> ## Documentation Index > Fetch the complete documentation index at: https://deepline.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Use DiscoLike in Deepline > Use discover or count for ICP expansion, bizdata for firmographic lookup, match when you start from a company name, and relationship datasets for vendors. [Human guide: work with your agent →](https://deepline.com/docs/human/providers/discolike/guide.md) Inspect one DiscoLike action before starting provider-backed work. Your first result is a verified input and output contract. ## Provider-specific requirements Use DiscoLike for website-first company discovery and domain intelligence. ### Best entry points 1. Use `discolike_count` to estimate volume before retrieving a large result set. Supported filters include phrase, category, geography, technology, and business model. 2. `discolike_discover` when you have seed domains or a natural-language ICP. 3. `discolike_bizdata` when you already know the domain and need a firmographic profile. 4. `discolike_match` when you start from a company name and need the best matching domain. 5. `discolike_search_indexed_contacts` when you want indexed contacts from DiscoLike's contact dataset at known company domains or matching contact/company filters. 6. `discolike_generate_candidate_contacts` when you want ContaGen-style open-web research to generate candidate contacts at known company domains using DiscoLike-configured BYOK model and search-provider integrations. 7. `discolike_run_company_research` when you want Claygent-style arbitrary company research: run one prompt per domain against company context and optional web search. 8. `discolike_vendors`, `discolike_publiclink`, `discolike_subsidiaries`, and `discolike_redirects` for relationship mapping. ### Segment behavior `discolike_segment` submits an asynchronous provider job and polls its status. The Deepline action returns completed segment rows when available. Callers do not poll the provider job separately. If the sync wait times out, call `discolike_get_segment_status` with the returned `task_id` to retrieve the provider result later. This is a free read-only job-ID action for tasks created by the same organization. Billing separately tracks accepted provider work until terminal usage is known. no result cache resumes the task. ### Contact generation behavior `discolike_search_indexed_contacts` searches DiscoLike's indexed contact/persona data. To leave specific people out, pass `exclude_persona_ids` (up to 1,000 DiscoLike `persona_id` values, for example from earlier calls to this tool when paging through a market). DiscoLike exclusion lists accept only persona IDs and domains, so LinkedIn URLs, emails, or names cannot be excluded. Deepline creates a temporary exclusion list for that one search and deletes it afterwards. callers never manage lists. If DiscoLike does not confirm the deletion, the call fails as retryable and is not charged. `discolike_generate_candidate_contacts` is the ContaGen path: it submits `POST /contacts/discover/generate`, then polls DiscoGen status until terminal results are available or the caller's wait budget expires. Use it only when candidate open-web contact discovery is acceptable. Treat generated `email`, `linkedin_url`, phone, and identity fields as candidates until validated. `discolike_run_company_research` is the Claygent-like path: it submits `POST /discogen/process`, runs an arbitrary prompt against each company domain, and polls DiscoGen status for final results. DiscoGen/ContaGen are BYOK from DiscoLike's perspective: they use the DiscoLike-configured LLM and search-provider integrations and may return a provider-side `estimated_cost` for model/search usage. For Deepline-managed DiscoLike execution, those configured model/search integrations are Deepline-managed upstream costs, so returned `estimated_cost` is reflected in Deepline billing. If the caller omits `integration_id`, Deepline uses the cheapest verified managed LLM config, OpenAI `gpt-5-nano`. if the caller omits `search_context_size`, Deepline uses `low`. Caller-selected model/search overrides, high search context, and `web_search: true` are blocked on the managed shared-key path. Website/profile context modes cost more than domain mode because they add company-context usage on top of the task launch. ### Pricing caveat DiscoLike usage is billed per query plus per net-new record retrieved. Records cached within the provider account for 90 days are free on repeat retrieval upstream, but Deepline uses stable customer-facing modeled pricing regardless. Deepline credit pricing for these actions is generated from the provider pricing metadata and rendered on the public provider pages. ## Find an applicable action Confirm your effective workspace, then search the live catalog: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline auth status --json deepline search "DiscoLike" --type tools --json ``` Search returns candidates. Check the returned provider and operation rather than selecting a similar title automatically. ## Inspect the selected contract Replace `` with the identifier returned by discovery: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline describe --json ``` These commands do not execute the selected provider action. Read its required inputs, supported access mode, pricing unit, outputs, and limits. A connection does not establish that every action supports BYOK. Follow the provider-specific requirements above and the live action contract. ## Prepare one reviewed input Use one authorized record that matches the inspected schema. Preserve its source identity and define the result you will accept. Open the action reference for its payload and response shape. Provider-backed execution can incur usage or external effects. For reusable logic, follow [Write Plays](https://deepline.com/docs/sdk-v2/plays.md). For direct-call recovery, use [Tool execution recovery](https://deepline.com/docs/sdk-v2/tool-execution-recovery.md). > [!TIP] > > Continue only when the workspace, provider, required fields, acceptance rule, and applicable price are understood. Keep unavailable access separate from no-result evidence. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.