Abstract: A substantial learning curve is required to construct integration processes in an integration platform. This can make it difficult for novice users to construct effective integration processes, and for expert users to construct integration processes quickly and efficiently. Accordingly, embodiments for building and operating a model to predict next steps, during construction of an integration process via a graphical user interface, are disclosed. The model may comprise a Markov chain, prediction tree, or an artificial neural network (e.g., graph neural network, recurrent neural network, etc.) or other machine-learning model that predicts a next step based on a current sequence of steps. In addition, the graphical user interface may display the suggested next steps according to a priority (e.g., defined by confidence values associated with each step).

Abstract: “Prevention is better than cure” aptly applies to the field of cybersecurity. However, state-of-the-art integration systems generally perform late-stage scanning that is reactive, rather than proactive. This can be particularly dangerous in a low-code environment, in which the integration processes may be constructed by novice users without expertise in mitigating cybersecurity threats. Accordingly, embodiments utilize artificial intelligence to proactively detect and resolve cybersecurity threats during the design stage of integration processes. For example, a generative model may be used with crowd-sourced integration configurations to generate synthetic integration data that are targeted towards specific cybersecurity threat endpoints. This synthetic integration data may be input to an integration process, during integration testing within a test environment, to detect and resolve cybersecurity threats, prior to deployment of the integration process to a production environment.

Abstract: State-of-the-art techniques for detecting personally identifiable information (PII) in data-processing workflows are not scalable, are inefficient, and/or are prone to human error. Accordingly, disclosed embodiments utilize a PII classifier during the design phase or at compile time, for an integration process, to automatically determine the likelihood that each field in the integration code of the integration process is personally identifiable information. Fields identified as likely representing PII data may be automatically excluded from being indexed into the crowd-sourced historical data that are used to train an artificial intelligence (AI) model. This improves operational efficiency, scalability, flexibility, data quality, and accuracy of the AI model, as well as facilitating compliance with data privacy and security regulations, improving trust and adoption, and fostering proactive data management.

Abstract: State-of-the-art automated techniques for generating application programming interface (API) documentation are not scalable as the number and sizes of application programming interfaces increase. Accordingly, disclosed embodiments provide scalable generation of API documentation using a split-and-merge algorithm and artificial intelligence (e.g., a generative artificial intelligence model, such as a large language model) for technically detailed types of API documentations. In addition, disclosed embodiments may utilize a key-endpoint shortlisting algorithm, along with the same artificial intelligence, for high-level types of API documentation.

Abstract: There has been progress towards making integration platform as a service (iPaaS) more accessible to novice users, using low-code integration-development environments. However, such users may easily miss opportunities for integrations within their integration platforms. Accordingly, disclosed embodiments provide an artificial intelligence (AI) agent that is capable of proactively reaching out to a user, and automatically identifying gaps within the user's integration platform, recommending integrations to solve those gaps, and generating an integration process to automate each recommend integration.

Abstract: A method of matching integration process users may comprise receiving execution logs recording data associated with selections of integration process visual elements, generating a user/visual element interaction matrix based on counts of integration process visual element selections, inputting the user/visual element interaction matrix into a trained neural network to generate an optimized user preference and visual element embedding matrices, determining a latent feature user preference value adapting positive user feedback to incorporate implicit negative feedback of users for the integration process visual elements based on the optimized user preference and visual element embedding matrices, identifying users associated with latent feature user preference values for one of the integration process visual elements falling within a preset range of each other as matching users, and transmitting identification of the matching users and identification of the one of the plurality of integration process visual ele

Abstract: Disclosed embodiments are directed to a collaboration model for software development that is driven by artificial intelligence (AI). In particular, an AI agent may provided as another member of a development team. The AI agent may utilize one or more generative AI models to synthesize a workflow model of a software entity to be developed, generate future state simulations of the software entity, and/or generate a project development timeline, including a sequence of well-defined agile sprints.

Abstract: Currently, partners of an integration platform as a service (iPaaS) platform must manually identify what solutions to build for the iPaaS platform. In an embodiment, a conversational artificial intelligence (AI) agent is used to perform an opportunity analysis that is capable of reducing the creative time, required for coming up with new solutions, from months to minutes. The opportunity analysis may acquire internal and/or external data, augment and/or clean that data, and apply a predictive model to the acquired data to predict software entities that would be beneficial to a computing environment. Clustering may be performed to identify software entities that are relevant to the partner, and those solutions may be filtered to a set of recommended non-existent software entities. These recommendations may be presented to the partner within the context of a real-time chat session with the AI agent.

Abstract: “Prevention is better than cure” aptly applies to the field of cybersecurity. However, state-of-the-art integration systems generally perform late-stage scanning that is reactive, rather than proactive. This can be particularly dangerous in a low-code environment, in which the integration processes may be constructed by novice users without expertise in mitigating cybersecurity threats. Accordingly, embodiments utilize artificial intelligence to proactively detect and resolve cybersecurity threats during the design stage of integration processes. For example, a generative model may be used with crowd-sourced integration configurations to generate synthetic integration data that are targeted towards specific cybersecurity threat endpoints. This synthetic integration data may be input to an integration process, during integration testing within a test environment, to detect and resolve cybersecurity threats, prior to deployment of the integration process to a production environment.

