US-20260127199-A1 - DECISION TRANSPARENCY ENHANCEMENT AND INTEGRATION OF USER FEEDBACK AND CONTROL OF ARTIFICIAL INTELLIGENCE OUTPUTS

Abstract

Methods and systems for decision transparency enhancement and integration of user feedback and control of artificial intelligence outputs are provided. A generative artificial intelligence (AI) agent configured to autonomously perform actions on platform elements and generate outputs based on information items is maintained. Each output is associated with metadata identifying one or more platform elements and one or more information items used. User input querying about a specific output is received via a user interface provided. A natural language response explaining the reasoning behind the output, generated using the metadata associated with the specific output and including references to the platform elements and information items identified in the metadata, is obtained and presented via the user interface.

Inventors

• Vlad MYSTETSKYI
• Danielle VERTMAN
• Oded BEN YEOSHOA
• Adi LIVNE
• Rony KOCH

Assignees

• Monday.com Ltd.

Dates

Publication Date

20260507

Application Date

20251231

Claims (20)

1. 1 . A system for enhancing decision transparency of artificial intelligence outputs, comprising: one or more processors configured to: maintain a generative artificial intelligence (AI) agent configured to autonomously perform actions on platform elements and generate outputs based on information items in at least one data store; associate each of the outputs generated by the generative AI agent with metadata identifying one or more platform elements and one or more information items used in generating each output; provide a user interface for prompting user input querying regarding the outputs generated by the generative AI agent; receive, via the user interface, a user input querying about a specific output generated by the generative AI agent; obtain a natural language response explaining the reasoning behind the output, generated using the metadata associated with the specific output and including references to the platform elements and information items identified in the metadata; and present the natural language response via the user interface.
2. 2 . The system of claim 1 , wherein the one or more processors are configured to compute a confidence score for each of the outputs generated by the generative AI agent, and present via the user interface the confidence score for the specific output.
3. 3 . The system of claim 2 , wherein the one or more processors are configured to responsive to the confidence score falling below a threshold for the specific output, prompt user input via the user interface for confirming that the generative AI agent is enabled to act upon the specific output.
4. 4 . The system of claim 2 , wherein the one or more processors are configured to: responsive to the confidence score exceeding a threshold, operate the generative AI agent to automatically act upon the specific output.
5. 5 . The system of claim 2 , wherein computing the confidence score comprises: calculating a semantic similarity score between the specific output and the information items used in its generation.
6. 6 . The system of claim 2 , wherein computing the confidence score comprises: calculating a semantic similarity score between the specific output and user interaction with the platform elements used in its generation.
7. 7 . The system of claim 2 , wherein computing the confidence score comprises: quantifying a volume of logged inputs within the information items used in generation of the specific output.
8. 8 . The system of claim 1 , wherein the one or more processors are configured to: store the natural language response in the at least one data store as an additional information item for use by the generative AI agent in outputs generation.
9. 9 . The system of claim 1 , wherein the one or more processors are configured to: provide a first visual signal indicating one or more displayed items affected by the specific output.
10. 10 . The system of claim 9 , wherein the one or more processors are configured to: provide, responsive to presentation of the natural language response, a second visual signal indicating one or more displayed items affected by the specific output.
11. 11 . The system of claim 10 , wherein the first and second visual signals are different from one another.
12. 12 . The system of claim 1 , wherein the one or more processors are configured to: provide a first visual signal indicating one or more displayed items affected by a first output generated by the generative AI agent via a first action type, and provide a second visual signal indicating one or more other displayed items affected by a second output generated by the generative AI agent via a second action type, wherein the first and second action types are different from one another and the first and second visual signals are visually distinct from one another.
13. 13 . The system of claim 1 , wherein the user interface comprises an interactive visual element for receiving the user input querying about the specific output.
14. 14 . The system of claim 13 , wherein the interactive visual element is presented next to the specific output.
15. 15 . The system of claim 1 , wherein the natural language response comprises at least one explanation type selected from the group consisting of: feature importance, rule tracing, and example based.
16. 16 . The system of claim 1 , wherein the natural language response is obtained by retrieving the metadata associated with the specific output from storage and generating the natural language response based on the metadata ad hoc in response to receiving the user input.
17. 17 . The system of claim 1 , wherein the natural language response is pre-generated based on the metadata associated with the specific output and obtained by retrieving it from storage in response to receiving the user input.
18. 18 . The system of claim 1 , wherein the generative AI agent is configured to: generate an automation of a task comprising one or more actions performed on one or more platform elements, compute a confidence score for a respective action of the automation, and determine according to the confidence score whether to perform at least one of: initiating the respective action in course of running the automation, and triggering the automation for running.
19. 19 . The system of claim 1 , wherein the one or more processors are configured to: provide an indication identifying a respective one of the at least one data store used for generating the specific output.
20. 20 . The system of claim 19 , wherein at least one data store comprises an on-platform internal data store and an off-platform external data store, and wherein respective indications identifying the internal and external data stores are different from one another.

