DiscoLike: Discover

Build a company list from seed domains (lookalikes) or a plain-language ICP description, with industry, location, employee-count, revenue, and technology.

Tool ID: discolike_discover

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'discolike_discover',
  {
    "domain": [
      "example.com"
    ],
    "negate_domain": [
      "example.com"
    ],
    "icp_text": "example"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline run discolike_discover --input '{
  "domain": [
    "example.com"
  ],
  "negate_domain": [
    "example.com"
  ],
  "icp_text": "example"
}'

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": [
    {
      "domain": "example.com"
    }
  ]
}

Use deepline describe discolike_discover --json for the latest machine-readable contract.

Input reference

Search firmographic data using domain matching, ICP text matching, or phrase matching. Returns business profiles ranked by relevance with optional AI enhancement.

Name	Type	Required	Default	Details
`payload.domain`	`array`	No	—	Domain(s) for lookalike matching. Up to 10 domains allowed. Maximum items: 10.
`payload.negate_domain`	`array`	No	—	Exclude results matching these domain contexts. Up to 10 domains. Maximum items: 10.
`payload.icp_text`	`string`	No	—	Natural language description of ideal customer profile for semantic matching (3-4000 characters). Minimum length: 3. Maximum length: 4000.
`payload.negate_icp_text`	`string`	No	—	Description of business concepts to exclude from results (3-4000 characters). Minimum length: 3. Maximum length: 4000.
`payload.retrieval`	`boolean`	No	`false`	Enable page data retrieval using Extract API.
`payload.enhanced`	`boolean`	No	`false`	Deprecated and ignored.
`payload.include_search_domains`	`boolean`	No	`false`	Include input domains in results (excluded by default).
`payload.max_records`	`integer`	No	`100`	Maximum records to return (5-10000). Default 500. Minimum: 5. Maximum: 10000.
`payload.consensus`	`integer`	No	`1`	Deprecated and ignored. Minimum: 1. Maximum: 20.
`payload.min_similarity`	`integer`	No	`0`	Minimum similarity score to include (0-99). Minimum: 0. Maximum: 99.
`payload.variance`	`"LOW" \| "MID_LOW" \| "MEDIUM" \| "MID_HIGH" \| "HIGH" \| "UNRESTRICTED"`	No	`"UNRESTRICTED"`	Deprecated. Use `relevance`. LOW/MID_LOW/MEDIUM map to MAX_RELEVANCE, MID_HIGH/HIGH to BALANCED, UNRESTRICTED to no stop. Allowed: `LOW`, `MID_LOW`, `MEDIUM`, `MID_HIGH`, `HIGH`, `UNRESTRICTED`.
`payload.offset`	`integer`	No	`0`	Records to skip for pagination. Minimum: 0. Maximum: 10000.
`payload.exclusion_query_id`	`array`	No	—	Exclude domains from saved queries.
`payload.inclusion_query_id`	`array`	No	—	Include domains from saved queries. Requires STARTER plan.
`payload.auto_icp_text`	`boolean`	No	`false`	Auto-generate ICP text from provided domain(s).
`payload.auto_phrase_match`	`boolean`	No	`false`	Auto-generate phrase matches from ICP text.
`payload.icp_prompt`	`string`	No	—	Natural language ICP description. Automatically extracts structured filters, generates ICP text, suggests domains, and applies them before running discovery. Overrides auto_icp_text and auto_phrase_match when set. Maximum length: 4000.
`payload.phrase_match`	`array`	No	—	Exact text fragments to search for in site content. Up to 20 fragments, each at least 3 characters. Maximum items: 20.
`payload.negate_phrase_match`	`array`	No	—	Exact text fragments to exclude from results. Up to 20 fragments, each at least 3 characters. Maximum items: 20.
`payload.subdomain`	`array`	No	—	Limit results to specified subdomains. Up to 20, each at least 3 characters. Maximum items: 20.
`payload.negate_subdomain`	`array`	No	—	Exclude specified subdomains from results. Up to 20, each at least 3 characters. Maximum items: 20.
`payload.tech_stack`	`array`	No	—	Filter to companies using specified vendor domains (up to 20). Maximum items: 20.
`payload.negate_tech_stack`	`array`	No	—	Exclude companies using specified vendor domains (up to 20). Maximum items: 20.
`payload.category`	`array`	No	—	Filter by industry category (ANY-OF. prefix + to require a category). Valid values: ACCOUNTING, ADVERTISING_AND_MARKETING, AGRICULTURE_AND_NATURAL_RESOURCES, ALCOHOL_AND_TOBACCO, AUTOMOTIVE, BIG_DATA_AND_ANALYTICS, BIOTECHNOLOGY, BLOCKCHAIN_AND_CRYPTOCURRENCY, BUSINESS_PRODUCTS_AND_SERVICES, CLOUD_COMPUTING, COMPUTER_HARDWARE_AND_SEMICONDUCTORS, CONGLOMERATES_SHELL_AND_HOLDING_COMPANIES, CONSTRUCTION, CONSUMER_PRODUCTS, CONSUMER_SERVICES, CYBERSECURITY, DEFENSE_AND_AEROSPACE, E-COMMERCE, See the live schema for the complete constraint.
