HG Insights - RGI

Comprehensive company research that aggregates firmographic, technographic, IT spend, cloud spend, intent signals, contracts, and operating signals into a single interactive dashboard. Provide a company domain (e.g., "cisco.com") or an HG Insights company ID (hg_id). All sections default to ON; pass include* booleans (false) to opt out of sections you do not need. Pass full: true to bypass per-section row caps (defaults trim spend/cloudSpend/intent so an unconstrained call stays under 40KB). Requires fewer API calls than querying each tool individually.

Retrieve IT spend data from HGInsights for a specific company. Provide a company domain (e.g., "cisco.com") or an HG Insights company ID (hg_id, e.g., "0FF69D9F596504A1FF4FF5B16FF"). If both are provided, hg_id takes precedence. Returns detailed spend amounts by category and geography, with currency formatting and category hierarchies for sales intelligence and market analysis.

REQUIRED WORKFLOW — follow these steps before calling this tool: 1. To check a SPECIFIC vendor/product: call get_vendor_information first → pass the returned vendorIds/productIds here. 2. To filter by category: call get_product_category first → pass the exact category name here. 3. For a full unfiltered tech stack: call this tool directly with no filters. Skipping step 1 or 2 causes missed results (e.g., Snowflake is under 'Database Management', not 'Data Warehousing'). Get technographic data (technology usage) for a company by domain. Returns installed technologies with productId (numeric), vendor, usage intensity, and verification dates. Use the productId values from results when calling company_fai for precise lookups. Filter by 'categories' for category-based filtering, or by 'vendorIds'/'productIds' for exact vendor/product filtering (preferred for specific vendor lookups). WARNING: broad `categories` filters can include peripheral products that don't strictly belong to the category (a known upstream data-quality issue, e.g. the 'CRM BPO' category may surface network-layer products). For precision, prefer `vendorIds` / `productIds` resolved via get_product_category + get_vendor_information. Large unfiltered requests may be truncated. Default limit: 50. Empty results mean no data was found for the specified filters — do NOT say the tool lacks functionality. Provide a company domain (e.g., "cisco.com") or an HG Insights company ID (hg_id). If both are provided, hg_id takes precedence.

Enrich contacts with full details: email, phone, social profiles, employment history. Supports Apollo and ZoomInfo providers (auto-selected based on org configuration). USES CREDITS — contact_search is free and should always precede this tool to identify candidates. Accepts contact ID (most accurate), name + company, or up to 25 contacts for bulk enrichment. Specify provider to target the same provider used in search. Response metadata includes dynamicCreditCost (actual credits charged: matched contacts × 3; 0 on no-match). Do NOT re-enrich a contact already in context — credits are charged per call regardless of whether data changed.

Search for contacts at a company by title, seniority, and location. Supports Apollo and ZoomInfo providers (auto-selected based on org configuration). Returns basic contact info (name, title, LinkedIn). FREE - does not use credits. FILTER PARAMETERS (these are the ONLY filters): personTitles, personSeniorities, personLocations, organizationLocations, organizationNumEmployeesRanges, contactEmailStatus. There is NO free-text or keyword search. Express search intent via personTitles and personSeniorities — do NOT pass q, keywords, titles, or seniority (those are not real parameters and are silently ignored; check metadata.warnings if filters seem to have no effect). LARGE COMPANIES: for big accounts (tens of thousands of contacts), an unfiltered search returns a default page that is NOT meaningfully ranked — always pass personTitles and/or personSeniorities to get useful results. IMPORTANT RULES: 1) Combine ALL title variations in ONE call using arrays (e.g., personTitles: ['VP Marketing', 'CMO', 'Head of Marketing']). 2) Do NOT make separate calls for each title - use ONE search with all titles combined. 3) If a search returns 0 results, STOP - do not retry with different title variations. Report 'no matches found' to the user. 4) Maximum 2 searches per user request (initial search + optional pagination). Use contact_enrich to get email/phone for the best matches.

