AI Workflow Automation

Just describe what you want. AI figures out the rest.

No more learning 11,000+ Actors. No more writing JSON workflows. Just tell it what you need in plain English.

"Find 20 AI startups in Austin and get their contact emails"

AI automatically:

1. Breaks down your request into steps
2. Selects the best Actors for each task
3. Executes the workflow
4. Summarizes results in clean, AI-ready format

3 Ways to Use

1. AI Mode (Recommended)

Just describe what you want:

{
    "prompt": "Compare laptop prices on Amazon and eBay",
    "openaiApiKey": "sk-or-...",
    "maxBudget": 5.00
}

Note: Uses OpenRouter API (get free key at openrouter.ai). Supports GPT-4, Claude, Llama, and more.

AI will:

• Decompose into tasks (search Amazon, search eBay)
• Select appropriate Actors
• Execute in parallel
• Return summarized comparison

2. Template Mode

Use pre-built workflows:

{
    "template": "lead-generation-pipeline"
}

Available Templates:

• ecommerce-price-comparison - Amazon + eBay price tracking
• lead-generation-pipeline - Google → Scrape → Extract emails
• real-estate-market-analysis - Zillow listings
• social-media-monitoring - Track brand mentions
• seo-competitor-analysis - SERP + page analysis
• news-aggregation - Multi-source news
• review-sentiment-analysis - Google Maps reviews

3. Custom Workflow

Define your own:

{
    "workflow": {
        "name": "my-workflow",
        "steps": [
            {
                "id": "search",
                "actorId": "apify/google-search-scraper",
                "input": { "queries": ["AI companies Austin"] }
            },
            {
                "id": "scrape",
                "actorId": "apify/cheerio-scraper",
                "dependsOn": ["search"],
                "inputMappings": [{
                    "sourceStepId": "search",
                    "sourceField": "organicResults",
                    "targetField": "startUrls"
                }]
            }
        ]
    }
}

Key Features

Feature	Description
AI Task Decomposition	Natural language → executable workflow
Smart Actor Selection	AI picks the best Actor for each task
Cost Estimation	Know the cost before running
Parallel Execution	Run 10 steps simultaneously
Auto-Retry	Failed steps retry automatically
LLM-Optimized Output	Clean summaries for AI agents
Dry Run Mode	Preview without executing

Input Parameters

Parameter	Type	Description
prompt	string	Describe what you want in plain English
openaiApiKey	string	OpenRouter API key (free at openrouter.ai)
template	string	Pre-built workflow template ID
workflow	object	Custom workflow definition
maxBudget	number	Maximum spend limit ($)
outputFormat	string	llm-optimized, markdown, json, raw
maxConcurrency	integer	Parallel steps (1-10)
dryRun	boolean	Preview only, don't execute

Output Formats

LLM-Optimized (Default)

Compact, token-efficient summary perfect for AI agents:

## Summary
Found 20 AI companies in Austin with contact information.

## Key Findings
- 18/20 companies have public email addresses
- Most common domain: .io (40%)
- Average company size: 15-50 employees

## Top Contacts
- TechCo AI: hello@techco.ai
- DataFlow: contact@dataflow.io
...

JSON

Structured data for programmatic use.

Markdown

Human-readable report format.

Raw

Unprocessed scraper output.

Pricing

Event	Price
AI Decomposition	$0.005
Workflow Step	$0.001
Workflow Completed	$0.002

Example: AI-powered 3-step workflow ≈ $0.01

Use Cases

Sales Teams

"Find SaaS companies in San Francisco, get decision-maker emails"

E-commerce

"Track competitor prices on Amazon, eBay, Walmart daily"

Real Estate

"Monitor Zillow for new listings under $500K in Austin"

Marketing

"Aggregate news about AI from 10 sources, summarize key trends"

Research

"Collect Google Maps reviews for coffee shops, analyze sentiment"

AI Agent Integration

Works with Claude, Cursor, LangChain, and any MCP client.

Claude Desktop

{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": ["-y", "@apify/actors-mcp-server"],
            "env": {
                "APIFY_TOKEN": "your_token"
            }
        }
    }
}

Then just ask Claude:

"Use the AI workflow automation Actor to find and contact AI startups"

Examples

Lead Generation

{
    "prompt": "Find 50 marketing agencies in New York, scrape their websites, extract contact emails and phone numbers",
    "openaiApiKey": "sk-...",
    "outputFormat": "json"
}

Price Monitoring

{
    "prompt": "Compare prices for 'Sony WH-1000XM5' on Amazon vs eBay",
    "openaiApiKey": "sk-...",
    "maxBudget": 2.00
}

Competitive Intelligence

{
    "prompt": "Analyze top 10 Google results for 'project management software', extract their features and pricing",
    "openaiApiKey": "sk-..."
}

Dry Run (Preview)

{
    "prompt": "Find tech jobs in Austin",
    "openaiApiKey": "sk-...",
    "dryRun": true
}

Returns what WOULD be executed without running.

How It Works

1. You describe what you want
           ↓
2. AI decomposes into tasks
           ↓
3. AI maps tasks to Actors
           ↓
4. Cost estimation & preview
           ↓
5. Parallel execution
           ↓
6. AI summarizes results
           ↓
7. Clean, actionable output

Limitations

• Requires OpenRouter API key for AI features (free at openrouter.ai)
• Max 50 steps per workflow
• Max 10 concurrent steps
• Max 24 hour timeout

Changelog

v3.0.0 (2026-01-12)

• AI Task Decomposition: Natural language prompts
• Smart Actor Selection: AI picks best Actors
• Cost Estimation: Budget control
• LLM-Optimized Output: Token-efficient summaries
• Dry Run Mode: Preview before executing

v2.0.0 (2026-01-11)

• Pre-built templates
• Parallel execution
• Auto-retry

v1.0.0 (2026-01-10)

• Initial release