Abstract: Techniques are described herein for using artificial intelligence (AI) and machine learning (ML) to automate, accelerate, and enhance various aspects of comparative user experience testing. Embodiments interface with generative language models to compare user experiences and summarize the results of the comparison. In some embodiments, automated systems and programmatic processes access a series of analysis contexts, where a context includes a collection of message content fragments. The systems and processes may use the message content fragments for a given context to construct a dialogue with a generative language model to compare separate user experiences based on the results of a set of user experience tests. The output of the generative language model at one stage of the analysis may be combined with content fragments for another context to craft a dialogue at another stage of the analysis and/or to perform additional analyses of the user experiences.

Abstract: One or more embodiments relate to a method for refining usability testing through the systematic collection and analysis of user click paths within an online interface. By tracking and filtering these click paths based on one or both of publicly observable attributes and non-publicly observable attributes, obtained in part through user responses to screening questions, the method generates distinct, aggregated click paths. These paths are then subjected to in-depth analysis that yields insights and metrics regarding user behavior and usability. Some embodiments further extend to the presentation of an interactive representation of these paths within a testing interface that allows researchers to explore and extract actionable findings.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience (UX) tests. In some embodiments, a system receives input defining or modifying a theme schema for classifying results of user experience tests. Responsive to receiving the input, the system trains a themer model based at least in part on example classifications in a training dataset, where the classifications map results to themes within the theme schema. When a new set of results for a user experience test is received, the trained machine learning model may generate a set of predicted themes to classify the test results. The output of the model may be used to render user interfaces and/or trigger other actions directed to optimizing a product's design.

Abstract: Techniques for machine-learning of long-term seasonal patterns are disclosed. In some embodiments, a network service receives a set of time-series data that tracks metric values of at least one computing resource over time. Responsive to receiving the time-series data, the network service detects a subset of metric values that are outliers and associated with a plurality of timestamps. The network service maps the plurality of timestamps to one or more encodings of at least one encoding space that defines a plurality of encodings for different seasonal patterns. Based on the mapped encodings, the network service generates a representation of a seasonal pattern. Based on the representation of the seasonal pattern, the network service may perform one or more operations in association with the at least one computing resource.

Abstract: Techniques are described herein for testing and characterizing user experiences with digital assets. Embodiments include a digital experience testing system for running usability tests with respect to user interface designs. The runtime testing environment may use a set of one or more compiled prototypes to test various facets of a user experience including what respondents do when interacting with a digital asset and how the experience engages the respondents' emotions. The digital experience testing system may analyze, enrich, synthesize, and/or otherwise process the results of one or more usability tests, based on the tracked user interactions, to provide guidance on user interface design optimizations.

Abstract: Techniques for artificial intelligence driven configuration management are described herein. In some embodiments, a machine-learning process determines a feature set for a plurality of deployments of a software resource. Based on varying values in the feature set, the process clusters each of the plurality of deployments into a cluster of a plurality of clusters. Each cluster of the plurality of clusters comprises one or more nodes and each node of the one or more nodes corresponds to at least a subset of values of the feature set that are detected in at least one deployment of the plurality of deployments of the software resource. The process determines a representative node for each cluster of the plurality of clusters. An operation may be performed based on the representative node for at least one cluster.

Abstract: Operations of a prompt management system are disclosed. The operations may include: receiving a prompt for performing a set of tasks, assigning an agent group that includes a plurality of agents to perform a set of roles associated with a dataset in support of the set of tasks, causing the plurality of agents to perform the set of roles using a first machine-learning model, receiving a set of role results from the plurality of agents responsive to performing the set of roles, performing the set of tasks using at least a second machine-learning model, and providing a task result for display on a user interface device. The set of tasks may include executing an operation on the set of role results using the second machine-learning model, and generating a task result that includes a product of the operation executed on the set of role results.

Abstract: Techniques are described for producing machine-generating findings associated with user experiences with products and/or services. In some embodiments, a finding generator receives a set of user experience test results, generates a set of permutations of user attribute values, and, for each permutation, determines distributions of quantitative values that measure one or more facets of the user experience with a product or service for users that have the user attribute values and users that do not. Based on a comparison of the distributions, the finding generator identifies a subset of permutations to retain, generates segments of user experience test results based on the permutations, and generates findings summaries based on the results included in each segment. The findings may be presented to an analyst and or consumed by downstream application to perform actions directed at improving the design of the product or service.

Abstract: Operations of a prompt management system are disclosed. The operations may include: receiving a prompt for performing a set of tasks, assigning an agent group that includes a plurality of agents to perform a set of roles associated with a dataset in support of the set of tasks, causing the plurality of agents to perform the set of roles using a first machine-learning model, receiving a set of role results from the plurality of agents responsive to performing the set of roles, performing the set of tasks using at least a second machine-learning model, and providing a task result for display on a user interface device. The set of tasks may include executing an operation on the set of role results using the second machine-learning model, and generating a task result that includes a product of the operation executed on the set of role results.

Abstract: Techniques are described herein for using artificial intelligence (AI) and machine learning (ML) to automate, accelerate, and enhance various aspects of user experience testing. Embodiments incorporate generative language models into user experience testing applications to extract key findings for improving product designs and driving product optimizations. In some embodiments, programmatic processes conduct a dialogue with a generative language model by engineering a set of input prompts as a function of prompt fragments, user experience test results, and test contexts. The AI-generated findings may drive actions directed to optimizing product designs and improving user experiences.