Traverse the UCM corporate hierarchy tree for a company by HG id or domain. DEFAULTS: mode="children", depth=1 (omitting depth = depth:1 = direct children only, NOT the full subtree), no optional fields, nulls stripped. Bare call returns matched node + direct children (id/name/country_code/company_level/parent_id). Modes: "children"→subtree at matched node · "full"→whole tree from GHQ (matched=selected:true) · "parents"→ancestor chain. See mode param for company_level values. SIZE: mode:"full"/deep trees on Fortune-500 parents (Microsoft,IBM,Alphabet) = 100–330+ nodes and can OVERFLOW the response — depth is the size lever. This tool does NOT truncate client-side (no truncated/totalNodes fields); YOU control size via depth/mode, so start narrow and escalate. BEWARE: (1) Acquired co + mode:"full" → WHOLE parent family; check company_level, use mode:"children" if not "Group HQ". (2) depth:1 hides holding-company chains; use depth:3-5 for all subsidiaries. (3) depth is applied BEFORE filters — a shallow depth removes deeper nodes before any filter runs, so pair filters with depth:5+. (4) naics_code/industry_name sparse; nulls dropped SILENTLY. (5) mode:"full"+country filter prunes whole GHQ tree; scope with mode:"children". Escalation: depth:5=walk down · mode:"full"=GHQ family · selected_fields=extra fields · all_fields:true=every field · mode:"parents"=ancestors · depth:0,all_fields:true=firmographic snapshot. Recipes: "Who owns X?"→mode:"parents" · "Direct subs"→defaults · "All subs"→depth:5 · "Sister cos"→mode:"parents" then mode:"full" on GHQ · "EU entities"→country_codes:[EU],depth:5 · "Revenue"→depth:0,selected_fields:["revenue_total","employees_total"]. Domain is LITERAL — "alphabet.com"=UK fleet co. Use search_companies for brand intents. Holding domains: Alphabet→"abc.xyz", Meta→"meta.com". Sub-brands resolve to GHQ. Anchor: matched node always retained even if it fails a filter. hierarchy:null=unresolved. No tree aggregation. No time series. Validate junk nodes. Credit: 0.1/node.

Search for product attributes in the HG Insights taxonomy. Free — no credits consumed. Supports substring search by `attributeName` (e.g. 'SaaS', 'Open Source', 'Cloud') or exact resolution of known ids via `attributeIds`. Returns attribute rows including `attribute_id` (Int16), `attribute_name`, `attribute_parent_id` (0 = root), `attribute_level`, and `product_count`. Note: `attribute_description` is null for most attributes — rely on `attribute_name` to identify them. The catalog has ~30 flat attributes (all level-1, no parent hierarchy in the live catalog). Typical workflow: search by `attributeName` to find the id, then pass the id to downstream tools. To browse the catalog, search by a broad `attributeName` (the catalog has ~30 flat attributes) — do NOT enumerate IDs sequentially with this tool. Use this when: you need to find an attribute_id by name before filtering a product search. Do NOT use this when the user wants category or vendor details — use `get_product_category` or `get_vendor_information` instead.

Search for product categories in the HG Insights taxonomy. Free — no credits consumed. Supports substring search by `categoryName` (e.g. 'CRM', 'Security') and/or `treeContains` (scans the full root-to-leaf path), or exact lookup by `categoryCode` or `categoryId`. Returns ranked category rows including `category_id` (Int128 hex), `category_code`, `category_name`, `category_name_tree` (root → leaf path), `has_category_installs`, and `product_count`. Use this when: you need to find a category_id by name before calling `company_technographic` or other tools that require a category_id; or to explore the category taxonomy by keyword. Do NOT use this when the user wants vendor or attribute details — use `get_vendor_information` or `get_product_attribute` instead. Do NOT call without at least one filter (`categoryName`, `treeContains`, `categoryCode`, or `categoryId`). When providing both `categoryId` and `categoryCode`, both must match the same record (AND logic) — if in doubt, provide only `categoryId`. `product_count` reflects direct products only, not subtree rollup. Note: `category_code` is null for many intermediate nodes; prefer `categoryId` for exact lookups.

Get comprehensive information about a software product including overview, pricing, competitors, and integrations from TrustRadius.

Get customer reviews and feedback for a software product with flexible filtering by rating and date.

Search for vendors in the HG Insights taxonomy and retrieve their `vendor_id`s and metadata. Free — no credits consumed. Supports substring search by `vendorName` and/or `description`, or exact lookup by `vendorId`. Returns a ranked list of vendor rows including `vendor_id` (UInt64), `vendor_name`, `vendor_url`, `vendor_parent_id` (null if top-level), `vendor_company_description`, and `product_count`. Set `includeProducts: true` to attach the top `productsLimit` products per vendor. Use this when: you need to find a vendor_id by name before calling `company_technographic`, `company_spend`, or other tools that require a vendor_id. Do NOT use this if you already have a `vendor_id` from a previous response — pass the ID directly to downstream tools. Do NOT use this when the user wants product details or reviews; use `get_product_information` instead. Do NOT use this to find product categories or product attributes; use `get_product_category` or `get_product_attribute` instead. Do NOT use this to list all vendors without a filter — always provide `vendorName`, `description`, or `vendorId`.

