Abstract: The present technology, roughly described, provides for mocking an application program interface (API) using a large language model (LLM). The present system generates a prompt with API signature information and API desired behavior information. The prompt can include instructions, library functions, examples, executed programs, and a current function invocation, as well as other content. The prompt can be generated, and submitted to an LLM to mock an API and generate a response. The response can be audited and the LLM can be fine tuned to provide improved performance in subsequent calls.

Abstract: A system automatically imputes automated agent decision logic. An interaction record is used with other data to determine an optimal and efficient logical path from a starting point in an interaction record to the end of the interaction record between an automated agent and a client. The logical path can be determined using a process that works backward, from the end point to the starting point, to determine the optimal path. Once complete, the resulting interaction record is supplemented with additional information regarding what states and/or steps were taken in the agent architecture specification to navigate through the interaction record.

Abstract: A system provides a language model that utilizes an optimized parser and operates at the byte- level in a context free grammar (CFG) and a tokenizer vocabulary. The CFG is constrained and automatically transformed to a byte-level grammar. A prediction mechanism is used to predict the allowed sequences of bytes that can appear after a given prefix. In some instances, only the next token is constrained so that candidates for the next token can be intersected with tokens in the tokenizer vocabulary. To achieve this, lattice parsing is performed using a finite state automaton (FSA) that is generated and then minimized.

Abstract: A system provides a rapid, interactive utility for rendering and optimizing a prompt for input into an LLM. A user interface allows a user to select and modify several prompt parameters, including but not limited to prompt format, selecting external content that can be dynamically retrieved, style of mark-up, and other aspects of a prompt. The utility renders a prompt based on user selection and modification of the parameters. The dynamic content within the prompt can include instructions for performing a task and examples of previous input data (e.g., prompts) and desired outputs by an LLM. Once an output is provided by an LLM in response to a rendered prompt, the prompt and output can be evaluated against one or more examples of similar prompts and high scoring outputs. The current prompt can then be optimized based on the evaluation to improve evaluation score metrics for the prompt.

Abstract: The present technology, roughly described, generates grammars, such as context free grammars, dynamically and by induction, that can specify constraints for a decoding system. The grammar can be created to support an automated agent involved in an interaction (e.g., a conversation) with a client. In some instances, grammars can be generated dynamically based on copying portions of an interaction history and based on business logic rules. Grammars can also be induced automatically from API specifications and collections of strings. The newly generated context free grammars can be used by a language model to perform constrained decoding.

Abstract: The system provides improved controls for an automated agent by generating a declarative specification for an automated agent. The declarative specification is generated based at least in part from previous conversation data associated with interactions between an automated agent and a customer. The policies may include general policies and specific policies. A general policy is one that is applied to all automated agents. After creating the declarative specification, an automated agent can interact with a customer in an interaction based on the specification. The automated agent responses are evaluated based on checklists associated with the policies to determine if a response was proper.

Abstract: A system that generates relevant and vetted training data using intelligent simulated users and evaluation of conversation data. A simulated user and an automated agent engage in a conversation to generate conversation and/or interaction data. The simulated user is guided by scenarios which are generated based on one or more controls to be followed by the automated agent. Using a simulated user driven by control-derived scenarios ensures the ensuing conversation data is relevant to the desired scope of operation for the automated agent. The conversation data is evaluated based on the controls to confirm the automated agent actions and responses followed the controls properly. Evaluating the conversation data based on the controls ensures that conversation data associated with properly followed controls is used as subsequent training data.

Abstract: A system providing a state-driven automated agent. The state machine can include multiple nested state machines to receive, process, and generate responses to a user inquiry received through a chat application. The state machine has a plurality of states, and navigates between states based on one or more machine learning (ML) models. In some instances, each state is associated with a machine learning model that can predict what state the state machine should transition to from its current state. The machine learning model(s) can be implemented using one or more large language models (LLM). The state-driven automated agent includes an auditing state that analyzes a predicted response to a user inquiry and identifies errors with the response. The errors may be identified and automatically self-corrected.

Abstract: A system for providing and managing an automated agent. The automated agent may interact with a customer and utilize rules and instructions to determine a response to the customer and actions to perform. The customer interactions by the automated agent are driven by a set and/or subset of instructions that can be analyzed before each automated agent response or action. The subset of instructions, customer conversational input, and other content can be processed by a machine learning model, which may be implemented as a large language model (LLM).

