batch_get_patents
ChatGPTGet content of multiple patents at once. More efficient than calling get_patent repeatedly. Use 'sections' to request only the parts needed. Available sections: abstract, claims, description, dates, parties, classifications, legal_status, citations, family. Use 'all' for everything. Choose sections based on user intent: - Patent overview → abstract,dates (default) - Detailed comparison → abstract,claims,description - Inventor/assignee comparison → parties - Legal/expiry status → legal_status,dates - Related patents → citations,family - Everything → all Always returns: publication_number, url, title (regardless of sections). Cost: 1 credit per patent.
batch_get_patents
ChatGPTGet content of multiple patents at once. More efficient than calling get_patent repeatedly. Use 'sections' to request only the parts needed. Available sections: abstract, claims, description, dates, parties, classifications, legal_status, citations, family. Use 'all' for everything. Choose sections based on user intent: - Patent overview → abstract,dates (default) - Detailed comparison → abstract,claims,description - Inventor/assignee comparison → parties - Legal/expiry status → legal_status,dates - Related patents → citations,family - Everything → all Always returns: publication_number, url, title (regardless of sections). Cost: 1 credit per patent.
generate_novelty_report
ChatGPTGenerate a novelty/patentability assessment for an invention idea. Submits async report. NOT for: simple patent search (use semantic_patent_search). Cost: 720 credits. Ask user to confirm before running. Async: returns report_id immediately. Poll with get_report_status. 5-15 minutes typical. IMPORTANT: The report is AI-assisted and is NOT legal advice. Always inform the user that results should be reviewed by a qualified patent attorney.
generate_novelty_report
ChatGPTGenerate a novelty/patentability assessment for an invention idea. Submits async report. NOT for: simple patent search (use semantic_patent_search). Cost: 720 credits. Ask user to confirm before running. Async: returns report_id immediately. Poll with get_report_status. 5-15 minutes typical. IMPORTANT: The report is AI-assisted and is NOT legal advice. Always inform the user that results should be reviewed by a qualified patent attorney.
get_patent
ChatGPTGet content of a specific patent by publication number. Use 'sections' to request only the parts needed. Available sections: abstract, claims, description, dates, parties, classifications, legal_status, citations, family. Use 'all' for everything. Choose sections based on user intent: - Patent overview → abstract,dates (default) - Detailed technical analysis → abstract,claims,description - Who invented/owns it → parties - Legal/expiry status → legal_status,dates - Related patents → citations,family - Everything → all NOT for: topic search (use semantic_patent_search), multiple patents (use batch_get_patents). Always returns: publication_number, url, title (regardless of sections). Cost: 1 credit per patent.
get_patent
ChatGPTGet content of a specific patent by publication number. Use 'sections' to request only the parts needed. Available sections: abstract, claims, description, dates, parties, classifications, legal_status, citations, family. Use 'all' for everything. Choose sections based on user intent: - Patent overview → abstract,dates (default) - Detailed technical analysis → abstract,claims,description - Who invented/owns it → parties - Legal/expiry status → legal_status,dates - Related patents → citations,family - Everything → all NOT for: topic search (use semantic_patent_search), multiple patents (use batch_get_patents). Always returns: publication_number, url, title (regardless of sections). Cost: 1 credit per patent.
get_report_patent_analysis
ChatGPTGet detailed analysis for specific patents from a completed novelty report. Pass patent publication numbers from the patent_directory in get_report_summary. Returns the full analysis for each patent including relevance explanation, novelty features, blocking potential, and key differences. Max 10 patents per call. Pass as a list of publication number strings. Only works when report status is 'completed'. Use get_report_status to check first. This tool call is free — it does not consume any credits.
get_report_patent_analysis
ChatGPTGet detailed analysis for specific patents from a completed novelty report. Pass patent publication numbers from the patent_directory in get_report_summary. Returns the full analysis for each patent including relevance explanation, novelty features, blocking potential, and key differences. Max 10 patents per call. Pass as a list of publication number strings. Only works when report status is 'completed'. Use get_report_status to check first. This tool call is free — it does not consume any credits.
get_report_status
ChatGPTCheck the current status and progress of a novelty report. Pass the report_id from generate_novelty_report. Returns status and progress details only — use get_report_summary for the full assessment once status is 'completed'. Polling guidance: wait 30s if pending/searching/analyzing_query/analyzing_final, wait 60s if analyzing_patents. This tool call is free — it does not consume any credits.