Returns the HG Insights data warehouse schema — table names, descriptions, approximate row counts, and column definitions (name, type, description). Call this tool before writing queries with hg_data_query to discover available tables and columns. Pass an optional table_name to filter results to a single table.

Execute read-only SQL SELECT queries against the HG Insights data warehouse. Call the hg_catalog tool first to discover available tables and columns before writing queries. Queries must be SELECT-only (no INSERT, UPDATE, DELETE, DROP, etc.). Returns rows, column names, row count, and credits consumed. Credit cost is dynamic based on the query (reported by the upstream API). PREFER search_companies OVER THIS TOOL for: finding companies by vendor/product/category, counting companies per country/industry/category (use groupBy parameter), filtering by employee count, revenue, or geography. search_companies has built-in groupBy (country, product_id, vendor_name, category, industry), technologyIds for exact product matching, and vendorName for all-products-from-a-vendor queries — all without writing SQL. Use hg_data_query only when search_companies cannot express the query (e.g. multi-table joins, time-series analysis, custom aggregations, or raw warehouse exploration). USE CASES for this tool: TAM analysis with complex joins, competitive displacement (category IN / product NOT IN), install time-series, or any query requiring warehouse tables not exposed by search_companies. WAREHOUSE CONSTRAINTS (queries violating these are rejected upstream, not by this tool): (a) `SELECT *` is rejected — always list explicit column names. (b) Every query must reference at least one allowed warehouse table (call hg_catalog for the list). REAL COLUMN NAMES (from hg_catalog — do NOT invent columns): company_locations (alias cl) has `name` (company name), `country_name`, `country_code`, `employees_min`, `employees_max`, `company_id`, `url_id`. install_global (alias ig) has `product_id`, `product_name`, `vendor_name`, `category_leaf_name`, `url_id` — there is NO category_id column. Join install_global to company_locations with `USING (url_id)`. Anchor TAM analyses on a specific product or vendor — get_vendor_information returns the product IDs in one call, which is enough to compute installed-base, competitive-displacement, and whitespace TAM shapes. Two concrete examples: (1) "How many mid-market North American companies have installed Splunk?" — call get_vendor_information(vendorName: "Splunk") to capture the product IDs, then `SELECT COUNT(DISTINCT cl.company_id) FROM install_global ig JOIN company_locations cl USING (url_id) WHERE ig.product_id IN (<splunk_product_ids>) AND cl.country_name IN ('United States', 'Canada') AND cl.employees_min >= 100 AND cl.employees_max <= 1000`. (2) "Companies running a SIEM that's not Splunk" (competitive displacement) — same first call for the Splunk product IDs, then derive Splunk's categories from install_global itself (get_vendor_information returns product_id/product_name only, NOT category_leaf_name — never guess a category value): `SELECT DISTINCT cl.company_id, cl.name FROM install_global ig JOIN company_locations cl USING (url_id) WHERE ig.category_leaf_name IN (SELECT DISTINCT category_leaf_name FROM install_global WHERE product_id IN (<splunk_product_ids>)) AND ig.product_id NOT IN (<splunk_product_ids>) LIMIT 1000`. The category subquery avoids enumerating every competitor product manually.

Find companies showing intent for a topic, vendor, or product. Returns merged HG proprietary + TrustRadius buyer intent signals with signal strength (0-100), intent levels, buyer journey stages, and context types. Use list_intent_topics to discover available topics first.

List Functional Area Intelligence (FAI) departments and their roles from the official HG Insights catalog. Returns each department's hex ID and name along with its roles (role hex ID and name). Use this to discover and reference real FAI department and role IDs — for example to correlate against the departmentId/roleId fields returned by the company_fai tool. IMPORTANT: always look up department and role IDs with this tool rather than guessing or fabricating them. Optionally filter by department name (case-insensitive partial match) and page with limit/offset.

Search or list intent topics from the official HG Insights catalog. Intent topics represent buying signals and research areas that indicate what technologies companies are actively investigating or planning to purchase. IMPORTANT: Use a single keyword per query (e.g., 'security', 'cloud', 'ERP', 'Salesforce'). Multi-word descriptive phrases (e.g., 'cloud storage solution') return 0 results because the search matches against catalog topic names, not natural language. For broader coverage, run multiple single-word queries with different keywords or declinations (e.g., 'cloud', then 'storage', then 'infrastructure'). IMPORTANT: When recommending intent topics, always use this tool to look up real topic IDs and names — never guess or fabricate them.

