IP Author

Head-to-head comparison of 2 US examiners: grant rate, statute rejection mix, art unit, average prosecution length, allowance after interview. Both name_a and name_b are required.

examiner_compare

Search IP Author's complete US Office-Action rejection corpus (~25M rejection paragraphs). Returns highlighted rejection excerpts plus Office-Action metadata such as mail date, examiner, application number, and rejection statute. `legal_reasoning_type_prefix` is the categorical search field. Rejections are organized into approximately 19 legal reasoning categories. For questions about Alice, KSR, anticipation, indefiniteness, or similar doctrines, use the category prefix. This covers category variants even when the rejection does not name the leading case and returns a structured `rejection_summary`. Available legal_reasoning_type_prefix values: - 101_Alice → all 3 Alice variants (mental_process, organizing_human_activity, mathematical_concept) - 101_Alice_mental_process | 101_Alice_organizing_human_activity | 101_Alice_mathematical_concept (more specific) - 102_anticipation → explicit + inherency - 103_TSM_combination | 103_KSR (5 KSR variants) - 112_indefiniteness | 112_written_description | 112_lack_of_enablement | 112_means_plus_function - double_patenting_obvious | double_patenting_statutory - restriction_requirement `q` supports specific named references (Fitzmaurice, Bilski) or phrases not captured by the available categories. Reading the response: - data.matches: result list. Each match has legal_reasoning_type (legal category), statute, rejection_summary (curated summary), and snippet (highlighted excerpt when q is supplied). - meta.total_match_count: corpus-wide count before the limit. When it is larger than match_count, you're seeing a sample, not the answer. - meta.next_offset: present when more results exist. Paginate by calling again with offset=<next_offset>. - meta.advice: rule-based suggestions for pagination or narrowing. Q syntax: whitespace-separated terms are ANDed. Multi-word queries miss variants that don't contain every word. A distinctive term ('Alice', 'Fitzmaurice', 'Bilski') generally has broader recall than a full citation. Use 'OR' / '"phrase"' / '-exclude' for fine control. Scoping (combine freely): - company: company name, matched across recognized name variants. - application_number: single app. Fastest path. - pd_from / pd_to: YYYYMMDD inclusive bounds on Office-Action mail date. - doc_types: CTNF / CTFR / NOA / CTAV / CTQU. - pending_only: when true, narrows to Office Actions on apps whose current status_text is one of the awaiting-response values (Final Rejection Mailed, Non Final Action Mailed, Advisory Action Mailed, Ex parte Quayle, Notice of Allowance Mailed). This supports a combined keyword, company, and pending-status search in one call. Sort modes: - 'relevance' (default): keyword-match strength. Best for prior-art-style retrieval. Degenerate for single-term queries (every match scores ~equal); the advice field will tell you to switch to date_desc if so. - 'date_desc' / 'date_asc': chronological browsing; date_desc places recent rejections first. Pagination uses limit (max 500) and offset; meta.next_offset is null after the final page. This tool returns matching rejection records and a total count, not corpus-wide distribution buckets — narrow the query or paginate to work through the matches.

filewrapper_search

Guided freedom-to-operate analysis. Finds active and pending patent rights that may cover a product, lets the user review the scope and candidates, compares shortlisted claims to the product, and produces an auditable clearance report with ranked risks, unresolved questions, and recommended physical checks. No preliminary retrieval call is required. The workflow is interactive by default: it returns the product's features, the search boundary, the surfaced patents and claims it proposes to read, the clearance read, and the output format, so the user can confirm or revise each. A review point advances only with the user's confirmation. New runs accept `product_description`, or `claim_elements` when the product features are already defined. The report includes the reviewed search scope, relevant granted and pending rights, claim-by-claim findings, legal-status and ownership context, mitigation considerations, and clear warnings for any unresolved scope or data gap. At the final review point the report can be delivered as a Word, Excel or PDF file to download. A partial result does not yet include the clearance conclusion.

