AI Navigation is currently only available for Enterprise customers. Contact sales to upgrade.
AI Navigation lets you describe any web scraping task in plain language. Our coordination AI agent then breaks down the task and enlists sub-agents to complete it. Use it when you need:
  • browser interactions (clicks, forms)
  • search, crawling, or multi-step navigation
  • data extraction from files (PDF, Excel, CSV)

​
When to Use

AI Navigation is ideal for scenarios that were previously difficult or impossible to automate:
  • Browser interactions – Handle multi-step click and type interactions before extracting data
  • File extraction – Locate, download, and extract the right content from files (PDF, Excel, CSV)
  • Scraping behind login – Access portals before collecting information
  • Search and crawling – Start from a root URL, then find and retrieve content based on keywords
AI Prompt

​
How to Use

To create a workflow with AI Navigation, you can set it up the same way as you would set up a normal workflow:
  1. Define the source URL - Start with any website URL where your data extraction begins
  2. Define your data schema
    • Auto-detected schema: The agent extracts what it discovers on the page or what you describe in your prompt
    • Manually defined schema: Any pre-defined or manually created schema will be used by the AI agent
  3. Choose AI Navigation mode - Select “AI Navigation” as your navigation method
  4. Write your instructions - Describe the step-by-step navigation and extraction process in natural language
  5. Test and deploy - Run a test extraction to validate the workflow, then deploy for production use

​
Writing Effective Prompts

For best results, try to be specific with your instructions:

​
1. Start with navigation

Be specific about where to go and what to click
  • ✅ “Navigate to the careers section, then click on ‘Engineering roles’”
  • ❌ “Find job postings”

​
2. Handle interactions

Tell the AI how to use forms, filters, or authentication
  • ✅ “Search for ‘sensors’ and filter by ‘in stock’”
  • ❌ “Find relevant products”

​
3. Specify data fields

List exactly what data to extract
  • ✅ “Extract: product_name, price, brand, availability”
  • ❌ “Get product information”

​
Variables

Variables allow you to define reusable values that can be referenced in your AI Navigation prompts using @variableName syntax. This is particularly useful when you need to run workflows with different input parameters.

​
How Variables Work

When your workflow runs, Kadoa automatically replaces variable references with the actual values you’ve defined. Example: If you create a variable named keywords with the value "ESG reports", this prompt: 
- Search for @keywords
- Filter by "2025"
- Extract: data, title, pdfLink
Becomes: 
- Search for "ESG reports"
- Filter by "2025"
- Extract: data, title, pdfLink

​
Creating Variables

  1. Navigate to team settings in your dashboard sidebar
  2. Click Add variable
  3. Enter a unique Key (no spaces allowed)
  4. Select the Data Type (String, Number, Boolean)
  5. Enter the Value
  6. Click Save

​
Using Variables in Prompts

When writing AI Navigation instructions:
  • Type @ to see available variables
  • Select from the suggestion list or type the variable name manually
  • The variable will be highlighted in your prompt editor
- Loop through ZIP codes @zipCodes in the location field
- Search for nearby stores within @radius miles
- Extract: store_name, address, phone, hours
Variables: zipCodes: ["10001","10002"], radius: 25

​
Using Variables via API

You can also use variables when creating workflows via API. Read more here. K

​
Example Prompts

​
Static Examples

- Search for "industrial sensors"
- Filter by "in stock"
- Extract: part_number, description, quantity, unit_price, supplier_code
- Download the technical specification PDFs for each product
- Continue through all result pages

- Navigate to the investor relations section
- Find all quarterly earnings reports from 2024-2025
- Download each PDF and extract: revenue, net_income, eps, guidance
- Also collect the following metadata: report_date, fiscal_quarter, filing_type