Retrieve one Phoenix artifact's content by its id. Pass either a synthetic artifact_id (`{runId}-html`, `{runId}-pdf`, …) or a bare run_id. Returns the deliverable's HTML content (when small enough to inline) plus a descriptor with the artifact type and an absolute webapp URL to open it. If the run has no artifact (queued, failed, unknown, or nonexistent), returns found:false rather than an error.

Get the status and details of a Phoenix agent run. Returns the current status, any generated artifacts, and cost information. If the run is still queued or running, return the status and run ID to the user rather than calling this tool again in a loop; repeated polling within one turn will exhaust the step budget.

Execute a Phoenix AI agent with the specified inputs. Creates an agent run that will be processed asynchronously. Returns the run ID for tracking status and retrieving artifacts. Runs are asynchronous and can take several minutes. After invoking, do NOT repeatedly poll for status — check status at most once or twice; if the run is still queued or running, tell the user the brief is generating and give them the run ID to check later. Only continue polling if the user explicitly asks you to wait.

List all available Phoenix AI agents for this organization. Returns agents that have been published and are ready for invocation. Each agent has specific capabilities defined by its allowed tools and input schema.

List this organization's Phoenix artifacts — the canonical brief (deliverable) each succeeded agent run or upload produced. Returns one row per run with its id, type, source, dates, and an absolute webapp URL to open it. Narrow with artifact_type, source, or a specific run_id, and page with limit/offset. Filters are structured only (no free-text/content search).

Phoenix onboarding / getting-started. When a user wants to get started with Phoenix (e.g. "I'm getting started", "help me get started", "what can Phoenix do"), you MUST ask EXACTLY these two questions and WAIT for the answers before doing anything else. Ask the role question as a NUMBERED choice list (so the user can just reply with a number), then the company question on its own line — formatted exactly: "First, what's your role? Reply with the number: 1. Sales 2. Marketing 3. Customer Success 4. Exec / Strategy 5. Other" and "And what company or product do you represent?". Ask ONLY those two — do NOT ask open-ended questions like "what are you hoping to do with Phoenix", and do NOT present role as a free-text question. Do not skip them, do not improvise, do not guess the answers. After you have BOTH answers, call this tool with `role`, `company`, and the 1–3 `recommended_prompts` slugs you recommend (based on their role and the tools visible in this session). It renders an interactive, branded onboarding widget; clients that cannot render MCP-app widgets get an equivalent text fallback. Exception (faster first run): if the user has not yet given a company, you MAY still call this tool with `role` and your `recommended_prompts` and OMIT `company` — Phoenix will pre-fill the company from the user's signup data when it can (corporate email domains only), and otherwise return a recommendation that asks for the company before running. Prefer this over stalling when a company is not yet available.

Upload an externally-produced PDF or HTML file into Phoenix as an artifact, by providing a publicly-fetchable https URL to the file. The file is hosted in S3 and appears in the Artifacts tab tagged "Uploaded". Only PDF and HTML files up to 25 MB are supported.

Discover and hydrate products from the HG Insights product catalog. Use action='search' to find product_ids by name/vendor/category/attributes (free). Use action='enrich' to hydrate 1-50 product_ids with full catalog details — product_details, category_info, vendor_info (1 credit per successful match). Typical flow: call search to disambiguate, then enrich the chosen product_id(s). Failed enrich ids return per-row NO_MATCH_FOUND errors at HTTP 200 and do not consume credits. When filtering by category, prefer resolving the exact category first via get_product_category and passing category_id — category_name does a substring match that can silently pick the wrong category (e.g. 'CRM' matches the BPO/outsourcing category, not the CRM software one). Same guidance applies to attributes via get_product_attribute (use attribute_ids over attribute_name).

