Bardeen

Extracts structured data from websites using pre-built or custom scraper templates that define CSS selectors, XPath patterns, or DOM traversal rules. The agent executes these templates against target URLs, handling pagination and multi-page crawling within a single workflow step. Templates are credit-metered (10 credits per scrape action) and support both generic website scraping and specialized scrapers for common platforms (LinkedIn profiles, search results, etc.).

Applies natural language AI evaluation to scraped or imported lead data, filtering candidates against user-defined criteria expressed in plain English (e.g., 'Find leads in tech companies with 50-500 employees'). The agent uses an LLM (provider unspecified, described as 'leading AI providers') to score and rank leads based on semantic matching, not keyword matching. Each qualification action costs 10 credits and operates on batches of leads extracted in prior workflow steps.

Validates email addresses and enriches contact records with verified phone numbers, physical addresses, and professional details by querying third-party data providers. Email validation is a discrete action (4 credits) that checks deliverability and format; enrichment actions (cost unspecified) append missing contact fields to lead records. The agent chains these actions sequentially within a workflow, with results merged back into the original dataset before export.

Exports extracted and enriched lead data directly to Google Sheets, Airtable, Notion, or CSV files in a single workflow action. The export action (30 credits for Google Sheets; cost for other destinations unspecified) handles schema mapping, deduplication, and append-vs-replace logic. Supports both one-time exports and scheduled recurring exports, with data automatically formatted for the target platform's schema.

Performs AI-augmented web searches to find leads, company information, or research data using 'leading AI and websearch providers' (specific providers unspecified). Integrates search results directly into lead sourcing workflows, with results automatically parsed and structured for downstream qualification or enrichment. Search actions are credit-metered and can be chained with scraping and enrichment to create end-to-end research pipelines.

Chains multiple discrete actions (scraping, enrichment, qualification, export) into a single automated workflow that executes sequentially without user intervention. Users define the workflow via a visual builder or template, specifying input/output mappings between actions. Each action is credit-metered independently, with total workflow cost calculated upfront. Workflows can be saved as templates and reused across multiple runs, with optional scheduling for recurring execution.

Operates as a browser extension that allows users to trigger scraping, enrichment, and export actions directly from web pages they're browsing, without leaving the browser or copying data manually. The extension provides a context menu or sidebar UI for selecting elements to scrape, defining extraction rules, or triggering pre-built workflows on the current page. Results are immediately available for export or further processing within the extension.

Provides pre-built, optimized scraper templates for popular platforms (LinkedIn, job boards, e-commerce sites, etc.) that handle platform-specific challenges like pagination, dynamic content, and anti-scraping measures. Templates are maintained by Bardeen and updated as target sites change, eliminating the need for users to build custom selectors. Users can use templates as-is or customize them for specific needs via the visual template builder.

Implements a credit-based pricing model where each action (scraping, enrichment, qualification, export) consumes a fixed number of credits. Users can see upfront credit costs before executing workflows, with total workflow cost calculated as the sum of all action credits. Credits are purchased as part of a subscription or pay-as-you-go plan, with usage tracked and reported in the account dashboard.