# US 2026/0093899 A1 · Collaboration on an asset using a generative response engine

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0093899 A1
- Document ID: US20260093899A1
- Status: Published application
- Kind: A1
- Application number: 19/043,013
- Filed: 2025-01-31
- Published: 2026-04-02
- Earliest claimed: 2024-09-30
- Assignees: OpenAI OpCo, LLC
- Applicants: OpenAI OpCo, LLC.
- Inventors: Bryan Ashley; Lee Byron; Kai Chen; Alexi Christakis; Noah Deutsch; Thomas Dimson; Tarun Gogineni; Daniel Levine; Matthew Lim; Bryant Jow; Akshay Nathan; Karina Nguyen; Michael Wu
- Web page: https://patentgrep.com/patent/US20260093899A1

## CPC

- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/35: Discourse or dialogue representation
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

The present technology can integrate a generative response engine capable of dynamically determining and displaying generated content in appropriate user interface formats. In response to user prompts, the generative response engine can display content in a content frame separate from the traditional conversational interface. The system intelligently assesses the nature of the content and determines the most suitable display mode, enhancing user interaction and collaboration. This interface facilitates both content creation and user collaboration by enabling seamless transitions between conversational responses and rich media content, such as drawings, games, or documents. The system thus optimizes content interaction based on its type and user needs, supporting diverse use cases across media formats.

## Claims

### Claim 1

A method comprising:
receiving, in a conversational interface of a front end to a generative response engine, a first prompt from a user account;
triggering, by the generative response engine, a collaborative surface of the front end distinct from the conversational interface of the front end, wherein triggering occurs in response to a determination by the generative response engine that a context of the first prompt satisfies a collaborative-interaction criterion;
outputting, by the generative response engine in response to the first prompt, an asset displayed in the collaborative surface, wherein the asset can be manipulated in the collaborative surface by the user account and the generative response engine and wherein manipulation of the asset by the user account can be used as prompts to the generative response engine;
displaying, by the front end via the collaborative surface, a current version of the asset wherein the current version of the asset is generated from user manipulation of the asset in the collaborative surface;
receiving, by the generative response engine, a second prompt and the current version of the asset, wherein the second prompt contains an instruction for modifying the current version of the asset;
modifying, by the generative response engine, the current version of the asset based on the instruction using tokens output by the generative response engine to create an updated version of the asset, wherein the tokens are sampled by the generative response engine from a probability distribution of possible tokens; and
providing, to the front end, the updated version of the asset for display via the collaborative surface.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
creating, by the generative response engine, a regular expression (RegEX) string to identify text of the asset that should be selected and replaced in creating the updated version of the asset.

### Claim 3 (depends on 2)

The method of claim 2, wherein the RegEX string instructs the collaborative surface to visually select the text of the asset that should be selected and replaced.

### Claim 4 (depends on 1)

The method of claim 1, wherein an interactive interface of the front end comprises a conversational interface and the collaborative surface, wherein the collaborative surface facilitates interaction with the asset by the user account.

### Claim 5 (depends on 4)

The method of claim 4, wherein the at least a portion of the current version of the asset was modified via the collaborative surface of the interactive interface, and the first prompt and the second prompt were provided to the generative response engine via the conversational interface.

### Claim 6 (depends on 5)

The method of claim 5, wherein the current version of the asset is provided to the generative response engine in a whisper message, wherein the whisper message is not displayed to the user in the conversational interface.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining to trigger the collaborative surface of the front end is based on the context indicating an intent of a user account to collaborate with the generative response engine on the asset.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
receiving, by the generative response engine, a message history comprising the first prompt and the second prompt, wherein the message history can include a subsequent prompt.

### Claim 9 (depends on 1)

The method of claim 1, wherein the generative response engine is post-trained on generated synthetic data using unsupervised learning techniques to determine when to trigger the collaborative surface.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
storing, in a history log, the current version of the asset and the updated version of the asset
receiving, at the front end, an undo prompt for undoing the modification to create the updated version of the asset;
retrieving, from the history log, the current version of the asset; and
displaying the current version of the asset in the collaborative surface.