get_report_status
ChatGPTCheck the current status and progress of a novelty report. Pass the report_id from generate_novelty_report. Returns status and progress details only — use get_report_summary for the full assessment once status is 'completed'. Polling guidance: wait 30s if pending/searching/analyzing_query/analyzing_final, wait 60s if analyzing_patents. This tool call is free — it does not consume any credits.
get_report_summary
ChatGPTGet the executive summary and patent directory of a completed novelty report. Returns the full patentability assessment (verdict, threats, recommendations) plus a lightweight directory of all analyzed patents (title, relevance score). Use get_report_patent_analysis to dig into specific patents from the directory. Only works when report status is 'completed'. Use get_report_status to check first. This tool call is free — it does not consume any credits. IMPORTANT: The report is AI-assisted and is NOT legal advice. Always show the disclaimer field to the user.
get_report_summary
ChatGPTGet the executive summary and patent directory of a completed novelty report. Returns the full patentability assessment (verdict, threats, recommendations) plus a lightweight directory of all analyzed patents (title, relevance score). Use get_report_patent_analysis to dig into specific patents from the directory. Only works when report status is 'completed'. Use get_report_status to check first. This tool call is free — it does not consume any credits. IMPORTANT: The report is AI-assisted and is NOT legal advice. Always show the disclaimer field to the user.
get_search_status
ChatGPTCheck status of a search or prior art analysis. Returns results if completed. Pass the search_id from semantic_patent_search or prior_art_search. If status is in_progress, wait 30s and retry. Results include publication_number, title, relevance score, and URL. This tool call is free — it does not consume any credits.
get_search_status
ChatGPTCheck status of a search or prior art analysis. Returns results if completed. Pass the search_id from semantic_patent_search or prior_art_search. If status is in_progress, wait 30s and retry. Results include publication_number, title, relevance score, and URL. This tool call is free — it does not consume any credits.
get_usage
ChatGPTCheck remaining GoVeda patent credit balance and billing period details. This tool call is free — it does not consume any credits.
get_usage
ChatGPTCheck remaining GoVeda patent credit balance and billing period details. This tool call is free — it does not consume any credits.
lookup_classifications
ChatGPTLook up CPC/IPC patent classification codes by keyword or technology description. USE FOR: finding the correct CPC/IPC codes to use as filters in semantic_patent_search or prior_art_search. NOT FOR: searching patents directly (use semantic_patent_search). Uses the classification DB's default search (exact-symbol boost + semantic vector search in parallel). Results are ranked by relevance; score and match_type are surfaced so the agent can reason about match confidence. Supports both precise code lookups (e.g., 'H01L') and natural language descriptions (e.g., 'semiconductor chip packaging'). This tool call is free — it does not consume any credits.
lookup_classifications
ChatGPTLook up CPC/IPC patent classification codes by keyword or technology description. USE FOR: finding the correct CPC/IPC codes to use as filters in semantic_patent_search or prior_art_search. NOT FOR: searching patents directly (use semantic_patent_search). Uses the classification DB's default search (exact-symbol boost + semantic vector search in parallel). Results are ranked by relevance; score and match_type are surfaced so the agent can reason about match confidence. Supports both precise code lookups (e.g., 'H01L') and natural language descriptions (e.g., 'semiconductor chip packaging'). This tool call is free — it does not consume any credits.
lookup_party
ChatGPTLook up standardized assignee (company) names for use as exact-match values in the assignees filter of search_conditions. USE FOR: resolving a free-text company name (e.g., 'Qualcomm') into the canonical name(s) actually stored on patent records, before passing them to semantic_patent_search or prior_art_search via search_conditions. NOT FOR: looking up inventor names — assignee/company names only. WHY THIS IS REQUIRED: the assignees filter is an exact-string match. Variants like 'Qualcomm', 'Qualcomm Inc.', 'QUALCOMM INCORPORATED' refer to the same entity but only one form is stored. Always look up first. Hierarchy expansion (expand_hierarchy=true): resolves the ultimate corporate owner and returns all subsidiary names in all_names. Pass the full all_names list as the value of an assignees filter to cover an entire corporate group. Hierarchy is only available for entities in the curated dictionary (mostly Russell 3000 / S&P 500 / Nikkei 225 / DAX 40 corporations). Input: free-text company name in any language. Use the full official name — common abbreviations may not match. This tool call is free — it does not consume any credits.
