Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →17 patent families cover function-calling schema generation for tool-using agents, with filings concentrated in G06F and G06N classes.
22 published records collapse into 17 simple (DOCDB) families; the difference is the same invention filed in more than one country. In force = 5 of 22 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.
This page reports a search for records combining function calling, tool invocation or API calling language with schema and agent terms across patent abstracts, claims and titles. The search string sets no date limit, so the result set spans whatever filing dates these records carry, not a fixed window the page chose. It returns 22 published records that de-duplicate to 17 simple patent families once filings for the same invention across different countries are merged.
The pool here is small: 17 families is not enough to support claims about a market, a trend, or who controls a technology area. Treat this page as a starting point for a closer search, not a finished map of the field.
Ordered by volume only, not by importance or claim strength. Counted in simple (DOCDB) patent families, so one invention filed in several countries counts once. Names come from Patsnap's standardised assignee field as recorded on each document; subsidiaries and group companies are not merged. The icon before each name is read from the name itself (words such as University, Institute or Ltd); the data carries no organisation-type field, so treat it as a reading aid rather than a classification. Filings held by named individuals rather than organisations are removed where they can be identified (11 here); that identification is not exhaustive, so an individually held filing can still appear below. Either way those filings stay inside the totals above. This table shows the top 12 of the 12 filers returned for this search; the data endpoint returns at most 100 entities, so even that 12 is not the complete set of filers. A single family can name more than one filer, so these counts overlap and do not add up to the total.
Pick a task. Every answer cites the patents behind it.
The figures below cover filing offices, the recent filing window, and the IPC subclasses that carry the most families in this set.
Published records rose from 7 in 2025 to 15 in 2026. This trend chart shows a recent window only, not the full scope of the search, and 2022 onward is still filling in as later-filed applications publish, recent years will read higher once those publications catch up. The series counts documents, not inventions, so a single invention filed in multiple places adds more than one mark.
Counted in published records by earliest filing year, not de-duplicated into families. A filing is counted in the year it was filed, but it only becomes visible after it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. 2022 onwards are therefore still filling in and are shaded; no growth figure on this page uses them. Because this series counts documents rather than inventions, a rise can mean more inventions or the same inventions filed in more countries; this dataset cannot separate the two.
G06F (Electric digital data processing) appears on 64.7% of the 17 families, the highest share in this set, followed by G06N (Computing based on AI models) at 41.2%, H04L (Digital information transmission) at 29.4%, and G06Q (Business, commerce & admin data processing) at 17.6%. Because one family can carry several IPC codes, these shares add up to more than 100%.
Shares are the percentage of the 17 patent families in scope. One patent family can carry several IPC classes, so the shares add up to more than 100%.
This page is one run against one query. Ask Eureka your own question about function calling schema generation for tool-using agents patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaThe abstract describes a method by a project manager agent that decomposes a task request into sub-tasks, sends each to a separate AI agent using a model-agnostic message schema, and on receiving responses detects a tool invocation command and routes it accordingly. It is the first record returned under the database's default ordering, not a ranking by citations, grant status or breadth.Filed by LANCIO, LLC; dated 2026-10-01. Shown here because it is the first record returned, not because it is the most cited or the broadest.


Selected as the first record the search returns under the database default order, then shown in full. It is not ranked by citations, claim breadth or commercial importance, and it is not a judgement about which filing in this space matters most.
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Three figures from this search are worth reading carefully before drawing any conclusion from them.
SYMBIOSIS INT DEEMED UNIV is named on 1 of the 17 simple patent families (5.9%). Eleven other filers are also named on 1 family each, and the remaining listed filers hold 2 or fewer. Filer rows are not rolled up to corporate group and one family can name more than one filer, so these rows are not added together here.
G06F (Electric digital data processing) appears on 64.7% of the 17 families in scope, ahead of G06N at 41.2%, H04L at 29.4% and G06Q at 17.6%. Because a family can carry more than one IPC code, these shares sum to more than 100% and are not mutually exclusive groupings.