Search for companies by firmographic and technographic criteria — list/filter workflow (e.g. "find US tech companies using Snowflake with 1K–10K employees"). Use this when: - Building a prospect or ICP list (e.g. "find mid-market US SaaS companies using Snowflake"). - Filtering by technology install across many companies — resolve IDs via get_vendor_information first. - Segmenting by geography, employee band, or revenue range combined with a technographic filter. - Discovering which companies in an industry or NAICS code have adopted a specific product. Do NOT use this when: - You already know the company domain or hg_id — call company_firmographic instead (faster, exact match, richer data). - You want a full company profile (intent, spend, technographics) — call company_research instead. - You want a single company's full tech stack — call company_technographic instead (returns one company's installs, not a list). - You have no filters — a zero-param call is rejected with HTTP 422 (server enforces ≥1 filter). - You only have revenue or employee filters — always pair with technology_ids, vendor_ids, category_ids, or countries. GUARDRAIL: countries=["US"] alone matches 500K+ records; revenue_min/max alone matches 100K+. Always combine ≥2 meaningful filters including one of: technology_ids, vendor_ids, category_ids, or countries. ⚠ ENFORCED REQUIREMENT — technology_countries requires is_localized=true. Omitting it (or setting it to false) returns HTTP 422. Always set is_localized=true whenever you use technology_countries. Empty results: (a) domains — exact spelling, no protocol/www; (b) company_name — ILIKE substring, not semantic; (c) bad technology_ids/vendor_ids/category_ids return HTTP 422 — resolve via get_vendor_information first. Response: companies[]{hg_id (→ enrichment tools), domain, company_name, relative_revenue (HG USD est, nullable), relative_employees (HG est), country_code (ISO-2), industry, industry_id}; total_count = total matches (paginate with offset).

Search USAspending.gov for U.S. federal contract awards. Filter by awarding agency, NAICS code, PSC code, keywords, contract value range, date range, and small business set-aside type. Returns contract details including recipient, obligation amount, and performance location. Requires the SAM.gov (Data.gov) integration to be configured.

Search SAM.gov for open U.S. federal solicitations (RFPs, RFQs, presolicitations, sources sought). Filter by keywords, NAICS code, PSC code, agency, set-aside type, posting date, and response deadline. Returns opportunity details including title, agency, deadline, and direct SAM.gov link. Requires the SAM.gov (Data.gov) integration to be configured.

Search and translate industry codes across HG industry (23 buckets), NAICS 2012 (~2,200 codes), and SIC 1987 (~1,500 codes) in a single call. Do NOT use this to find what industry a specific company belongs to — call `company_firmographic` (pass `companyDomain` or `hg_id`) for that. This tool searches taxonomy definitions, not company records. Use cases: (1) free-text lookup — pass `q` with a name fragment ("software publishers"); (2) code translation — pass `q` with a known code ("541511", "7372") for the full crosswalk; (3) numeric prefix — all-digit `q` does prefix match on code columns only (`q=52` returns NAICS sector 52 and its descendants, not codes like 1152); (4) multi-term OR — comma-separated `q` (`q=software,publishing,saas`) unions the matches in one call; (5) grouped listing — pass `taxonomy` (industry|naics|sic) for one row per distinct entity with crosswalk counts (`naics_count`, `sic_count`); add `naics_leaf_only=true` with `taxonomy=naics` to drop 2/3/4/5-digit rollups and keep only the 1,590 6-digit leaf codes. Colloquial sector terms (fintech, saas, ecommerce, healthcare, cybersecurity, cleantech, ev, biotech, gaming, streaming, logistics, adtech, proptech, insurtech, edtech, airline, hospitality, renewable, semiconductor, …) are expanded server-side into the substrings actually present in NAICS/SIC names — the response includes a top-level `alias_expansions` array showing what ran. Zero-result self-heal: when `results` is empty AND `q` is a near-miss against a taxonomy name (trigram similarity), the response includes a top-level `suggestions` array (up to 5 closest taxonomy names). Check it before retrying — handles typos and near-misses. If `results` is empty and `suggestions` is also absent, the term is semantically unrelated to any taxonomy entry — try rephrasing as a broader category (e.g., "restaurants" instead of "pizza"). NAICS hierarchy: each `naics` block exposes `hierarchy_level` (sector|subsector|industry_group|naics_industry|national_industry) and `is_leaf` — only leaf NAICS are safe to chain into downstream code-based filters (rollups will not match a single company's NAICS classification). `display_name_with_level` disambiguates same-named adjacent levels (e.g. "Commercial Banking (subsector 5221)" vs "(national_industry 522110)"). Unscoped mode returns the raw crosswalk — the same NAICS may appear on multiple rows, one per SIC partner. For most use-cases, prefer `taxonomy=naics` or `taxonomy=sic` to get one de-duplicated row per code. Only use unscoped mode when you need the full NAICS↔SIC mapping table. Downstream chaining: when passing a SIC code to other tools (e.g. search_companies), always use `sic.sic_standard_code` (e.g. "7372"), NOT `sic.sic_code` (e.g. "I7372" — the HG-extended form carries an internal letter prefix and won't match). To filter companies by industry, pass returned `industry_id` integer values to `search_companies` (the `industry_ids` parameter takes integer IDs — resolve them here first). Scope: taxonomy crosswalks only — no revenue, headcount, company counts, or other firmographic data. For company filtering by size/location/revenue, use `search_companies` or `company_firmographic`. HG bucket quirks worth knowing: there is no Software/Information HG bucket. `Software Publishers` (NAICS 511210 / SIC 7372) rolls up to `Computer and Electronic Product Manufacturing`; `Custom Computer Programming` (541511) and `Data Processing` (518210) live under `Professional, Scientific and Technical Services`. For fine-grained software/tech filters, prefer NAICS or SIC over the HG industry bucket. Paging: `pagination.offset_exceeds_total` is true when you paged past the end (empty results with `has_more=false` would otherwise be ambiguous). Max `limit` is 500. Free — no credits consumed.

