Prosecution Insights
Last updated: April 19, 2026
Application No. 18/672,693

CHAT INTERFACE WITH CHATBOT AGENT SUPPORTED BY LANGUAGE MODELS FOR PLACING GROUP ORDERS

Non-Final OA §101
Filed
May 23, 2024
Examiner
WEAVER, ADAM MICHAEL
Art Unit
2658
Tech Center
2600 — Communications
Assignee
Maplebear Inc.
OA Round
1 (Non-Final)
92%
Grant Probability
Favorable
1-2
OA Rounds
2y 9m
To Grant
99%
With Interview

Examiner Intelligence

Grants 92% — above average
92%
Career Allow Rate
11 granted / 12 resolved
+29.7% vs TC avg
Strong +20% interview lift
Without
With
+20.0%
Interview Lift
resolved cases with interview
Typical timeline
2y 9m
Avg Prosecution
27 currently pending
Career history
39
Total Applications
across all art units

Statute-Specific Performance

§101
33.2%
-6.8% vs TC avg
§103
44.7%
+4.7% vs TC avg
§102
19.0%
-21.0% vs TC avg
§112
2.1%
-37.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 12 resolved cases

Office Action

§101
DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claim(s) 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claims 1, 12, and 20 recite “receiving, via a chat interface of an online system, input data with information about a conversation”, “generating a first prompt for input”, “requesting the ingredient generation LLM to generate, based on the first prompt input into the ingredient generation LLM, the list of ingredients”, “generating a second prompt for input”, “requesting the item generation LLM to generate, based on the second prompt input into the item generation LLM, the list of items at the retailer”, “causing the chat interface to display content”, and “placing the group order comprising the list of items”. These limitations, as drafted, are a process that, under a broadest reasonable interpretation, covers the abstract idea of “mental processes” because they cover concepts performed in the human mind, including observation, evaluation, judgement, and opinion. See MPEP 2106.04(a)(2). That is, other than reciting “a chat interface of an online system”, “an ingredient generation large language model (LLM)”, and “an item generation LLM”, nothing in the claimed elements preclude the steps from practically being performed by a person listening to or reading a conversation between multiple people, writing down ingredients noted by the individuals in the conversation, finding these ingredients at a store or online retailer, and providing a list to the individuals in the group conversation to look over before purchasing the items. This judicial exception is not integrated into a practical application because the additional elements “a chat interface of an online system”, “an ingredient generation large language model (LLM)”, and “an item generation LLM” are all recited at a high- level of generality. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the claims as a whole are directed to an abstract idea (Step 2A, prong two). Claims 1, 12, and 20 do not include any additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical applications, the additional elements of “a chat interface of an online system”, “an ingredient generation large language model (LLM)”, and “an item generation LLM” amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (Step 2B). Dependent claims 2-11 and 13-19 are directed to the conversational context and metadata of the conversation, as well as the generation of the individual prompts. That is, nothing in the claimed elements, preclude the steps from practically being performed by a person listening to or reading a conversation between multiple people, writing down ingredients noted by the individuals in the conversation, finding these ingredients at a store or online retailer, and providing a list to the individuals in the group conversation to look over before purchasing the items. Even when considered individually and in combination, the additional elements in claims 1-20 represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept (Step 2B). Prior Art Discussion: Best prior art of record relevant to the claimed invention but not considered: Olivier et al. (US Patent Application Publication No. 2025/0322438, having the same applicant and inventors; see Abstract and para [0004]) describes an online concierge system and method that generates a set of items and a list of ingredients using an ingredient identification model and a candidate order form model, and then generates a final order form. Davish et al. (US Patent Application Publication No. 2025/0005297; see paras [0003]-[0004] and Figs. 1A and 3) describes a system for a chatbot conversing with a user, wherein the user’s queries, as well as chat history and metadata, are input as prompts into an LLM to accomplish a particular goal. Boyd et al. (US Patent Application Publication No. 2025/0315875, having the same applicant and inventors; see Abstract, paras [0002]-[0003], and Fig. 3), describes a system for monitoring an online database and using LLMs to generate a list of recipes that are recommended to the user, wherein then the user is able to choose whether or not to add these recommended items into a cart. Lowet et al. (EP3735880A1; see Abstract, para [0048], and Fig. 4) describes a food processing device adapted to identify an ingredient and an associated recipe and a processor is adapted to identify the ingredients and the associated recipe by way of a machine learning algorithm trained to recognize ingredients based on the sensed ingredient characteristics. The prior art of record, including the above cited references, alone or combined, neither teaches nor renders obvious at least the limitations comprising, as a whole, “a method, performed at a computer system comprising a processor and a computer-readable medium, comprising: receiving, via a chat interface of an online system, input data with information about a conversation between a plurality of users of the online system about a group order for the plurality of users; generating a first prompt for input into an ingredient generation large language model (LLM), the first prompt including the received input data and a request for generating a list of ingredients for the group order; requesting the ingredient generation LLM to generate, based on the first prompt input into the ingredient generation LLM, the list of ingredients and metadata associated with the plurality of users; generating a second prompt for input into an item generation LLM, the second prompt including the list of ingredients, the metadata and a request for generating a list of items at a retailer associated with the online system for the group order; requesting the item generation LLM to generate, based on the second prompt input into the item generation LLM, the list of items at the retailer; causing the chat interface to display content prompting approval by the plurality of users for conversion of the list of items; and responsive to the approval, placing the group order comprising the list of items at the online system for delivery to a user of the plurality of users”, in combination with the rest of the limitations recited in the independent claims 1, 12, and 20. Claims 2-11 depend from claim 1, and claims 13-19 depend from claim 12. Note: If the independent claims 1, 12, and 20 are amended to overcome the rejection, the Application can be placed in condition for allowance. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM MICHAEL WEAVER whose telephone number is (571)272-7062. The examiner can normally be reached Monday-Friday, 8AM-5PM EST. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at (571) 272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /ADAM MICHAEL WEAVER/Examiner, Art Unit 2658 /RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658
Read full office action

Prosecution Timeline

May 23, 2024
Application Filed
Feb 19, 2026
Non-Final Rejection — §101 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12591752
ZERO-SHOT DOMAIN TRANSFER WITH A TEXT-TO-TEXT MODEL
2y 5m to grant Granted Mar 31, 2026
Patent 12585765
SYSTEM AND METHOD FOR ROBUST NATURAL LANGUAGE CLASSIFICATION UNDER CHARACTER ENCODING
2y 5m to grant Granted Mar 24, 2026
Patent 12579375
IMPLEMENTING ACTIVE LEARNING IN NATURAL LANGUAGE GENERATION TASKS
2y 5m to grant Granted Mar 17, 2026
Patent 12562077
METHOD, COMPUTING DEVICE, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM TO TRANSLATE AUDIO OF VIDEO INTO SIGN LANGUAGE THROUGH AVATAR
2y 5m to grant Granted Feb 24, 2026
Study what changed to get past this examiner. Based on 4 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
92%
Grant Probability
99%
With Interview (+20.0%)
2y 9m
Median Time to Grant
Low
PTA Risk
Based on 12 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month