`payload.negate_category`	`array`	No	—	Exclude specified industry categories. Valid values: ACCOUNTING, ADVERTISING_AND_MARKETING, AGRICULTURE_AND_NATURAL_RESOURCES, ALCOHOL_AND_TOBACCO, AUTOMOTIVE, BIG_DATA_AND_ANALYTICS, BIOTECHNOLOGY, BLOCKCHAIN_AND_CRYPTOCURRENCY, BUSINESS_PRODUCTS_AND_SERVICES, CLOUD_COMPUTING, COMPUTER_HARDWARE_AND_SEMICONDUCTORS, CONGLOMERATES_SHELL_AND_HOLDING_COMPANIES, CONSTRUCTION, CONSUMER_PRODUCTS, CONSUMER_SERVICES, CYBERSECURITY, DEFENSE_AND_AEROSPACE, E-COMMERCE, EDUCATION, ENERGY, ENGINEERING, See the live schema for the complete constraint.
`payload.min_digital_footprint`	`integer`	No	—	Minimum digital footprint score (0-800). Default 25. Minimum: 0. Maximum: 800.
`payload.max_digital_footprint`	`integer`	No	—	Maximum digital footprint score (0-800). Default 800. Minimum: 0. Maximum: 800.
`payload.state`	`array`	No	—	Filter by ISO 3166-2 state codes or names (up to 100), listed at https://docs.discolike.com/states/. Requires exactly one country value, which may be a region alias. The state is then resolved against every country the alias covers. A value that resolves under none is rejected. Maximum items: 100.
`payload.negate_state`	`array`	No	—	Exclude specified states from results (up to 100). Same format and country rules as state. Maximum items: 100.
`payload.country`	`array`	No	—	ISO-3166-1 alpha-2 country codes (e.g., US, GB, DE) or region aliases: EU, LATAM, MENA, APAC, NORDICS, DACH, BENELUX, GCC, ASEAN, CEE, ANZ, EUROPE, ASIA, AFRICA, NORTH_AMERICA, SOUTH_AMERICA, OCEANIA, ANTARCTICA.
`payload.negate_country`	`array`	No	—	Exclude specified countries from results. Accepts same codes and region aliases as country.
`payload.start_date`	`string`	No	—	Minimum company start date (YYYY-MM-DD) or range (YYYY-MM-DD,YYYY-MM-DD).
`payload.redirect`	`boolean`	No	`false`	Include domains that redirect to another domain.
`payload.social`	`array`	No	—	Filter by social platform presence. Valid values: facebook, instagram, linkedin, pinterest, threads, tiktok, twitter, x, yelp, youtube, googleplay, applestore, amazon, vk, bluesky, xing. Note: ‘twitter’ is an alias for ‘x’.
`payload.negate_social`	`array`	No	—	Exclude companies with specified social profiles. Filter by social platform presence. Valid values: facebook, instagram, linkedin, pinterest, threads, tiktok, twitter, x, yelp, youtube, googleplay, applestore, amazon, vk, bluesky, xing. Note: ‘twitter’ is an alias for ‘x’.
`payload.language`	`array`	No	—	Filter by site language. Valid values: af (Afrikaans), ar (Arabic), az (Azerbaijani), bg (Bulgarian), bn (Bengali), bs (Bosnian), ca (Catalan), cs (Czech), da (Danish), de (German), el (Greek), en (English), eo (Esperanto), es (Spanish), et (Estonian), eu (Basque), fa (Persian), fi (Finnish), fr (French), ga (Irish), gl (Galician), he (Hebrew), hi (Hindi), hr (Croatian), hu (Hungarian), hy (Armenian), id (Indonesian), is (Icelandic), it (Italian), ja (Japanese), ka (Georgian), ko (Korean), ky See the live schema for the complete constraint.
`payload.negate_language`	`array`	No	—	Exclude specified languages from results. Filter by site language. Valid values: af (Afrikaans), ar (Arabic), az (Azerbaijani), bg (Bulgarian), bn (Bengali), bs (Bosnian), ca (Catalan), cs (Czech), da (Danish), de (German), el (Greek), en (English), eo (Esperanto), es (Spanish), et (Estonian), eu (Basque), fa (Persian), fi (Finnish), fr (French), ga (Irish), gl (Galician), he (Hebrew), hi (Hindi), hr (Croatian), hu (Hungarian), hy (Armenian), id (Indonesian), is (Icelandic), it (Italian), ja See the live schema for the complete constraint.
`payload.employee_range`	`string`	No	—	Filter by employee count range. Format: ‘min,max’ (e.g., ‘1,5000’). Maps to buckets: 1-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+.
`payload.revenue_range`	`string`	No	—	Filter by company revenue. Format: ‘min,max’ in raw numbers (e.g., ‘1000000,10000000’ for 1M-10M). Maps to buckets: 1B. Unknown-revenue domains (N/A) are included when the range covers the <1M bucket.
`payload.business_model`	`array`	No	—	Filter by business model label. Multi-select with OR semantics. Valid values: B2B, B2C, B2G, G2B, G2C, D2C, C2C, C2B.
`payload.negate_business_model`	`array`	No	—	Exclude domains with these business model labels. Filter by business model label. Multi-select with OR semantics. Valid values: B2B, B2C, B2G, G2B, G2C, D2C, C2C, C2B.
`payload.exclude_leadgen`	`boolean`	No	`true`	Exclude suspected lead generation sites. Filters out profiles with score <= 25 that also lack phone, email, and social media presence.

