discovery

Executes multi-query web research: Query construction examples:

"SaaS CTO hiring US"
"SaaS companies series B funding"
"top SaaS startups 2026"
"50-500 employee SaaS companies US list"
"B2B SaaS engineering leaders"

For each query:

web_search to find results
web_fetch promising company websites, LinkedIn profiles, job boards
Extract structured data:
- Person: name, title, company
- Company: URL, industry, employee count
- Signals: hiring, funding, news

Target: 2-3x your leads_per_report setting for quality filtering.

3. Lead Enrichment

Based on enrichment_depth setting:

Basic Enrichment

Name, title, company (from discovery)

Standard Enrichment

Additionally fetches:

Company website → extract employee count, industry, tech stack, product description
Job boards → hiring signals (growth indicator)

Deep Enrichment

Additionally fetches:

Recent funding news: web_search "[company] funding round"
Recent company news: web_search "[company] news 2026"
Social profiles: web_search "[name] [company] linkedin twitter"

Knowledge graph storage:

knowledge_add_entity({type: "lead", name: "Jane Smith", title: "CTO"})
knowledge_add_entity({type: "company", name: "Acme SaaS Inc", industry: "SaaS"})
knowledge_add_relation({from: "Jane Smith", to: "Acme SaaS Inc", type: "works_at"})

4. Scoring & Ranking

Each lead scored 0-100:

Criteria	Points	Example
ICP Match	+30	Industry, role, size, geo all match
Growth Signals	+20	Hiring, funding, recent news
Enrichment Completeness	+20	All fields populated
Recency	+15	Company active recently
Accessibility	+15	Public contact info available

Example:

Jane Smith, CTO @ Acme SaaS Inc
Score: 85/100
- ICP match: 30/30 (SaaS, CTO, 120 employees, US)
- Growth: 18/20 (hiring 3 engineers, Series B last year)
- Enrichment: 20/20 (full profile)
- Recency: 12/15 (news from 2 months ago)
- Accessibility: 5/15 (LinkedIn public, email pattern inferred)

5. Deduplication

Compares against leads_database.json:

// Normalize and match
const key = `${normalizeCompanyName(lead.company)}_${normalizeName(lead.name)}`

if (existingLeads.has(key)) {
  // Update existing lead with new enrichment data
  leads[key] = mergeEnrichment(existing, newData)
} else {
  // Add new lead
  leads[key] = newLead
}

6. Report Generation

Generate report in configured format:

CSV Format

Name,Title,Company,Company URL,Industry,Company Size,Score,Discovery Date,Notes
Jane Smith,CTO,Acme SaaS Inc,https://acmesaas.com,SaaS,120,85,2026-03-06,"Hiring engineers, Series B funded"

JSON Format

[
  {
    "name": "Jane Smith",
    "title": "CTO",
    "company": "Acme SaaS Inc",
    "company_url": "https://acmesaas.com",
    "industry": "SaaS",
    "size": 120,
    "score": 85,
    "discovered": "2026-03-06",
    "enrichment": {
      "funding": "Series B, $15M",
      "hiring": true,
      "tech_stack": ["React", "Python", "PostgreSQL"]
    }
  }
]

Markdown Table Format

| # | Name | Title | Company | Score | Signal |
|---|------|-------|---------|-------|--------|
| 1 | Jane Smith | CTO | Acme SaaS Inc | 85 | Hiring, Series B |

Saved as: lead_report_YYYY-MM-DD.{csv,json,md}

Output

Lead Hand generates:

File	Description
`lead_report_YYYY-MM-DD.*`	Daily/weekly lead report in your chosen format
`leads_database.json`	Cumulative database of all discovered leads

Dashboard Metrics

Leads Found — Total unique leads discovered
Reports Generated — Number of reports delivered
Last Report — Date of most recent report
Unique Companies — Count of unique companies in database

Scheduling

Lead Hand runs automatically on your configured schedule:

# Check active schedules
openfang schedule list

# Example output:
Schedule: lead-hand-daily
Frequency: daily at 09:00
Last run: 2026-03-06 09:00:00
Next run: 2026-03-07 09:00:00

Manual trigger:

> Generate a lead report now

Tips & Best Practices

For best results:

Start with Standard enrichment depth — Deep can be slow for large batches
Use specific role titles — “VP Engineering” works better than “executive”
Combine with Researcher Hand to verify company fit before outreach
Export to CSV and import into your CRM
Review leads weekly to refine your ICP criteria

Common Issues

“No leads found”
Broaden your criteria — try removing geography filter or increasing company size range. “Too many duplicate leads”
Lead Hand deduplicates automatically. If you’re seeing repeats, delete leads_database.json to reset. “Enrichment data missing”
Some companies have minimal public data. Lower scoring leads often have incomplete profiles. “Wrong industry/role in results”
Web search can return tangential results. Check your target_industry and target_role settings are specific.

Advanced Usage

Custom Lead Sources

Find leads from companies mentioned in this Crunchbase list: [URL]

Competitor Targeting

Find decision-makers at companies using [Competitor Product]

Event-Based Discovery

Find CTOs at companies that recently raised Series A funding in fintech

Export & Integration

# Export to CRM-ready format
openfang hand run lead --export-format salesforce

# Or use the JSON output with custom scripts
cat lead_report_2026-03-06.json | jq '.[] | select(.score > 80)'

Get Started

Core Concepts

Autonomous Hands

Configuration

Integrations

Guides

​Overview

​What It Does

​Configuration

​Target Profile

​Lead Discovery

​Enrichment Settings

​Activation

​Basic Setup

​Example Workflow

​How It Works

​1. Target Profile Construction

​2. Lead Discovery

​3. Lead Enrichment

​Basic Enrichment

​Standard Enrichment

​Deep Enrichment

​4. Scoring & Ranking

​5. Deduplication

​6. Report Generation

​CSV Format

​JSON Format

​Markdown Table Format

​Output

​Dashboard Metrics

​Scheduling

​Tips & Best Practices

​Common Issues

​Advanced Usage

​Custom Lead Sources

​Competitor Targeting

​Event-Based Discovery

​Export & Integration

​Next Steps

Researcher Hand

Collector Hand

Overview

What It Does

Configuration

Target Profile

Lead Discovery

Enrichment Settings

Activation

Basic Setup

Example Workflow

How It Works

1. Target Profile Construction

2. Lead Discovery

3. Lead Enrichment

Basic Enrichment

Standard Enrichment

Deep Enrichment

4. Scoring & Ranking

5. Deduplication

6. Report Generation

CSV Format

JSON Format

Markdown Table Format

Output

Dashboard Metrics

Scheduling

Tips & Best Practices

Common Issues

Advanced Usage

Custom Lead Sources

Competitor Targeting

Event-Based Discovery

Export & Integration

Next Steps