At retrieval, 5 of the 22 published records (23%) were granted and still in force. The remaining records fall into other statuses not broken out individually here, so this figure describes status at one point in time rather than an outcome rate.
The search returned records filed at 5 receiving offices: United States (8), WIPO/PCT (6), India (5), China (2) and Australia (1), counted in published records. These counts sum to the record total, not the family total, since one invention can appear at more than one office.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to function calling schema generation for tool-using agents patent landscape, with the prior art for and against each one.
This page surfaces counts and classifications; the next steps involve reading actual claim language and tracking how the set changes.
An abstract or a family count cannot establish what a granted claim requires. Pull the claim sets for the records that matter to your work before drawing any freedom-to-operate conclusion.
Explore records in EurekaThe most recent filing years in this dataset are still incomplete because of publication lag. Re-running this search periodically will surface records that have not yet published.
Set up monitoring in EurekaA 17-family result is thin enough that adjacent phrasing could materially change what comes back. Testing related terms may surface records this exact string misses.
Refine this search in EurekaThis search returned 22 published records that de-duplicate to 17 simple patent families, where a family groups filings for the same invention across countries. The search string combines function calling, tool invocation or API calling language with schema and agent terms, so it captures a specific phrasing rather than every patent that might touch this area. Different wording could return a different set, so treat 17 as the size of this particular search, not a count of all patents on the topic.
Twelve organisations appear in the filer list returned by this search, and none is named on more than 1 of the 17 families except the joint leaders, all tied at 1 family each. SYMBIOSIS INT DEEMED UNIV and eleven other filers each hold the same single-family count, so there is no filer with a larger count in this dataset. The list excludes filings held by named individuals, which are still counted in the totals but not shown as rows, and it is not the complete set of filers since the underlying data endpoint caps at 100 entities.
The IPC subclasses with the largest share of the 17 families are G06F (Electric digital data processing) at 64.7%, G06N (Computing based on AI models) at 41.2%, H04L (Digital information transmission) at 29.4%, and G06Q (Business, commerce & admin data processing) at 17.6%. Because a single family can carry more than one classification code, these percentages add up to more than 100% and should not be read as a partition of the dataset. Smaller classes also appear in the search but are not detailed here.
5 of the 22 published records (23%) were granted and still in force as of the 2026-10-21 retrieval date. The remaining records sit in other statuses, pending, withdrawn, refused or lapsed, that are not broken out individually in this dataset, so no single alternative status can be quoted. Legal status changes continuously, so this figure is a snapshot rather than a fixed outcome.
No. The dataset covers 17 simple patent families returned by one specific search string, and a 17-family pool is too small to support conclusions about a market, a trend, or which organisation controls a technology area. The filer list itself is capped and excludes individually named inventors from its rows even though they remain inside the totals. This page is best used as a starting point for a more targeted search rather than a finished landscape.
The trend chart, counted in published records by earliest filing year, shows 7 records in 2025 rising to 15 in 2026, with 2022 onward still filling in as later filings publish. Because publication can lag filing by up to 30 months for some routes, the most recent years understate their eventual totals and should not be read as a slowdown or acceleration. The series also counts documents rather than inventions, so one invention filed in several countries adds more than one mark to the line.
Go past this page: query the whole function calling schema generation for tool-using agents patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Search. Every figure on this page comes from one Patsnap search, run once and not edited afterwards. This is the exact search string:
TAC:(("function calling" OR "tool invocation" OR "API calling") AND schema AND agent)
Reading the field codes: TAC searches the title, abstract and claims of each record, not the full description. The search string sets no date limit, so the scope is every matching record in the database regardless of when it was filed. It is not restricted to recent years. How this string was built matters for how far the counts can be pushed. It was generated in batch from a topic list rather than hand-crafted for this page, and the result set is not manually screened. A keyword search over title, abstract and claims both over-captures (unrelated filings that happen to use the same words) and under-captures (the same invention written in different words). This page cannot measure either effect, so read every figure here as what this particular string returned, not as what exists in the field. One subclass (G06F) carries 64.7% of the patent families, so this search returned a classification-tight set.
