Online presence
What does their digital footprint look like?
1.Clean URL — clean_website_url
Normalizes URLs and domains and can reject social or third-party hosts.
Inputs
Field | Required | Description |
|---|---|---|
url | ✅ | URL to normalize |
mode | — | tld, clean, or clean_no_3p |
Outputs
Field | What you get |
|---|---|
result_url | Cleaned domain or URL |
is_social | Whether input is a social or profile URL |
errors | Any issues that came up |
🔗 Chain it: find_business_website → clean_website_url → tech_stack_scan
2.Website Modernity — detect_website_modernity
Classifies a site as Modern or Old from HTML and site signals.
Inputs
Field | Required | Description |
|---|---|---|
website | ✅ | Website URL |
llm | — | Model override |
Outputs
Field | What you get |
|---|---|
website_modernity | Modern, Old, or null |
reasoning | Short explanation |
errors | Any issues that came up |
🔗 Chain it: clean_website_url → detect_website_modernity → icp_score
3.Google Business Profile — find_business_on_google
Finds the best Google Maps listing with rich profile fields.
Inputs
Field | Required | Description |
|---|---|---|
company_name | ✅ | Business name |
address | — | Address hint |
city | — | City hint |
state | — | State hint |
country | — | Country hint |
latitude | — | Lat hint |
longitude | — | Lng hint |
llm | — | Model override |
Outputs
Field | What you get |
|---|---|
place_id | Google Place ID |
title | Listing title |
website | Listed website |
rating | Star rating |
reviews | Review count |
confidence | Match confidence (0–100) |
errors | Any issues that came up |
🔗 Chain it: find_business_on_google → find_business_website → enrich_google_reviews
4.Find Website — find_business_website
Finds the canonical company website from company name and location context. Starting point for most workflows.
Inputs
Field | Required | Description |
|---|---|---|
company_name | ✅ | Company name |
address | — | Address hint |
city | — | City hint |
state | — | State hint |
llm | — | Model override |
Outputs
Field | What you get |
|---|---|
website | Candidate official website |
source | Provenance metadata |
confidence | Match confidence (0–100) |
errors | Any issues that came up |
🔗 Chain it: find_business_on_google → find_business_website → enrich_company_firmographics
5.Company Social Profiles — find_company_social_urls
Finds official Facebook, Instagram, LinkedIn, and Yelp URLs with confidence labels.
Inputs
Field | Required | Description |
|---|---|---|
company | ✅ | Company name |
website | ✅ | Company website |
address | — | Address hint |
llm | — | Model override |
max_iterations | — | Search loop limit |
Outputs
Field | What you get |
|---|---|
facebook_url | Facebook URL |
instagram_url | Instagram URL |
linkedin_url | LinkedIn URL |
yelp_url | Yelp URL |
errors | Any issues that came up |
🔗 Chain it: find_business_website → find_company_social_urls → enrich_google_reviews
6.Tech Stack — tech_stack_scan
Builds a website technology profile via crawl and signatures, with optional additional research.
Inputs
Field | Required | Description |
|---|---|---|
url | ✅ | Website URL |
company_name | ✅ | Company name |
categories | — | Requested tech categories |
techs | — | Requested specific techs |
enable_online_research | — | Toggle extra research |
llm | — | Model override |
Outputs
Field | What you get |
|---|---|
profile | Final tech profile object |
errors | Any issues that came up |
🔗 Chain it: clean_website_url → tech_stack_scan → icp_score
7.Website Status — website_active_inactive
Classifies a site as Active or Inactive (parked, for sale, error, etc.).
Inputs
Field | Required | Description |
|---|---|---|
url | ✅ | Website URL |
llm | — | Model override |
Outputs
Field | What you get |
|---|---|
overall_category | Active, Inactive, or null |
inactive_reason | Why it was marked inactive |
reasoning | Supporting rationale |
errors | Any issues that came up |
🔗 Chain it: clean_website_url → website_active_inactive → find_business_website