find_similar_patents
ChatGPTFind patents that disclose similar subject matter to a given patent. Supply a publication, application or grant number of a published patent. For example, values like 'US20160266243A1', 'EP4016123B1', and 'US14/643,719' are all accepted. This tool will then return a list of patents, grouped by patent familiy, that deal with similar subject matter to the given patent. Results are ordered from most to least relevant. Each result contains its patent number, title, abstract and url, a link to that patent's page in the Clerq app. Wherever a patent number appears in your reply, make it a link to its url. Use the patent lookup tool separately if more fields are needed. Optional filters narrow which patents can match. They do not replace the patent number: keep the source document in patent_number, and use filters for metadata such as dates, offices, classifications, parties, legal status, or document numbers. Values within one list are alternatives. Different filter fields all have to match. On a party, not true excludes that name and not false includes it. A *_date_to value is exclusive and must be after the matching *_date_from. Only this tool and natural_language_patent_search count toward the search limit: together they allow each user 30 searches per rolling hour. Other Clerq tools are not limited this way. Once the limit is reached the tool fails and says how long to wait. Args: patent_number: A patent identifier that can be either a patent publication, application, or grant number. max_results: Number of similar patent families to return, from 1 to 25. filters: Optional metadata limits. Omit them to search the whole index. Returns: The requested number of similar patent families, most similar first. Raises: ToolError: If the number is invalid, cannot be resolved, the filters are unusable, or the search fails.
get_patentability_triage
ChatGPTRead progress and selected results from a patentability triage workflow. With no sections this returns only compact workflow and step status. Request features, prior_art, or analyses only when that material is needed. The prior-art list is capped by max_results; detailed analyses are returned only for the supplied patent document numbers. A requested section not yet produced appears in unavailable_sections rather than as invented or stale data. Treat next_action as authoritative: poll only for poll, wait until next_poll_at, and stop for use_results, ask_user, stop_failed, or stop_stalled. The API owns the clock and rate-limits rapid polling, so the language model must not estimate elapsed time. A terminal section state of failed or not_produced will not become available through further polling. A patent in prior_art has a url, its page in the Clerq app; link its number to it when presenting it. Args: workflow_id: Identifier returned by start_patentability_triage. sections: Optional result sections to load in addition to status. max_results: Maximum entries per bounded result list, from 1 through 20. analysis_document_numbers: Up to 10 selected patents whose reasoning is needed. Returns: Current progress and only the selected result sections currently available. Raises: ToolError: If the input is invalid, the workflow is unavailable, or reading fails.
get_patents
ChatGPTRetrieve selected data for up to 25 patents. Supply a list of up to 25 patent identifiers. Identifiers can be patent publication, application, or grant numbers. For example, values like 'US20160266243A1', 'EP4016123B1', and 'US14/643,719' are all accepted. Select only the fields needed for the user's current task. Claims and description sections contain full text and can be very large, so request them only when their text will be used. Citation fields contain compact citation identifiers and phases rather than nested patent records. Common choices are title and abstract for a summary, claims for claim analysis, dates and legal_status for status questions, parties for ownership questions, and citations or classifications for prior-art investigation. Args: identifiers: One to 25 publication, application or grant identifiers, including a jurisdiction where applicable. Duplicates are ignored. fields: One or more fields needed for the current task. Returns: Ordered resolved patents with their canonical document numbers, requested data and url, plus identifiers that could not be resolved. When presenting a patent number, link it to its url. Raises: ToolError: If the input is invalid or the API call fails.
get_report
ChatGPTRead a completed patentability report. Without document_number this returns the overview (mode is overview): the elements the run analysed, each with an element_ref, its claim number and text. The elements of a patentability or triage report are invention features, not claims. With document_number it returns that recorded document's findings (mode is document): novelty, risk and gaps fields under document, and each analysed element's disclosure status (fully disclosed, partially disclosed or not disclosed) with its evidence chunks and the label the report shows for it. Use label to name an element to the user. document.analysis_status is analyzed when the document was assessed. A skipped_* or failed_* status, or not_analyzed, means the elements were not assessed against that document; that is missing evidence, not a negative finding. Use element_ref values returned here to filter one element; element_id is provenance only. A patent document has a url, its page in the Clerq app; link the document number to it when presenting it. Results are paged. When pagination.more is true, call again with the next page, and state partial coverage until then. Args: workflow_id: Report workflow. run_id: Completed run of that workflow. document_number: A document from list_report_prior_art. element_ref: One element to return; requires document_number. page: Page to return, from 1. page_size: Results per page; omit for the server's default. Returns: The overview or one document's findings, with a pagination envelope. Raises: ToolError: If the input is invalid or the report cannot be read.