What is being counted. Two different units appear on this page and they are not interchangeable. The filer list and the technology split are counted in simple (DOCDB) patent families: one invention counts once however many countries it was filed in. The total, the jurisdiction split and the filing-year chart are counted in published records: the same invention counts once per publication. For this search that is 22 records and 17 families. Record counts reward filing in many jurisdictions; family counts do not. Shares are only ever taken against a denominator in the same unit, and each one names it.
Who the filers are. Names come from Patsnap's standardised assignee field, as recorded on the documents themselves. They are not rolled up to corporate group: a parent and its subsidiaries appear as separate entries, and a portfolio acquired from another company stays under the name on the document unless the assignment is reflected there. This list is meant to carry organisations, not people. Filings held by a named individual are identified by matching the assignee against the inventors on the same search, and, for names written in Chinese, Japanese or Korean characters, by the name carrying no organisational suffix; those are removed from the list (11 of them here). Neither test is exhaustive: the inventor list it matches against is itself capped, and a personal name written in Latin script with no organisational wording in it cannot be told apart from a short company name by rule. So an individually held filing can still appear in the list. Those filings stay inside every total and share on this page either way, so the listed entries can add up to less than the total. A record shown in full further down still names its assignee exactly as the patent office records it, including where that is a person: that name is how the record is identified and checked. What is left out of the ranking is people as ranked entries, not people as cited sources. The table shows the top 12 of the 12 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 12 is not every filer. One patent family can name several filers and each is counted separately, so these rows are not slices of a divided whole: adding them together over-counts, and this page deliberately publishes no combined "top five" share for that reason. See every filer, individuals included
Dates. The year chart counts by earliest filing year, not publication year. A filing only becomes visible once it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. Measured across these pages, the year four back from today still holds only about 89% of its eventual count. 2022 onwards are therefore shaded on the chart as still filling in. The data behind this page was retrieved on 2026-10-21.
Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (5 of 22). Everything else is pending, withdrawn, refused, lapsed or not determinable, and those states are not broken out here because the underlying codes do not separate them cleanly. Legal status changes continuously and is reported per document, not per family. Get the status breakdown in Eureka
Classification. The technology split uses IPC subclasses (four characters, for example H01M). A single record usually carries several, so the shares add up to more than 100% and a record can appear in more than one bar. Subclass is a coarse grouping; it describes the field a record was classified into, not what the claims cover. Break the classes down to subgroup level
Who wrote the words. The tables, charts, counts, shares and patent numbers on this page are produced directly from the search result by a program; none of them are written or estimated by a language model. The surrounding prose, headings, FAQ answers and the answers in the question panel are drafted by a language model that is given those same figures and is not permitted to introduce others. Prose can still mis-describe a correct figure, so where the two disagree, the tables and charts are the record.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries limitations that apply to every figure above. Recent filings are under-counted, because an application is not public until roughly 18 months after filing and database loading adds further delay. The search string defines and constrains everything shown: records that use different terminology, or that sit outside the fields searched, are absent and cannot be counted. Applicant names, classification codes, legal-status codes and citation records are taken as recorded and may contain errors, duplicates, omissions or stale entries. Ordering by volume is not a measure of quality, scope, enforceability or commercial value, and a larger portfolio is not a stronger one. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, validity or infringement search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. No attorney-client relationship is created by it. Any patent, commercial, or strategic decision should be verified independently against the primary records and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
The question panel. The answers behind the suggested questions on this page were written when the page was generated, not in response to your click. The progress steps that play before an answer appears are an animation of how that analysis was done; nothing is being searched or computed at that moment. Typing your own question instead opens Patsnap Eureka, which does run it live.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.
Help us improve
Something wrong, out of date, or missing on this page? Tell us and it goes straight to the team that maintains it.
This page