freedom_to_operate

Continue a `landscape` run and collect the finished report using the `job_id` returned by `landscape`. It keeps working on the same run and returns the finished bundle directly when it is ready; if the run needs more time it returns the current progress plus a `next_step` identifying `landscape_status` with the same `job_id` as the next step. A result whose status starts with `completed` contains the report. Most runs take 30-240s; runs with `deep_taxonomy` can take up to ~8 minutes, and a stage that repeats across calls is normal, not a stall. While running, `progress` shows the step count and the current stage. Interim progress does not contain a landscape report. The completed bundle has the same structured sections, narrative hints, presentation outline, and optional private `report_url` as a completed `landscape` response.

landscape_status

**The landscape tool.** Comprehensive multi-section report: filer scorecard with composite quality index, filing trajectory + acceleration, geo + CPC distribution, crown jewels (multi-factor), technology evolution heatmap, whitespace matrix, SEP overlay, lead-lag, evolving pipeline (granted/pending/expiring), continuation stacking, M&A signals, momentum forecast. Add `market_context` via `augmentations` to also open with cited market/industry context. Persona-tailored output (vc | ip_director | litigator | rd_scientist | inventor). `q` determines which patents are analysed; `topic` is the plain-English label used for market context. Precise queries combine quoted phrases with OR and classification filters, for example tac_en:("5G NR" OR "5G New Radio") AND cpcpri:H04W*. Bare terms can match an excessively broad corpus. When `q` is absent, the short `topic` label becomes the patent search. A search matching too little or far too much is not reported as a landscape: the result carries status `insufficient_corpus` or `decomposition_required` plus a hint describing how the query can be adjusted. Drives itself: it submits and polls internally. For corpora over ~10k families this can take 90-240s (up to ~8 minutes with `deep_taxonomy`); if it does not finish within one window it returns a `job_id` and a `next_step` identifying `landscape_status` as the continuation tool. Re-entering `landscape` with that job opens another report view rather than polling the existing view. A completed result contains structured report sections, a narrative hint for each section, and a top-level `presentation.report_outline`. The outline identifies the recommended section order and table data, which carry the report's substance; a short bullet summary in their place omits most of it. Hosts that render inline app UIs show the landscape as an interactive report — charts, tables, section navigation — automatically; there is nothing to pass on for that. A completed run also carries `report_url`: that same interactive report, stored and openable only by the person who ran the search — a long signed link, meant as a labelled link rather than pasted as raw text. The field is absent when no interactive report was stored.

landscape

Search for prior art and assess novelty across patents, non-patent literature, or technical-standards contributions. A new search requires `corpus` and `corpus_because`; the server validates that the selected corpus matches the supplied user intent. The `standards` corpus applies to requests for standards contributions. That collection is currently strongest for multimedia video-coding inventions. A complete review may require separate searches across more than one corpus. The tool is collaborative by default: it returns reviewable invention framing, scope, date, filters, search terms, and ranked results so the user can confirm or revise them. A review step advances only with user-supplied confirmation. `autonomous=true` requires explicit user authorization to skip intermediate review; the run then applies defaults and stops at the ranked results — the same results screen, opening with the defaults it chose — where the user refines or picks the deliverable. Existing searches continue with fields returned by the prior result; a new search represents a different invention. A change to an earlier step after the results — the scope, the target date, a filter, the search — is a continuation of the same run: a continuation on the results step with the user's words (e.g. 'go back to the filters and set the year to 2020'); the run reopens that step and keeps the parked results and prior changes — none of it is lost by this reopening. (A new search for text that already has a paused run continues that run; `new_run=true` only if the user explicitly wants to start over.) Returns characterization, public filter and query specifications, ranked references with analysis, additional relevant references when available, and requested report or download deliverables. The subject patent and its related publications are excluded from invalidity results and disclosed in `self_excluded`.

prior_art_search

**Deep prosecution strategy brief** for an Office Action response decision. US prosecutions only. Composite of: file_wrapper + response_arguments + filewrapper_search (similar rejections), enriched with: - rejection-statute mix (the statutes cited in the latest Office Action) - argument patterns: named patterns like 'swearing behind under 1.131', 'TSM rebuttal', 'Graham secondary considerations', 'enablement carve-out' — each with a summary, frequency in the corpus, and 'when to use' note. - recommended_strategies with risk_level (low/med/high) and expected path to allowance - deadline math: statutory due date, USPTO 1-5 month extension fees (large/small/micro entity), AFCP 2.0 eligibility window - strategic options playbook: response (with/without amendment) / RCE / continuation / AFCP 2.0 / pre-appeal brief / full appeal — with viability, expected pendency, USPTO fees, and statute-driven preference annotations.