Abstract: A system for generating instructions based on part from human training materials, wherein the generated instructions are used to train automated agents. The training materials may include training manuals, knowledge-base documents, articles, and other content. The training materials are processed and converted to a format that is digestible by a machine learning model. The processed training materials can be submitted as a prompt, along with role information and prompt instruction information. The prompt instructions provided with the role and training materials may direct the machine learning model to find relevant generated instructions from the provided training materials. The machine learning model processes the prompt and outputs extracted instructions from the content. The instruction document may be stored in a vector database for later use.

Abstract: An example operation may include one or more of assigning a fractional ownership of a transport, receiving, at a server, sensor data associated with one or more of the transport and a device proximate to the transport, determining a condition of the transport, based on the sensor data, updating the fractional ownership of the transport based on the condition, and providing a responsibility based on the fractional ownership.

Abstract: Methods, systems, and devices for a cross-linked distributed ledger. The cross-referencing system includes multiple computing devices including a first computing device and a second computing device. A computing device of the multiple computing devices is configured to maintain a first cross-linked distributed ledger. The first cross-linked distributed ledger has a first set of multiple linked records that are associated with a first identifier. The first computing device includes a processor. The processor is configured to link or provide a first record associated with the first identifier to the first cross-linked distributed ledger. The first record has a first reference to a second record. The second record is within a second set of multiple cross-linked records of a second cross-linked distributed ledger.

Abstract: An example operation may include one or more of applying a user profile to one or more transports and a transport management database, monitoring user requirements and user usage of the one or more transports over a period of time, identifying a plurality of transport profiles stored in a transport availability pool of the transport management database, identifying a proposed fractional ownership of one or more of a plurality of transports identified in the transport availability pool based on the monitored user requirements and user usage of the one or more transports, and providing the proposed fractional ownership of the one or more of a plurality of transports identified in the transport availability pool to a user device associated with the user.

Abstract: Methods and systems for managing access to a data location associated with a vehicle. The method includes detecting, by one or more sensors of the vehicle, vehicle data. The method also includes recording, by an electronic control unit (ECU) of the vehicle, the vehicle data to the data location. The method also includes storing, by a smart contract located on a blockchain, an access state associated with the data location, the access state indicating one or more devices having access to the data location. The method also includes communicating, by the ECU, an instruction to the smart contract to change the access state associated with the data location to grant access to a third-party device or revoke access from the third-party device.

Abstract: An example operation may include one or more of applying a user profile to one or more transports and a transport management database, monitoring user requirements and user usage of the one or more transports over a period of time, identifying a plurality of transport profiles stored in a transport availability pool of the transport management database, identifying a proposed fractional ownership of one or more of a plurality of transports identified in the transport availability pool based on the monitored user requirements and user usage of the one or more transports, and providing the proposed fractional ownership of the one or more of a plurality of transports identified in the transport availability pool to a user device associated with the user.

Abstract: An example operation may include one or more of assigning a fractional ownership of a transport, receiving, at a server, sensor data associated with one or more of the transport and a device proximate to the transport, determining a condition of the transport, based on the sensor data, updating the fractional ownership of the transport based on the condition, and providing a responsibility based on the fractional ownership.

Abstract: An example operation may include one or more of receiving, at a server, a request for a service associated with a transport, the request including an identifier associated with a first user and the transport, and authorizing, by the server, the service when the transport and a device associated with a second user are proximate to an object that provides the service.

Abstract: An example operation may include one or more of monitoring a transport for a condition level status, determining one or more subsequent destination areas for the transport based on a current route, determining a minimum period of time and a service type required to increase the condition level status, identifying one or more service locations for the transport based on the condition status level, the service type and the one or more subsequent destination areas, wherein the one or more service locations have an availability to accommodate the transport for the minimum period of time, and forwarding an updated route to the transport comprising the one or more subsequent destination areas and the one or more service locations.

Abstract: Methods, systems, and devices for a cross-linked distributed ledger. The cross-referencing system includes multiple computing devices including a first computing device and a second computing device. A computing device of the multiple computing devices is configured to maintain a first cross-linked distributed ledger. The first cross-linked distributed ledger has a first set of multiple linked records that are associated with a first identifier. The first computing device includes a processor. The processor is configured to link or provide a first record associated with the first identifier to the first cross-linked distributed ledger. The first record has a first reference to a second record. The second record is within a second set of multiple cross-linked records of a second cross-linked distributed ledger.