Digital content generation with in-prompt hallucination management for conversational agent

1 . A method comprising:

determining a first state of a conversational system;

receiving at least one user input via a first agent of the conversational system, wherein a state graph is associated with the first agent;

providing a prompt associated with the first state to a first machine learning model, wherein the prompt comprises at least one instruction to cause the first machine learning model to (i) use at least the first state to generate first output comprising at least one second state and reasoning, wherein the at least one second state is generated by the first machine learning model using the first state and the reasoning comprises an explanation of how the first machine learning model generated the at least one second state, (ii) determine that a second state selected by the first machine learning model is associated with the first agent, (iii) initiate a transition to the second state associated with the first agent, and (iv) use the first output including the reasoning to generate second output;

receiving the second output generated using the first machine learning model and the prompt; and

providing at least two options for presentation via the conversational system, wherein the at least two options comprise digital content generated using the first machine learning model and the second output.

2 . The method of claim 1 , further comprising:

receiving a user selection of an option of the at least two options; and

providing the user selection of the option to the first machine learning model.

3 . The method of claim 1 , further comprising:

using a second machine learning model and the at least one user input, determining a user intent; and

using the user intent and the first machine learning model to determine the at least one second state.

4 . The method of claim 1 , further comprising:

using a second machine learning model and the at least one user input, determining a user intent;

using the user intent, a decision tree, and the first machine learning model to determine that the second state selected by the first machine learning model is associated with a second agent of the conversational system; and

initiating a transition from the first agent to the second agent.

5 . The method of claim 1 , further comprising:

using a second machine learning model and the at least one user input, determining a user intent; and

using the user intent, the state graph associated with the first agent, and the first machine learning model to determine that the second state selected by the first machine learning model is associated with the first agent.

6 . The method of claim 1 , wherein the first state comprises at least one input, at least one output, at least one operation capable of being performed by the first machine learning model using the at least one input, and at least one transition, wherein a transition identifies a second state of the conversational system.

7 . The method of claim 1 , wherein at least one of:

the first state is associated with a user input received via a job search interface of the conversational system;

the second output comprises a comparison of user credentials to job requirements; or

the at least two options are generated using the comparison of user credentials to job requirements.

8 . The method of claim 1 , wherein:

a user input comprises a selection of a first option associated with the first state, wherein the first option comprises natural language generated by the first machine learning model using at least the first state; and

the at least two options are generated using the selection of the first option.

9 . A system comprising:

at least one processor; and

at least one memory coupled to the at least one processor, wherein the at least one memory comprises at least one instruction that, when executed by the at least one processor, causes the at least one processor to be capable of performing at least one operation comprising:

determining a first state of a conversational system;

receiving at least one user input via a first agent of the conversational system, wherein a state graph is associated with the first agent;

providing a prompt associated with the first state to a first machine learning model, wherein the prompt comprises at least one instruction to cause the first machine learning model to (i) use at least the first state to generate first output comprising at least one second state and reasoning, wherein the at least one second state is generated by the first machine learning model using the first state and the reasoning comprises an explanation of how the first machine learning model generated the at least one second state, (ii) determine that a second state selected by the first machine learning model is associated with the first agent, (iii) initiate a transition to the second state associated with the first agent, and (iv) use the first output including the reasoning to generate second output;

receiving the second output generated using the first machine learning model and the prompt; and

providing at least two options for presentation via the conversational system, wherein the at least two options comprise digital content generated using the first machine learning model and the second output.

10 . The system of claim 9 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to be capable of performing at least one operation further comprising:

using a second machine learning model and the at least one user input, determining a user intent;

using the user intent, a decision tree, and the first machine learning model to determine that the second state selected by the first machine learning model is associated with a second agent of the conversational system; and

initiating a transition from the first agent to the second agent.

11 . The system of claim 9 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to be capable of performing at least one operation further comprising:

using a second machine learning model and the at least one user input, determining a user intent; and

using the user intent and the first machine learning model to determine the at least one second state.

12 . The system of claim 9 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to be capable of performing at least one operation further comprising:

using a second machine learning model and the at least one user input, determining a user intent; and

using the user intent, the state graph associated with the first agent, and the first machine learning model to determine that the second state selected by the first machine learning model is associated with the first agent.

13 . The system of claim 9 , wherein the first state comprises at least one input, at least one output, at least one operation to be performed by the first machine learning model using the at least one input, and at least one transition, wherein a transition identifies a second state of the conversational system.

14 . The system of claim 9 , wherein at least one of:

the first state is associated with a user input received via a job search interface of the conversational system;

the second output comprises a comparison of user credentials to job requirements; or

the at least two options are generated using the comparison of user credentials to job requirements.

15 . The system of claim 9 , wherein:

a user input comprises a selection of a first option associated with the first state, wherein the first option comprises natural language generated by the first machine learning model using at least the first state; and

the at least two options are generated using the selection of the first option.

16 . At least one non-transitory machine-readable storage medium comprising at least one instruction that, when executed by at least one, causes at least one processor to:

determine a first state of a conversational system;

receive at least one user input via a first agent of the conversational system, wherein a state graph is associated with the first agent;

provide a prompt associated with the first state to a first machine learning model, wherein the prompt comprises at least one instruction to cause the first machine learning model to (i) use at least the first state to generate first output comprising at least one second state and reasoning, wherein the at least one second state is generated by the first machine learning model using the first state and the reasoning comprises an explanation of how the first machine learning model generated the at least one second state, (ii) determine that a second state selected by the first machine learning model is associated with the first agent, (iii) initiate a transition to the second state associated with the first agent, and (iv) use the first output including the reasoning to generate second output;

receive the second output generated using the first machine learning model and the prompt; and

provide at least two options for presentation via the conversational system, wherein the at least two options comprise digital content generated using the first machine learning model and the second output.

17 . The at least one non-transitory machine-readable storage medium of claim 16 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to:

use a second machine learning model and the at least one user input to determine a user intent;

use the user intent, a state graph associated with the first agent, and the first machine learning model, determining that the second state selected by the first machine learning model is associated with the first agent; and

initiating a transition to the second state associated with the first agent.

18 . The at least one non-transitory machine-readable storage medium of claim 16 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to:

use a second machine learning model and the at least one user input, determining a user intent;

use the user intent, a decision tree, and the first machine learning model to determine that the second state selected by the first machine learning model is associated with a second agent of the conversational system; and

initiate a transition from the first agent to the second agent.

19 . The at least one non-transitory machine-readable storage medium of claim 16 , wherein:

a user input comprises a selection of a first option associated with the first state, wherein the first option comprises natural language generated by the first machine learning model using at least the first state; and

the at least two options are generated using the selection of the first option.

20 . The at least one non-transitory machine-readable storage medium of claim 16 , wherein the at least one instruction, when executed by the at least one processor, causes the at least one processor to:

use a second machine learning model and the at least one user input to determine a user intent; and use the user intent and the first machine learning model to determine the at least one second state.