lookup_party
ChatGPTLook up standardized assignee (company) names for use as exact-match values in the assignees filter of search_conditions. USE FOR: resolving a free-text company name (e.g., 'Qualcomm') into the canonical name(s) actually stored on patent records, before passing them to semantic_patent_search or prior_art_search via search_conditions. NOT FOR: looking up inventor names — assignee/company names only. WHY THIS IS REQUIRED: the assignees filter is an exact-string match. Variants like 'Qualcomm', 'Qualcomm Inc.', 'QUALCOMM INCORPORATED' refer to the same entity but only one form is stored. Always look up first. Hierarchy expansion (expand_hierarchy=true): resolves the ultimate corporate owner and returns all subsidiary names in all_names. Pass the full all_names list as the value of an assignees filter to cover an entire corporate group. Hierarchy is only available for entities in the curated dictionary (mostly Russell 3000 / S&P 500 / Nikkei 225 / DAX 40 corporations). Input: free-text company name in any language. Use the full official name — common abbreviations may not match. This tool call is free — it does not consume any credits.
prior_art_search
ChatGPTFind prior art for a specific patent. Analyzes the patent's content and finds similar earlier patents. USE FOR: finding patents similar to a KNOWN patent (you have the publication number). NOT FOR: searching by topic or description (use semantic_patent_search). Accepts non-standard patent number formats — auto-resolves to standard UCID. Optional filters via search_conditions: dates, country, language, assignees (company), classifications, patent status. Supports AND/OR logic. Use lookup_classifications to find correct CPC/IPC codes before filtering. Use lookup_party to resolve a free-text company name to its standardized form before using the assignees filter (exact-string match). Cost: ~690 credits (50 results), scales with limit. Ask user to confirm before running. Async: returns search_id immediately. Poll with get_search_status. 3-5 minutes typical.
prior_art_search
ChatGPTFind prior art for a specific patent. Analyzes the patent's content and finds similar earlier patents. USE FOR: finding patents similar to a KNOWN patent (you have the publication number). NOT FOR: searching by topic or description (use semantic_patent_search). Accepts non-standard patent number formats — auto-resolves to standard UCID. Optional filters via search_conditions: dates, country, language, assignees (company), classifications, patent status. Supports AND/OR logic. Use lookup_classifications to find correct CPC/IPC codes before filtering. Use lookup_party to resolve a free-text company name to its standardized form before using the assignees filter (exact-string match). Cost: ~690 credits (50 results), scales with limit. Ask user to confirm before running. Async: returns search_id immediately. Poll with get_search_status. 3-5 minutes typical.
semantic_patent_search
ChatGPTSearch patents by technology description or invention concept. Semantic search across 220M+ global patents, returns ranked results. USE FOR: finding patents about a topic, technology, or invention concept. NOT FOR: finding prior art of a known patent (use prior_art_search), fetching a specific patent by number (use get_patent). Optional filters via search_conditions: dates, country, language, assignees (company), classifications, patent status. Supports AND/OR logic. Use lookup_classifications to find correct CPC/IPC codes before filtering. Use lookup_party to resolve a free-text company name to its standardized form before using the assignees filter (exact-string match). Cost: ~50 credits (10 results), ~80 (20), ~320 (100). Scales with limit. Polls internally until results are ready (5-15s typical, 180s max).
semantic_patent_search
ChatGPTSearch patents by technology description or invention concept. Semantic search across 220M+ global patents, returns ranked results. USE FOR: finding patents about a topic, technology, or invention concept. NOT FOR: finding prior art of a known patent (use prior_art_search), fetching a specific patent by number (use get_patent). Optional filters via search_conditions: dates, country, language, assignees (company), classifications, patent status. Supports AND/OR logic. Use lookup_classifications to find correct CPC/IPC codes before filtering. Use lookup_party to resolve a free-text company name to its standardized form before using the assignees filter (exact-string match). Cost: ~50 credits (10 results), ~80 (20), ~320 (100). Scales with limit. Polls internally until results are ready (5-15s typical, 180s max).
start_free_trial
ChatGPTActivate a 14-day free trial with 10,000 credits. Call this when prompted after a tool returns FREE_TRIAL_AVAILABLE. Only available for new users who haven't used a free trial before. This tool call is free — it does not consume any credits.
start_free_trial
ChatGPTActivate a 14-day free trial with 10,000 credits. Call this when prompted after a tool returns FREE_TRIAL_AVAILABLE. Only available for new users who haven't used a free trial before. This tool call is free — it does not consume any credits.
