Airia Ltd.

Gregory Roberts

Erich Stuntebeck

John Manton

Roman Fedoruk

Spencer Reagan

Ravish Chawla

William Dewesse

Systems and methods are described for comparing execution of two or more artificial intelligence (AI) pipelines. A platform can provide a user interface (UI) that allows for selection or creation of multiple AI pipelines. The AI pipelines can utilize different pipeline objects, such as different prompts, datasets, or models. The AI pipelines can be displayed on a single UI screen, where execution of the AI pipelines is simultaneously simulated. The same inputs can be provided to the multiple AI pipelines, and the corresponding outputs can display on screen. The platform can also vectorize and compare the semantic similarity of the outputs, presenting an indicating of the semantic similarity on the same UI screen.

Simultaneous simulated execution and semantic evaluation of artificial intelligence pipelines

Systems and methods are described for tool discovery and ingestion for artificial intelligence ('AI') agents. An AI platform can discover a first tool specification that includes an action and a description. The first tool specification is ingested to create a first tool object. The first tool object includes the action and an endpoint. Tool labels are determined from the specification and applied to the first tool object. A user interface displays the tool object, and it is added to an AI agent. The AI agent includes a manifest file that is used to execute the AI agent. This includes determining whether the AI agent is authorized to perform the action, and providing the AI agent with access to a tool credential, wherein the tool credential is sent to the endpoint.

Automated tool discovery and ingestion for artificial intelligence agents

Systems and methods are described for dynamic execution of artificial intelligence ('AI') agents. A server can receive, from a client device, an input associated with an AI agent. Based on a manifest file or user profile, the server can identify a management policy that applies to the AI agent. The server then dynamically configures access to the agent objects based on applying the management policy. The management policy is applied to a device status of the client device, a user profile of a user of the client device, and/or a network configuration of the client device. The server then executes a modified workflow based on the dynamically configured access, wherein the modified workflow bypasses or changes operation of at least one of the agent objects. Based on the modified workflow, the server transmits an output to the client device.

Dynamic execution of artificial intelligence agents through device management

Systems and methods are described for building artificial intelligence ('AI') agents. A server can provide a user interface (UI) that includes options to select and connect various agent objects. The agent objects can include prompt objects, dataset objects, model objects, and one or more code objects. A subset of the agent objects can be identified as available for selection based on evaluation of at least one management policy associated with an administrative user. A manifest file is generated based on the connected agent objects, and the manifest is validated against dependency rules to ensure that the stages of the agent meet prerequisites for the stages. Then, the server performs a simulated execution of an agent that corresponds to the validated manifest file, including an identification of at least one execution metric associated with the simulated execution.

Managed design and generation of artificial intelligence agents

Systems and methods are described for providing multitenancy in an artificial intelligence (AI) platform. The platform can provide a user interface (UI) that allows for creation of an organization, tenants within that organization, and groups within tenants. This hierarchy can dictate resource permissions that impact which AI pipelines and AI pipeline objects are available to a user. The different tenants can have segregated data and utilize different pipeline objects, such as different prompts, datasets, or models. A marketplace UI can prioritize additional marketplace pipelines for approval and inclusion with the tenant.

Controlling access to resources in a multi-tenant artificial intelligence pipeline platform

Systems and methods are described for building artificial intelligence ('AI') pipelines. A user interface (UI) includes selectable pipeline objects, such as a dataset and an AI model, that a user can position and connect on the screen. This causes execution linking between the selected pipeline objects, with the execution linking being visually displayed in the UI. A management policy can be applied to the pipeline, including user or device requirements for accessing the dataset in the pipeline. Then the UI can present a simulated execution of the AI pipeline, in which a test query is input and the pipeline objects execute in an order displayed in the UI. The pipeline can then be deployed for access at an endpoint.

Building and simulating execution of managed artificial intelligence pipelines

Systems and methods are described for a managed multidimensional search based on an application query and management policies. The application can receive a pipeline endpoint. The query can be sent to the pipeline endpoint. The pipeline can vectorize the query for comparison against a vector database of an identified dataset. The closest vectors can be converted back to content chunks. The system can generate prompts related to the content chunks and send those prompts to an AI model. The AI model can then output a response that includes the most relevant content, citations, and hyperlinks. These can be displayed in the application.

Growing community of inventors

Alpharetta, GA, United States of America

Gregory Roberts