Search warm intro relationships
search_warm_intro_relationshipsSearch warm intro relationship paths across the workspace using rich filters on accounts, contacts, super connectors, and relationship quality. Returns fully resolved results with contact, super connector, account, relationship evidence, and intro request context per path. IMPORTANT — rendering: do NOT dump raw JSON or long prose in chat. Render results in a tabular UI artifact (React/HTML table) — one row per relationship path. Include as many columns as the data provides: Contact (full_name, title, seniority, company_name, email), Super Connector (full_name, title, email), Account (account_name, domain, industry, owner_full_name, employee_size), Relationship (strength, category, confidence, intro_value, score, summary, relationship_path_types, number_of_meetings, last_contacted_at), Intro Request (current_state, requester_full_name, is_recommended_connector, connector_request_status when has_intro_request). Hide internal UUIDs unless the user asks. Include pagination when page_info indicates more pages.
Use when: Use for workspace-wide warm intro discovery when you need to combine multiple filters — e.g. VP contacts at accounts owned by a rep, CONFIRMED paths via a specific connector, or contacts at a specific domain. After results return, render the table UI in the same turn — do not summarize paths as paragraphs. CATEGORY TRIGGER WORDS — if the user's request contains any of: investor(s), customer(s), board member(s), advisor(s), champion(s), alumni, leadership, partner(s) — treat this as a FILTER_FIELD_CATEGORY request, NOT a seniority or strength filter. These words describe who the connector is in relation to the company, not how senior the contact is or how strong the tie is. NEVER substitute FILTER_FIELD_SENIORITY or FILTER_FIELD_STRENGTH as a proxy for a category-based request. Required flow for any category-based request: (1) call get_workspace_categories FIRST, (2) filter response to relationship_type SUPER_CONNECTORS and is_deleted false, (3) match the user's term to the closest category label(s) — include all plausible matches as OR'd values (e.g. both 'Investor' and 'Investors' if both exist), (4) pass those category id UUIDs as FILTER_FIELD_CATEGORY values. Never pass label strings directly as FILTER_FIELD_CATEGORY values. Mixed requests (e.g. 'senior leaders who investors know'): apply FILTER_FIELD_CATEGORY AND FILTER_FIELD_SENIORITY together in the same call. When filtering by super connector, prefer FILTER_FIELD_CONNECTOR_ID (exact UUID match) over FILTER_FIELD_SUPER_CONNECTOR_NAME whenever the connector user_id is known — name prefix matching requires a single first or last name token and silently returns zero results for full names like "Steven Hagler". When the user supplies Salesforce/HubSpot account IDs, pass them straight to FILTER_FIELD_ACCOUNT_REFERENCE_ID — do not call search_accounts_with_filters to map them to UUIDs first.
Behavior: read_only
workspace_id / user_id are injected from request headers.
Returns results[] with fields:
source: Originating party of the path. source.user is set for User→Contact and User→Account paths; source.company is set for Account→Account paths; source.contact is set for Contact→Account (COMPANY_ALUMNI) paths. target: Intended intro recipient. target.contact is set for User→Contact paths; target.account is set for User→Account and Account→Account paths; both are set for COMPANY_ALUMNI paths. relationship: Relationship quality and evidence — strength, category, confidence, intro_value, score, summary, number_of_meetings, last_contacted_at, is_approved, connected_on_date. relationship_path_types is a list of {type, description} objects — use type values to determine which source/target sub-fields are populated. intro_request: Intro request context — show when has_intro_request is true: current_state, requester_full_name, created_at, is_time_sensitive, is_recommended_connector, connector_request_status. Show '—' when absent. Also returns pagination info (total_pages, current_page_number, page_size, total_count).
IMPORTANT: If the response contains more than one record, always present the options to the user and ask them to choose before taking any follow-up action. Do not act on all results automatically.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | ||
| search | No | ||
| filters | No | Optional active filters to scope the returned option values — e.g. if a location filter is active, seniority options will only include values present for that location. | |
| page_size | No | ||
| page_number | No | ||
| _triggered_by | No | REQUIRED. Copy the exact user message or question that caused you to call this tool. Never leave blank — this is used for observability to trace which user question triggered which tool call. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||