Abstract: Conventional testing of artificial intelligence (AI) agents is time-consuming and insufficient. Accordingly, embodiments provide an automated testing and validation framework for the tools utilized by AI agents. The framework may leverage artificial intelligence, including a classifier for classifying tools, a generative model that creates test cases based on the tool classification, an optimization model that maximizes test coverage while minimizing computation cost, an edge-detection model that identifies edge test cases, and/or an execution engine that manages execution of the test suite. The framework may be integrated into a continuous integration and continuous deployment (CI/CI) pipeline.

Abstract: A federated data system enables multiple, independent, decentralized, and autonomous data sources to be queried as if they were a single system. State-of-the art federated data systems suffer from excessive data movement, static execution strategies, and inefficient distributed joins. Disclosed embodiments introduce a multi-agent framework into the federation layer of the federated data system. This agentic framework may comprise a supervisor artificial intelligence (AI) agent that divides queries, from a query engine, into subqueries and utilizes other AI agents to perform sub-tasks, such as rewriting one or more the of the subqueries, determining an execution strategy, executing the subqueries according to the execution strategy, and learning from past query executions. The supervisor AI agent may perform in-memory joins of the results of the subqueries, and return a final query result to the query engine.

Abstract: As artificial intelligence (AI) agents become more prevalent, it has become important to measure their effectiveness. Disclosed embodiments enable autonomous, real-time evaluation of AI agents using a monitoring service and peer AI agents. In an embodiment, calls, by a performing AI agent, to models and tools, during a session, are made through respective gateways which collect session data. A monitoring service acquires the session data from the gateways, and invokes one or a plurality of monitoring AI agents to evaluate the performance of the performing AI agent based on the session data and one or more adaptable session parameters. The result of the evaluation(s) may be stored for analysis and development of the performing AI agent.

Abstract: Artificial intelligence (AI) agents are increasingly being used to automate tasks within integration environments. However, a problem occurs in hybrid environments in which the AI agent is hosted in a cloud-computing environment, whereas the tools, required by the AI agent, are hosted on an on-premise system of an organization. In this case, the AI agent may not know the organization-specific operations available through the on-premise tool—let alone, the requirements of those operations. Accordingly, embodiments enable an AI agent to automatically learn the specific operations, including the requirements (e.g., inputs and outputs) of those operations, during installation and/or execution, via a predefined discovery operation that is implemented by the application programming interface of every on-premise tool.

Abstract: A method and system for facilitating user access to enterprise related data are provided. A catalog of data and metadata is generated from enterprise related data stored in a plurality of data stores. A user interface (UI) is displayed on an electronic device associated with a user. The UI is configured to provide a plurality of query options to query the catalog of data and metadata. At least one query option is configured to enable the user to provision a query to a virtual assistant associated with the UI. The query provided by the user using a query option is received, and a processing of the query is facilitated. A display of a response is caused on the UI based on the processing of the query. The response is selected from among a plurality of response options.

Abstract: A method and system for retrieving information from a plurality of data stores associated with the enterprise data universe are provided. The method includes causing display of a user interface (UI) on an electronic device associated with a user. A natural language query provided by the user using the UI is received and parsed to generate a plurality of query elements. A grammar-based analysis of the plurality of query elements is performed and an expression is generated based on the grammar-based analysis of the plurality of query elements. At least one answer to the query is retrieved from a knowledge base using the expression. The retrieved answer is provisioned to the user on the UI.

Abstract: A method and system for facilitating user access to enterprise related data are provided. A catalog of data and metadata is generated from enterprise related data stored in a plurality of data stores. A user interface (UI) is displayed on an electronic device associated with a user. The UI is configured to provide a plurality of query options to query the catalog of data and metadata. At least one query option is configured to enable the user to provision a query to a virtual assistant associated with the UI. The query provided by the user using a query option is received, and a processing of the query is facilitated. A display of a response is caused on the UI based on the processing of the query. The response is selected from among a plurality of response options.

Abstract: A method is disclosed. A finite state machine model for a single system workflow is replicated across a plurality of distributed nodes associated with a leader election protocol. A leader is determined amongst the plurality of distributed nodes to perform a next action of the finite state machine model based at least in part on the leader election protocol. One or more nodes amongst the plurality of distributed nodes are configured to submit a timeout ticket if the next action of the finite state machine model does not appear to have been performed by the leader within a prescribed time.