Extract the full text of a named section from a specific company's SEC 10-K (annual), 10-Q (quarterly), or 8-K (current event) filing. Use this when a user asks about the content of a named filing section (e.g., "What are Microsoft's risk factors?", "Show me Apple's MD&A", "Get AAPL's latest earnings 8-K"). Section codes and topic-to-code mapping are in the "section" parameter. SCOPE: US domestic issuers only (10-K / 10-Q / 8-K). For foreign issuers that file 20-F, 6-K, or 40-F (e.g., Barclays, BP, SAP, Toyota), use sec_full_text_search with filingTypes: ["20-F"] or ["6-K"]. Do NOT call for general company background (revenue, headcount, products) — use company_research instead. FISCAL FILTERING: fiscalYear narrows by calendar year. Quarter-precise filtering is NOT supported — use dateFrom/dateTo instead. Returns the single most recent matching filing; for recurring 8-K events (e.g., 2.02 earnings), use dateFrom/dateTo to target a specific window. PROXY STUBS: For most large-cap companies, 10-K sections 10–14 (Directors, Compensation, Security Ownership, Related Party, Accountant Fees) are incorporated by reference from the DEF 14A Proxy Statement and return a short stub (under 50 words). If content is under 100 words and mentions a Proxy Statement, the full data is not available via this tool. 8-K EXHIBIT NOTE: Items like 2.02 (earnings) often contain only a stub referencing Exhibit 99.1. The exhibit text is not returned. For full earnings narrative, use sec_full_text_search. Do not call if the filing section content is already present in the conversation.

Search within SEC filing content for specific terms or phrases. Thin wrapper around the sec-api.io full-text-search API. Accepts ticker symbols and resolves them to CIKs automatically. Supports AND, OR, NOT, wildcards (*), and exact phrases ("quoted"). DO NOT USE to extract a named section ("risk factors", "MD&A") from a specific filing — use sec_filing_section (that tool calls this concept filingType, a singular enum, not formTypes). For general company background (revenue, employees, technographics) use company_research; for non-SEC web info use web_search. CORPUS: Covers incident-reporting and event-driven filings. Common financial terms ("revenue", "earnings") are not indexed and return zero results. DATE WARNING: startDate defaults to the last 30 days. Annual filings (10-K, 20-F, 40-F) are filed yearly — pass startDate "2020-01-01" for them or you get zero results. QUERY EXAMPLES: "material weakness" · cybersecurity AND breach · layoff* · "going concern" OR "substantial doubt" · acquisition NOT merger. USE CASES: Risk: "material weakness", "going concern" · Cyber: "cybersecurity incident" · M&A: acquisition, merger · Foreign issuers: formTypes ["20-F"] (Barclays/BP/Toyota/Shell), ["6-K"] (interim), ["40-F"] (Canadian) — some ADR issuers (e.g. SAP) have no 20-F on EDGAR. Returns up to 100 filings per page with direct EDGAR URLs. If resolvedCiks in searchParams is empty after passing tickers, the ticker filter was NOT applied and results are unfiltered — check it (and any warnings) before treating results as company-specific.

Search the web for current information, news, and research. Returns relevant results with summaries and URLs. Useful for getting up-to-date information on any topic. Cost: 0.01 credits (basic) or 0.02 credits (advanced extraction). Set includeRawContent=true to get full cleaned page content (free, slightly higher latency).