prosecution_strategy

Extract the argument sections from each prior response on a US application, showing what was argued and what worked. Merges the parsed responses table with applicant response documents (REM / amendments) from the file wrapper. Each response carries _source, and inline arguments_text when the stored body really is argument text; a text_quality flag means the response EXISTS but our stored copy is partial or unavailable. In that case the response and date remain present, and download_url points to the source document. The `_meta.advice` field describes data-quality limitations.

application_response_arguments

SEP essentiality assessment. Construes the claims, identifies the standard and release, reads the specification when it can be retrieved, maps every limitation to a provision, and re-checks each mapping before reaching a weakest-link verdict. Supports SEP essentiality analysis, declared-SEP checks, FRAND licensing research, and patent-to-standard mapping. The tool is collaborative by default: it returns the claims to assess, the standard and release it will chart against, whether the specification was actually retrieved, the limitation-to-provision mapping, and the output format, so the user can confirm or revise each. A review step advances only with user-supplied confirmation. Declared-SEP status (e.g. ETSI) is surfaced when known; standards are often paywalled, so the specification text can be supplied when a fetch is unavailable. A patent is standard-essential when a mandatory portion of the standard cannot be implemented without practicing every limitation of the claim, so the assessment follows the all-limitations / weakest-link rule. Returns the patent, the identified standard and release (with declared status), a per-claim mapping (each limitation with its verbatim normative text, section citation, and match strength), an overall assessment (verdict, confidence, essentiality type, key risks, recommended next steps), and a ready-to-read claim chart. The verdict is delivered in the completed result.

sep_analysis

Search the IP Author patent corpus (179M global publications) using a structured Boolean query DSL. Returns hits[] + the headline count via TOP-LEVEL `total_hits`. FAMILY-LEVEL RESULTS ARE THE DEFAULT (load-bearing): - One result per EXTENDED PATENT FAMILY, not per publication. So a search describes distinct inventions without counting the same family repeatedly. - `total_hits` is the complete family count for count questions. - `family_scope='single'` returns every publication, such as for per-country filing analysis. - `family_scope='simple_family'` groups by simple family. READING THE RESPONSE — load-bearing: - data.total_hits: the complete family-level count. `len(hits)` and facet bucket sums describe only the returned sample. - data.returned: how many rows were actually returned. - data.hits[]: one publication per family. - data.advice: rule-based hints about narrowing or pagination. - _pagination: cursor/has_more/total (mirror of total_hits for backward compat). ASSIGNEE FIELDS — pick the right one: - co: current parent rollup for portfolio-level counts ('all Huawei patents'). co:Huawei catches every Huawei subsidiary rolled up to the canonical parent. - pa: literal assignee name on the document, appropriate when you need a specific entity (e.g. counting 'Apple Computer, Inc.' separately from 'Apple Inc.'). It does not include subsidiary rollups. - normpaorig / suggestedpa: pre/post-reassignment canonical forms. Supports proximity operators (ADJ, NEAR, WITH, SAME, with W/N shorthands and numeric distances like NEAR5, 3W). **EMBEDDED BREAKDOWNS — load-bearing for efficient analysis:** - Every `search` response includes, in `data.facets`, top-5 buckets for top filers (`co`), primary CPC class (`cpcpri`), and publication year (`pdyear`) — a free overview of the result set in the same response, so you rarely need a second call just to break results down. - `auto_facets` selects different breakdown fields, including logical field, e.g. `auto_facets: ["pnctry", "adyear"]` (publication country, filing year); an empty array disables embedded breakdowns. **DATE-RANGE SHORTHAND**: `filters` accepts `{pd_from: "20200101", pd_to: "20251231"}`. Examples: co:Cisco AND pnctry:US AND pd:[20240101 TO *] clm:("zero trust" NEAR5 networking) co:(Qualcomm OR Huawei OR Samsung) AND tac_en:beamforming AND clm:5G AND pd:[20200101 TO *] ← correct for company rollup standards_declared:true AND co:Qualcomm*

search