Abstract: It is difficult for an integration developer, especially a novice integration developer, to fully understand the impact of adding a new integration process to a runtime engine. Accordingly, disclosed embodiments may predict an impact of adding an integration process to a runtime engine using crowd-sourced historical data and generative artificial intelligence. Additional or alternative embodiments may determine a resolution to mitigate the impact of adding an integration process to a runtime engine, also using crowd-sourced historical data and generative artificial intelligence. This resolution may comprise one or more modifications to a configuration of the integration process and/or runtime engine, such as increasing the amount of a computational resource (e.g., processing power, memory, disk space, etc.) allocated to the runtime engine.

Abstract: An information handling system operating an integration connectivity sales facilitation system may comprise a display device displaying a request from a purchasing user to facilitate purchase of a product for sale by the selling user, a processor to automatically generate code instructions of a future data integration process for transferring a first dataset field value identified by a first dataset field name at a purchasing user to a second dataset field value identified by a second dataset field name at the selling user, based on a merged data lineage map for previously generated code instructions for transferring such first and second dataset field values to a common trading partner storage location identified by a common trading partner dataset field name, and a network interface device transmitting the code instructions for future execution and a runtime engine for execution at a remote location in deployment of the future data integration process.

Abstract: State-of-the-art Integration Platform as a Service (iPaaS) platforms do not enable users to utilize their own artificial intelligence (AI) models (e.g., large language models or other generative model). Disclosed embodiments enable users to bring your own model (BYOM) within an integration platform. In particular, users may build or import their own AI model, and integrate that AI model into their integration processes in the same manner as any other integration step. This may involve dragging a shape, representing the AI model, from a virtual palette onto a virtual canvas, and configuring the corresponding AI step. During execution, the resulting integration process may automatically and dynamically, in real time, receive input data and retrieve contextual metadata to enhance the input data with context. The combination of input data and contextual metadata may be provided to the AI step to perform the desired task with improved accuracy.

Abstract: Current agentic systems are unable to balance the costs of artificial intelligence (AI) agents with performance. Disclosed embodiments introduce a scoring AI agent, which scores deviations between the actual performance of a performing AI agent and the expected performance of the performing AI agent. When this deviation becomes substantial, the scoring AI agent may modify parameter(s) in an adaptive governance policy that governs operation of the performing AI agent. In this manner, an AI agent can be automatically throttled down and/or up, as real-time conditions evolve.

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: Existing platforms for developing artificial intelligence (AI) agents rely on static testing or limited real-world scenarios to evaluate agentic behavior. Accordingly, a simulator is disclosed that enables the simulation of an AI agent with adaptive test scenarios. During the simulation, a visualization interface may display a trace of the behavioral flow of the AI agent in real time. The simulator may also monitor and display one or more performance metrics and provide indications of the guardrail compliance of the AI agent in real time. A user may also pause, rewind, or modify the simulation in real time, to make immediate and real-time adjustments to the configuration of the AI agent.

Abstract: There is currently no tool for predicting the cost of performing an inference by an artificial intelligence (AI) agent. As a result, AI agents may easily end up exceeding economic, computational, energy, and/or ecological budgets. Disclosed embodiments utilize one or more AI agents to identify similar historical inputs to a prospective input, on which inference is to be performed, and predict an economic, computational, energy, and/or ecological cost of performing inference on the prospective input. If the cost would exceed a budget, the inference may be automatically blocked, at least temporarily, to prevent the budget from being exceeded.

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: There is no unified, comprehensive system for the governance of artificial intelligence (AI) agents. Accordingly, disclosed embodiments register a plurality of AI agents, potentially from disparate sources, into a centralized registry. Prior to activation, each AI agent is associated with a governance policy. After activation, each AI agent is monitored in real time, during execution, to determine whether or not the AI agent remains compliant with the associated governance policy. When an AI agent becomes non-compliant with the associated governance policy, corrective action may be taken, and the AI agent may be labeled as untrusted. The corrective action may comprise alerting a user, modifying the AI agent, adjusting an amount of each of one or more computational resources that is allocated to the AI agent, modifying an access of the AI agent to one or more systems, adjusting a communication control of the AI agent, and/or the like.

Abstract: Conventionally, artificial intelligence (AI) agents must be manually registered with platforms, which results in a lack of scalability, as the number of AI agents continues to surge into the millions and hundreds of millions, a lack of compatibility and standardization between agent specifications, and siloes of AI agents that cannot be combined into a unified registry. Accordingly, disclosed embodiments provide a AI-powered registration service that is capable of automatically registering AI agents, regardless of input format and regardless of the framework in which those AI agents are defined, using a standard agent schema, into a unified and centralized registry. In turn, this unified registry improves searching and discovery of AI agents.

Abstract: There is currently no protocol that enables artificial intelligence (AI) agents to autonomously select provider entities in a scalable, standardized, transparent manner, based on real-time conditions. In disclosed embodiments, provider entities autonomously register with a distributed ledger. Consumer AI agents may, when needing a new provider entity, autonomously query the distributed ledger and select a new provider entity. When selecting the new provider entity, a consumer AI agent may execute a negotiation protocol to obtain an optimal service agreement. In this manner, provider entities may autonomously onboard themselves, and AI agents may autonomously evolve, over time, to acquire new capabilities, by selecting new provider entities from an ever expanding universe of autonomously onboarded provider entities.