list_report_prior_art
ChatGPTList the prior art a completed patentability report displays. Documents are in report order, each with its rank, its recorded novelty, risk and gaps fields and stored title. Start summaries from these fields, then read a document's element findings with get_report. A missing title, or an analysis_status other than analyzed, means the report holds no such data; say so rather than inferring it. Use get_patents for patent details the report does not store. A patent has a url, its page in the Clerq app; link the document number to it when presenting it. Non-patent documents have none. Results are paged. When pagination.more is true, call again with the next page. Args: workflow_id: Report workflow. run_id: Completed run of that workflow. page: Page to return, from 1. page_size: Documents per page; omit for the server's default. Returns: One page of recorded prior art with a pagination envelope. Raises: ToolError: If the input is invalid or the report cannot be read.
natural_language_patent_search
ChatGPTFind patents that disclose subject matter similar to a given natural language description. Given a natural language description of an invention, problem or technical approach — a sentence or a few paragraphs no longer than 512 tokens — this tool returns a ranked list of patents families that deal with similar subject matter. The match is semantic, not keyword-based or lexicographic. Boolean operators, quoted phrases, wildcards and field prefixes are not interpreted and only dilute the query, so describe the subject matter rather than constructing a boolean keyword search string. Longer, more detailed descriptions perform better than short keyword-like ones. Results are grouped by patent family, so each entry is one invention rather than one publication. Each result includes its patent number, title, abstract and url, a link to that patent's page in the Clerq app. Wherever a patent number appears in your reply, make it a link to its url. Use the patent lookup tool separately if more fields are needed. Optional filters narrow which patents can match. They do not replace the semantic query: keep the subject matter in query, and use filters for metadata such as dates, patent offices, CPC/IPC classifications, parties, legal status, or document numbers. Values within one list are alternatives. Different filter fields all have to match. On a party, not true excludes that name and not false includes it. A *_date_to value is exclusive and must be after the matching *_date_from. Only this tool and find_similar_patents count toward the search limit: together they allow each user 30 searches per rolling hour. Other Clerq tools are not limited this way. Make each search count: describe the subject matter fully in one query rather than trying many small variations. Once the limit is reached the tool fails and says how long to wait. Args: query: The subject matter to search for, described in natural language up to 512 tokens in length. max_results: Number of patent families to return, from 1 to 25. filters: Optional metadata limits. Omit them to search the whole index. Returns: The requested number of patent families, most similar first. Raises: ToolError: If the query is unusable, or the API did not answer with results.
start_patentability_triage
ChatGPTStart an automated patentability triage for an invention disclosure. This is a billable operation that consumes the account's configured triage credit charge. It creates a durable Clerq workflow and returns immediately; claim/feature generation, patent searching and result analysis continue asynchronously and may take several minutes or longer. After a successful start, do not call get_patentability_triage in the same model turn. Tell the user that the workflow is running, provide its workflow ID, and return control to them. A later turn can check progress and retrieve only the result sections needed, but never before the returned next_poll_at and only when next_action is poll. This version accepts disclosure text, not file uploads. Known prior art is optional and is normalized by Clerq before the workflow starts. Args: title: Short name by which the user can recognize this workflow. invention_disclosure: Technical description or feature list to assess. priority_date: Optional earliest relevant date, in ISO YYYY-MM-DD form. known_prior_art_patents: Up to 20 patent identifiers already known to the user. Returns: The workflow and run identifiers needed to inspect asynchronous progress. Raises: ToolError: If the input is invalid, credits are unavailable, or kickoff fails.