### Claim 11

A computing system, comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, configure the computing system to:
receive, in a conversational interface of a front end to a generative response engine, a first prompt from a user account;
trigger, by a generative response engine, a collaborative surface of the front end distinct from the conversational interface of the front end, wherein triggering occurs in response to a determination by the generative response engine that a context of the first prompt satisfies a collaborative-interaction criterion;
output, by the generative response engine in response to the first prompt, an asset displayed in the collaborative surface, wherein the asset can be manipulated in the collaborative surface by the user account and the generative response engine and wherein manipulation of the asset by the user account can be used as prompts to the generative response engine;
display, by the front end via the collaborative surface, a current version of the asset wherein the current version of the asset is generated from user manipulation of the asset in the collaborative surface;
receive, by the generative response engine, a second prompt and the current version of the asset, wherein the second prompt contains an instruction for modifying the current version of the asset;
modify, by the generative response engine, the current version of the asset based on the instruction using tokens output by the generative response engine to create an updated version of the asset, wherein the tokens are sampled by the generative response engine from a probability distribution of possible tokens; and
provide, to the front end, the updated version of the asset for display via the collaborative surface.

### Claim 12 (depends on 11)

The computing system of claim 11, wherein the instructions further configure the computing system to:
create, by the generative response engine, a regular expression (RegEX) string to identify text of the asset that should be selected and replaced in creating the updated version of the asset.

### Claim 13 (depends on 12)

The computing system of claim 12, wherein the RegEX string instructs the collaborative surface to visually select the text of the asset that should be selected and replaced.

### Claim 14 (depends on 11)

The computing system of claim 11, wherein an interactive interface of the front end comprises the conversational interface and the collaborative surface, wherein the collaborative surface facilitates interaction with the asset by the user account.

### Claim 15 (depends on 14)

The computing system of claim 14, wherein the at least a portion of the current version of the asset was modified via the collaborative surface of the interactive interface, and the first prompt and the second prompt were provided to the generative response engine via the conversational interface.

### Claim 16 (depends on 15)

The computing system of claim 15, wherein the current version of the asset is provided to the generative response engine in a whisper message, wherein the whisper message is not displayed to the user in the conversational interface.

### Claim 17 (depends on 11)

The computing system of claim 11, wherein determining to trigger the collaborative surface of the front end is based on the context indicating an intent of a user account to collaborate with the generative response engine on the asset.

### Claim 18 (depends on 11)

The computing system of claim 11, wherein the instructions further configure the computing system to:
receive, by the generative response engine, a message history comprising the first prompt and the second prompt, wherein the message history can include a subsequent prompt.

### Claim 19 (depends on 11)

The computing system of claim 11, wherein the generative response engine is post-trained on generated synthetic data using unsupervised learning techniques to determine when to trigger the collaborative surface.

### Claim 20

A non-transitory computer-readable storage medium comprising instructions that when executed by at least one processor, cause the at least one processor to:
receive, in a conversational interface of a front end to a generative response engine, a first prompt from a user account;
trigger, by a generative response engine, a collaborative surface of the front end distinct from the conversational interface of the front, wherein triggering occurs in response to a determination by the generative response engine that a context of the first prompt satisfies a collaborative-interaction criterion;
output, by the generative response engine in response to the first prompt, an asset displayed in the collaborative surface, wherein the asset can be manipulated in the collaborative surface by the user account and the generative response engine and wherein manipulation of the asset by the user account can be used as prompts to the generative response engine;
display, by the front end via the collaborative surface, a current version of the asset wherein the current version of the asset is generated from user manipulation of the asset in the collaborative surface;
receive, by the generative response engine, a second prompt and the current version of the asset, wherein the second prompt contains an instruction for modifying the current version of the asset;
modify, by the generative response engine, the current version of the asset based on the instruction using tokens output by the generative response engine to create an updated version of the asset, wherein the tokens are sampled by the generative response engine from a probability distribution of possible tokens; and
provide, to the front end, the updated version of the asset for display via the collaborative surface.
