UNGRIA Patentes y Marcas, S.A.

A method is provided. The method is performed by a hyper-automation system performing agentic automations. The hyper-automation system include a memory storing for the agentic automations and for agent health score generation. The hyper-automation system include at least one processor executing the computer code to cause the method to optimize the agentic automations. The method includes generating a set of standardized metrics for application to an agent executing agentic automations. The method includes performing an evaluation of the agent executing the agentic automations that determines performance metrics by measuring success rates, error frequencies, and execution efficiency for different use cases or business processes. The method includes comparing the performance metrics across different use cases or business processes for the agent. The method includes generating agent health scores based on comparing the performance metrics and agent health score definitions.

A computer-implemented system and method for AI observability, distributed tracing, and privacy-preserving monitoring in Al-driven environments. The system assigns a unique trace identifier to Al-generated requests, enabling seamless tracking across multiple AI processing components. Al logs are enriched with structured metadata, including model execution parameters, inference confidence scores, and processing timestamps, to facilitate trace-to-log correlation. A federated trace management system ensures trace data is distributed across multiple storage locations while enforcing jurisdiction-based compliance regulations. To enhance privacy, the system applies privacy-preserving transformations, such as redaction, tokenization, and homomorphic encryption, preventing exposure of personally identifiable information (Pll) in trace logs. The invention enables scalable Al observability with minimal performance overhead by implementing dynamic trace segmentation policies, selective sampling techniques, and cryptographic trace linking.

The present invention relates to a hypohalite bleach composition, preferably hypochlorite, comprising phenoxypropanol as corrosion inhibitor, which exhibits good stability. It relates also to the use of said formulation, to a process of treating a surface with said composition, and to the use of phenoxypropanol as corrosion inhibitor in hypohalite bleach compositions.

Systems and methods are provided for autonomously and semi-autonomously generating and executing automated test scripts from user stories using an Al-driven architecture. An AI agent receives user stories and associated acceptance criteria from one or more data sources. A reasoning engine processes the user stories to extract test scenarios and generates structured representations of the scenarios. An actuator module translates the scenarios into executable automated test scripts and autonomously integrates the scripts into continuous integration and delivery (CI/CD) pipelines. The actuator may further provision test environments, execute the automated test scripts, and collect telemetry, including execution results and system metrics. Optional embodiments include multi-agent configurations, replay mechanisms, escalation modules, and sandbox environments for semi-autonomous operation. The system supports deployment across cloud-native, on-premises, and hybrid infrastructures, providing a scalable solution for Al-driven continuous testing in enterprise software development environments.

The present invention relates to a forming device, configured to be coupled to a container forming machine, said forming device comprising forming means and displacement means, coupled to each other by connecting means. Likewise, the present invention relates to a container forming machine, comprising such a forming device.Thus, the present invention relates to the connecting means between the very elements of a forming device, which is configured to form containers, as well as a container forming machine, preferably forming cardboard containers, which forming device is configured like that of the present invention.

The ejection system for the laminated material stacker allows the position of retractable guides (5), which are the elements that secure the position of the laminates when they are released, to be adjusted so as to reduce the distance between vacuum assemblies and a pallet/laminates that have already been stacked. The system further comprises a plurality of vacuum assemblies that can be moved towards or away from each other, adapting to the width of the laminates of laminated material entering the system.

Systems and methods for optimizing at least one of a process or an Al (artificial intelligence) agent are provided. The process and the Al agent are executed on one or more computing systems for performing a task. A visual representation of the execution of the process and the Al agent is generated. At least one of the process or the Al agent is optimized based on the visual representation. The optimized at least one of the process or the Al agent is output.

A method is provided. The method is implemented by a hyper-automation system including processors executing computer code for agentic automations and an artificial intelligence trust layer and a memory storing the computer code. The method includes initially setting guardrails for an agent within the artificial intelligence trust layer of the hyper-automation system. The method includes operating the agent according to the guardrails to implement a workflow of the agentic automations including an action. The guardrails define a scope of the agent to control the operation of the agent as the agent implements action.

Frameworks and agentic loops for auto-generating tools and/or building artificial intelligence (AI) agents using tools are disclosed. The agentic loops may be represented in Business Process Model and Notation (BPMN) or any other desired workflow language. The tools can be implemented as static, invocation-specific, or dynamic caller-side or server-side tools. The tools may not be defined at all, may only be abstractly defined, or may be entirely defined within an Al agent definition. The implementation of these tools can be injected as part of the agentic process. The Al agent that implements these tools may also build other Al agents that can leverage the caller-side and server-side tools.

Systems and methods for evaluating computer security issues of a computer system are provided. An alert for a computer security issue of a computer system is received. An initial AI (artificial intelligence) agent determines 1) a strategy for evaluating the computer security issue and 2) one or more additional AI agents from a pool of AI agents for evaluating the computer security issue. The computer security issue is evaluated according to the strategy using the one or more additional AI agents. Results of the evaluation of the computer security issue are output.