IP Library Granted Patent US 12688183
Granted Patent B2
US 12688183 · App. 18/827,524 · Granted Jul 21, 2026

Ephemeral views for database query generator

Inventors: Abhishek Kishore Modi (San Francisco, CA); Simon Townsend-Last (New York, NY); Sharabesh Ramesh (New York, NY); Theo Morice Bleier (San Francisco, CA); Parthiv Shah (San Francisco, CA)
Assignee: Notion Labs, Inc.
G06F16/2423G06F16/2425G06F16/24522
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12688183
App. No.
18/827,524
Granted
Jul 21, 2026
Kind
B2
Abstract

A system can generate and render, at a computing device, a page comprising a graphical user interface (GUI) that includes a displayable item from a first block of a block-based data structure. The system can use at least a portion of a natural language prompt received by the GUI to cause a neural network (e.g., an LLM) to generate a query executable against the block-based data structure to return a result set comprising a second block. The second block is not initially displayed at the page and can be discoverable by determining query context using at least a portion of the natural language prompt in combination with a property of the first block. The system can cause the generated query to be executed against the block-based data structure to generate and display, at the GUI, (i) an ephemeral view comprising the result set and (ii) a query tuning control configured to enable dynamic tuning of the generated query via the GUI.

Claims (74)

1 . One or more tangible, non-transitory, computer-readable storage media excluding transitory signals and carrying instructions, the media comprising instructions recorded thereon, wherein the instructions, when executed by at least one data processor of a computing system, cause the computing system to perform operations for enabling user tuning of artificial intelligence (AI)-generated queries against a block-based data structure comprising a render tree having a set of blocks linked via block properties, the operations comprising:

generating and rendering, at a computing device associated with a particular user, a page comprising a graphical user interface (GUI) comprising a displayable item from a first block from the set of blocks included in the render tree;

generating and binding to the page a schema definition configured to enable data discovery of a subset of blocks in the set of blocks, wherein the subset of blocks is not initially displayed on the page, wherein the subset of blocks is generated using permissions information for the particular user, and wherein the permissions information associates the particular subset of blocks with the first block in the render tree via an upward pointer or a downward pointer;

capturing, via an input control of the GUI, a natural language prompt;

using at least a portion of the natural language prompt, performing operations comprising:

using the at least a portion of the natural language prompt, determining a property of the first block;

cross-referencing the property of the first block, via the schema definition, to a second block in the subset of blocks included in the schema definition; and

causing a large language model to generate a query executable against the block-based data structure to return a result set comprising the second block from the block-based data structure;

causing the generated query to be executed against the block-based data structure to generate a result set comprising a displayable item from the second block; and

using the result set, generating and displaying, at the GUI, (i) an ephemeral view comprising the result set and (ii) a tuning control configured to enable dynamic tuning of the generated query via the GUI.

2 . The one or more tangible, non-transitory, computer-readable media of claim 1 , wherein the instructions, when executed by the at least one data processor of the computing system, cause the computing system to perform operations to:

generate additional context using (i) at least an additional portion of the natural language prompt in combination with (ii) a property of the second block;

wherein the query is executable against the block-based data structure to return the result set comprising a third block from the block-based data structure, the third block determined based on the additional context.

3 . The one or more tangible, non-transitory, computer-readable media of claim 1 , wherein the instructions, when executed by the at least one data processor of the computing system, cause the computing system to perform operations to:

in response to detecting a user interaction with the tuning control, modify the generated query.

4 . The one or more tangible, non-transitory, computer-readable media of claim 3 ,

wherein the tuning control is structured to enable a user to interact, via the ephemeral view, with items in the block-based data structure that are not initially visible from the page,

the tuning control being operable to set at least one of a property name of the second block, a condition applied to a property of the second block, or a content option for the property of the second block.

5 . The one or more tangible, non-transitory, computer-readable media of claim 4 , the operations further comprising:

causing a modified query to be executed against the block-based data structure to generate an updated result set for the ephemeral view.

6 . The one or more tangible, non-transitory, computer-readable media of claim 4 , the operations further comprising:

filtering the ephemeral view based on the user interaction with the tuning control.

7 . The one or more tangible, non-transitory, computer-readable media of claim 4 ,

wherein the result set comprises a first item in a first content modality and a second item is in a second content modality different from the first content modality,

wherein the first content modality or the second content modality comprises one or more of text, data, a table, an image, an audio item, a video item, a multimedia item, or a digital map; and

wherein the tuning control is additionally operable to set: (i) at least one of a first property name of the second block that stores the first item, a first condition applied to a property of the second block, or a first content option for the property of the second block, and (ii) at least one of a second property name of a third block that stores the second item, a second condition applied to a property of the third block, or a second content option for the property of the third block.