Abstract: Techniques are described herein for using artificial intelligence (AI) and machine learning (ML) to automate, accelerate, and enhance various aspects of comparative user experience testing. Embodiments interface with generative language models to compare user experiences and summarize the results of the comparison. In some embodiments, automated systems and programmatic processes access a series of analysis contexts, where a context includes a collection of message content fragments. The systems and processes may use the message content fragments for a given context to construct a dialogue with a generative language model to compare separate user experiences based on the results of a set of user experience tests. The output of the generative language model at one stage of the analysis may be combined with content fragments for another context to craft a dialogue at another stage of the analysis and/or to perform additional analyses of the user experiences.

Abstract: Techniques are described herein for producing machine-generated findings given a set of user experience test results. In some embodiments, the system generates the findings using an artificial intelligence and machine learning engine. The findings may highlight areas that are predicted to provide the most insight into optimizing a product's design. A finding may be generated based on all or a subset of the test result elements, including qualitative and/or quantitative data contained therein. A finding may summarize a subset of the UX test results that are interrelated. A finding may link a summary to one or more references extracted from the set of test results to show support for the machine-generated insights in the underlying raw test data. Machine-generated findings reports may provide near instantaneous guidance for optimizing product designs while removing extraneous information from a vast quantity of raw test result data.

Abstract: Techniques and embodiments described herein include a scalable system for integrating panel-based research with user experience (UX) testing tools, such as online survey applications. The techniques provide for the parallelization of a single request across multiple panel providers. The parallelization across multiple panel providers may occur transparently to users, including the designers of UX testing tools and methodologies, without requiring any complex modifications of the underlying source code. The parallelization may further significantly reduce request processing speeds within the system. Additionally or alternatively, the techniques provide for runtime adjustments of configurations to adjust rates at which respondents with varying attributes are fielded. As a result, qualified UX test respondents may be fielded much more quickly, increasing system scalability by allowing the system to process more requests within a given timeframe.

Abstract: Techniques are described herein for using artificial intelligence to select, curate, normalize, enrich, and synthesize the results of user experience (UX) tests. In some embodiments, a system identifies a set of unstructured textual elements associated with one or more UX tests. The system may configure agents using generative language model services, including a reviewing agent that reviews and edit outputs of a machine learning classification model applied to the unstructured textual elements and/or a curating agent that selects unstructured textual elements to represent themes within the user experience test classified using the machine learning classification model. The outputs may be used to enhance the scalability, function, and efficiency of applications directed at improving product designs.

Abstract: Techniques for machine-learning of long-term seasonal patterns are disclosed. In some embodiments, a network service receives a set of time-series data that tracks metric values of at least one computing resource over time. Responsive to receiving the time-series data, the network service detects a subset of metric values that are outliers and associated with a plurality of timestamps. The network service maps the plurality of timestamps to one or more encodings of at least one encoding space that defines a plurality of encodings for different seasonal patterns. Based on the mapped encodings, the network service generates a representation of a seasonal pattern. Based on the representation of the seasonal pattern, the network service may perform one or more operations in association with the at least one computing resource.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience (UX) tests. In some embodiments, a system receives input defining or modifying a theme schema for classifying results of user experience tests. Responsive to receiving the input, the system trains a themer model based at least in part on example classifications in a training dataset, where the classifications map results to themes within the theme schema. When a new set of results for a user experience test is received, the trained machine learning model may generate a set of predicted themes to classify the test results. The output of the model may be used to render user interfaces and/or trigger other actions directed to optimizing a product's design.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience (UX) tests. In some embodiments, a system identifies a set of expectation elements associated with one or more UX tests. An expectation element may specify, using unstructured data that does not conform to a schema, an expectation for a user experience and a respective outcome for the user experience. A themer model may generate predictions that map the respective expectation elements to a theme from a theme schema, which may include a plurality of themes. A selector model may generate selection scores for the expectation elements. The predicted themes and selection scores may be used to render user interfaces and/or trigger other actions directed to optimizing a product's design.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience (UX) tests. In some embodiments, a system receives input defining or modifying a theme schema for classifying results of user experience tests. Responsive to receiving the input, the system trains a themer model based at least in part on example classifications in a training dataset, where the classifications map results to themes within the theme schema. When a new set of results for a user experience test is received, the trained machine learning model may generate a set of predicted themes to classify the test results. The output of the model may be used to render user interfaces and/or trigger other actions directed to optimizing a product's design.

Abstract: Techniques and embodiments are described herein for detecting and mitigating fraudulent activity within user experience (UX) test applications. In some embodiments, a system applies a set of rules and/or machine learning (ML) models to each respondent of an online survey or UX test. Different ML models may be trained to learn domain-specific patterns indicative of fraudulent activity. The system may then select the ML models based on attributes of the UX test and/or respondent. The selected rules and/or ML models may generate a probabilistic score representing a likelihood that the respondent is currently engaging in or will engage in fraudulent activity with respect to a UX test. If the score exceeds a threshold, then the system may take action to mitigate the fraudulent activity, such as triggering the removal of the user from an accepted respondent pool, halting further engagement between the respondent and the UX test, and generating alerts.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience tests. In some embodiments, a system identifies a qualitative element within a result set for a user experience test. The system then selects a machine learning model to apply based on one or more attributes associated with the user experience test and generates a predicted visibility, quality, and/or relevance for the qualitative element. Based on the prediction, the system generates a user interface that curates a set of results of the user experience test.