Description

RELATED APPLICATIONS This application is a Continuation-in-Part (CIP) of PCT Patent Application Nos. PCT/IL2024/050820, PCT/IL2024/050821, and PCT/IL2024/050822, all having an International Filing Date of Aug. 14, 2024, and each of which claim the benefit of priority of U.S. Provisional Patent Application Nos. 63/519,519 filed on Aug. 14, 2023, 63/548,339 filed on Nov. 13, 2023, and 63/645,998 filed on May 13, 2024. This application also claims the benefit of priority of U.S. Provisional Patent Application No. 63/802,765 filed on May 9, 2025. The contents of the above applications are all incorporated by reference as if fully set forth herein in their entirety. BACKGROUND Some embodiments described in the present disclosure relate to implementing artificial intelligence capabilities in digital environments and, more specifically, but not exclusively, to integrating generative artificial intelligence capabilities within digital environments such as Software as a Service platforms, cloud-based software solutions, and/or the like, optionally aimed to enhance data management, project coordination, cross-platform synchronization, data interaction and/or analysis functionality, product customization, and/or the like. In recent years, the software industry has seen a significant shift towards cloud-based solutions, with Software as a Service (SaaS) emerging as a dominant model for delivering applications to users, and the adoption of SaaS platforms for various business operations growing exponentially. These cloud-based solutions, and SaaS platforms specifically, offer numerous advantages, including accessibility, scalability, and cost-effectiveness. These platforms typically provide a wide range of applications and services to meet various business needs such as customer relationship management (CRM), human resources management (HRM), project planning and/or management, accounting, marketing automation, data analysis, and/or the like. Concurrently, the field of artificial intelligence (AI) has experienced rapid advancements, particularly in the area of generative AI. Generative AI models, such as large language models (LLMs), have demonstrated remarkable capabilities in natural language processing (NLP), content generation, and complex problem-solving. These AI models can learn patterns and structures from input data and generate new content with similar characteristics. In particular, generative AI models, via capabilities of creating new content and providing intelligent responses based on vast amounts of training data, have shown immense potential in enhancing user interactions and automating complex tasks. SUMMARY It is an object of the present disclosure to describe systems and methods of artificial intelligence capabilities integration in software applications, enhanced management and cross synchronization of software platforms, and intent-based interactions in software platforms. The foregoing and other objects are achieved by the features of the independent claims. Further implementation forms are apparent from the dependent claims, the description and the figures. The disclosed subject matter, in some embodiments thereof, relates to systems and methods for implementing artificial intelligence (AI) capabilities in software applications and, more particularly, but not exclusively, to systems and methods for integrating generative artificial intelligence capabilities within Software as a Service (SaaS) platforms. In one aspect, embodiments of the disclosed subject matter provide a method and a system for using generative artificial intelligence (AI) in a Software as a Service (SaaS) platform. The system comprises one or more processors configured to cause a display of a table structure including multiple items, each with multiple item characteristics, associated with a common table objective. The system further displays at least one input interface for receiving user inputs to interact with items in the table structure. A generative AI agent is added as a SaaS platform user with credentials to read and write data in certain items. The system prompts the generative AI agent with data type of item characteristics and/or structural relations between items, generates instructions for performing an action by interacting with item characteristics, and executes the generated instructions. In another aspect, embodiments of the disclosed subject matter provide a method and a system for using generative artificial intelligence (AI) for intent-based interaction within a Software as a Service (SaaS) platform. The method involves maintaining a generative AI agent configured to interact with sets of alphanumeric data stored in table structures, each with a plurality of items comprising the alphanumeric data. The generative AI agent is associated with a profile defining its role in a team assigned to a project. The role refers to a set of rules according to which the generative AI agent is guided to interact with data in