8 . A computing system comprising at least one data processor and one or more non-transitory, computer-readable storage media excluding transitory signals and carrying instructions, the media having instructions recorded thereon, wherein the instructions, when executed by the at least one data processor of the computing system, cause the computing system to perform operations for enabling user tuning of artificial intelligence (AI)-generated queries against a block-based data structure comprising a render tree having a set of blocks linked via block properties, the operations comprising:

rendering, at a computing device associated with a particular user, a page comprising a graphical user interface (GUI) comprising a displayable item from a first block from the set of blocks included in the render tree;

generating and binding to the page a schema definition configured to enable data discovery of a subset of blocks in the set of blocks, wherein the subset of blocks is not initially displayed on the page, wherein the subset of blocks is generated using permissions information for the particular user, and wherein the permissions information associates the particular subset of blocks with the first block in the render tree via an upward pointer or a downward pointer;

capturing, via an input control of the GUI, a natural language prompt;

using at least a portion of the natural language prompt, performing operations comprising:

using the at least a portion of the natural language prompt, determining a property of the first block;

cross-referencing the property of the first block, via the schema definition, to a second block in the subset of blocks included in the schema definition; and

causing a large language model to generate a query executable against the block-based data structure to return a result set comprising the second block from the block-based data structure;

causing the generated query to be executed against the block-based data structure to generate a result set comprising a displayable item from the second block; and

using the result set, generating and displaying, at the GUI, (i) an ephemeral view comprising the result set and (ii) a tuning control configured to enable dynamic tuning of the generated query via the GUI.

9 . The computing system of claim 8 , wherein the instructions, when executed by the at least one data processor of the computing system, cause the computing system to perform operations to:

generate additional context using (i) at least an additional portion of the natural language prompt in combination with (ii) a property of the second block;

wherein the query is executable against the block-based data structure to return the result set comprising a third block from the block-based data structure, the third block determined based on the additional context.

10 . The computing system of claim 8 , wherein the instructions, when executed by the at least one data processor of the computing system, cause the computing system to perform operations to:

in response to detecting a user interaction with the tuning control, modify the generated query.

11 . The computing system of claim 10 ,

wherein the tuning control is structured to enable a user to interact, via the ephemeral view, with items in the block-based data structure that are not initially visible from the page,

the tuning control being operable to set at least one of a property name of the second block, a condition applied to a property of the second block, or a content option for the property of the second block.

12 . The computing system of claim 11 , the operations further comprising:

causing a modified query to be executed against the block-based data structure to generate an updated result set for the ephemeral view.

13 . The computing system of claim 11 , the operations further comprising:

filtering the ephemeral view based on the user interaction with the tuning control.

14 . The computing system of claim 11 ,

wherein the result set comprises a first item in a first content modality and a second item is in a second content modality different from the first content modality,

wherein the first content modality or the second content modality comprises one or more of text, data, a table, an image, an audio item, a video item, a multimedia item, or a digital map; and

wherein the tuning control is additionally operable to set: (i) at least one of a first property name of the second block that stores the first item, a first condition applied to a property of the second block, or a first content option for the property of the second block, and (ii) at least one of a second property name of a third block that stores the second item, a second condition applied to a property of the third block, or a second content option for the property of the third block.

15 . A computer-implemented method, the method comprising:

rendering, at a computing device associated with a particular user, a page comprising a graphical user interface (GUI) comprising a displayable item from a first block from a set of blocks of a render tree included in a block-based data structure, wherein individual ones of blocks in the set of blocks are linked via block properties;

generating and binding to the page a schema definition configured to enable data discovery of a subset of blocks in the set of blocks, wherein the subset of blocks is not initially displayed on the page, and wherein the subset of blocks is generated using permissions information for the particular user, and wherein the permissions information associates the particular subset of blocks with the first block in the render tree via an upward pointer or a downward pointer;

capturing, via an input control of the GUI, a natural language prompt;

using at least a portion of the natural language prompt, performing operations comprising:

using the at least a portion of the natural language prompt, determining a property of the first block;

cross-referencing the property of the first block, via the schema definition, to a second block in the subset of blocks included in the schema definition; and

causing a large language model to generate a query executable against the block-based data structure to return a result set comprising the second block from the block-based data structure;

causing the generated query to be executed against the block-based data structure to generate a result set comprising a displayable item from the second block; and

using the result set, generating and displaying, at the GUI, (i) an ephemeral view comprising the result set and (ii) a tuning control configured to enable dynamic tuning of the generated query via the GUI.

16 . The method of claim 15 , further comprising:

generating additional context using (i) at least an additional portion of the natural language prompt in combination with (ii) a property of the second block;

wherein the query is executable against the block-based data structure to return the result set comprising a third block from the block-based data structure, the third block determined based on the additional context.

17 . The method of claim 15 , further comprising:

in response to detecting a user interaction with the tuning control, modifying the generated query.

18 . The method of claim 17 ,

wherein the tuning control is structured to enable a user to interact, via the ephemeral view, with items in the block-based data structure that are not initially visible from the page,

the tuning control being operable to set at least one of a property name of the second block, a condition applied to a property of the second block, or a content option for the property of the second block.

19 . The method of claim 18 , further comprising:

causing a modified query to be executed against the block-based data structure to generate an updated result set for the ephemeral view.

20 . The method of claim 18 , further comprising:

filtering the ephemeral view based on the user interaction with the tuning control.