This input schema is too large for an inline display. Read the complete live contract with deepline describe discolike_discover --json.

Output reference

Standard tool result payload.

Name	Type	Required	Default	Details
`result.data`	`array`	Yes	—	Provider response payload.
`result.data[].domain`	`string`	Yes	—	Company domain and unique record identifier
`result.data[].name`	`string \| null`	No	—	Company name inferred from certificate or website data
`result.data[].status`	`object`	No	—	Company operating status with confidence score.
`result.data[].status.status`	`string \| null`	No	—	Operating status: ‘active’ or ‘closed’
`result.data[].status.confidence`	`number \| null`	No	—	Confidence score for the status (0.0-1.0)
`result.data[].score`	`integer \| null`	No	—	Digital footprint score derived from certificate history (1-800). Not a verified measure of company size or buying power
`result.data[].start_date`	`string \| null`	No	—	First observed certificate date (YYYY-MM-DD). Not a verified company founding or incorporation date
`result.data[].end_date`	`string \| null`	No	—	Company end date if closed (YYYY-MM-DD), empty if still in business
`result.data[].address`	`object`	No	—	Company headquarters address from website metatags or content.
`result.data[].address.street`	`string \| null`	No	—	Street address of HQ, from website metatags or content
`result.data[].address.city`	`string \| null`	No	—	City, from website metatags or content
`result.data[].address.state`	`string \| null`	No	—	State/subdivision name (ISO 3166-2 label). The underlying stored value is the ISO code and filters accept either
`result.data[].address.zip`	`string \| null`	No	—	ZIP/postal code, from website metatags or content
`result.data[].address.country`	`string \| null`	No	—	Two-letter country code (ISO 3166-1 alpha-2), from website metatags or content
`result.data[].latitude`	`number \| null`	No	—	Latitude of the company’s location, when resolved
`result.data[].longitude`	`number \| null`	No	—	Longitude of the company’s location, when resolved
`result.data[].geo_precision`	`string \| null`	No	—	How precisely the location was resolved (e.g. rooftop, city, country)
`result.data[].phones`	`array \| null`	No	—	Array of phone numbers listed on the website
`result.data[].public_emails`	`array \| null`	No	—	Array of contact emails listed on the website
`result.data[].domain_associations`	`array`	No	—	Associated domains
`result.data[].social_urls`	`array \| null`	No	—	URLs pointing to the company page on Twitter, LinkedIn, Facebook
`result.data[].redirect_domain`	`string \| null`	No	—	Last domain in the redirect chain, if any
`result.data[].description`	`string \| null`	No	—	Description, from website metatags or content
`result.data[].keywords`	`record`	No	—	Keywords generated by Natural Language Models based on site content, as keyword:confidence pairs
`result.data[].industry_groups`	`record`	No	—	Top industries (up to 2), as industry:confidence pairs
`result.data[].sub_industry`	`object \| null`	No	—	Sub-industry labels scoped to the company’s industry category, as PARENT/SUB:confidence pairs. null when the domain was not scored against them
`result.data[].employees`	`string \| null`	No	—	Employee count bucket (output only). To filter, use employee_range with ‘min,max’ format (e.g., ‘51,200’)
`result.data[].revenue_range`	`"<1M" \| "1-10M" \| "10-100M" \| "100M-1B" \| ">1B" \| "N/A"`	No	—	Company revenue bucket: 1B, or N/A when unknown Allowed: `<1M`, `1-10M`, `10-100M`, `100M-1B`, `>1B`, `N/A`.
`result.data[].business_model`	`record`	No	—	Business model labels as label:confidence pairs (B2B, B2C, B2G, G2B, G2C, D2C, C2C, C2B)
`result.data[].update_date`	`string \| null`	No	—	Date of last record update (YYYY-MM-DD)
`result.data[].mx_provider`	`string \| null`	No	—	Email/MX hosting provider for the domain: a provider domain (e.g. ‘google.com’, ‘microsoft.com’), the sentinel ‘no_mx’ when the domain publishes a null MX record, or null when no MX record was found
`result.data[].linkup`	`null`	No	—	Deprecated field, always None
`result.data[].similarity`	`number \| null`	No	—	Similarity score 0-100 between output domain and query domains or NL text
`result.data[].vendors`	`array \| null`	No	—	Technology vendors used by company (when tech_stack filter is used)
`result.meta`	`object`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: provider_usage (provider usage).
Estimated Deepline credits: 0.05 per pricing unit.

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation