Rules engine for dynamic contextual routing to artificial intelligence models
The invention provides a rules engine that manages user requests within an interface integrating multiple AI platforms and AI Models. Upon receiving a query, the engine assigns scores based on factors like management rules, user preferences, and contextual information. Determinative scores, such as those enforcing strict enterprise policies, can override others, leading the engine to block or reroute the query. If no score is determinative, the engine forwards the query and associated prompts to a specialized routing AI Model for contextual analysis. Based on this analysis, the rules engine directs the query to the most appropriate AI Model or defaults to the user-designated AI Model. This system balances user intent with rule enforcement, optimizing query processing across various AI platforms while ensuring compliance with enterprise guidelines.
1. A method for routing a request to an appropriate artificial intelligence (“AI”) model, comprising:
receiving a first request from a user device, the first request including an identification of an intended AI model;
determining whether sending the first request to the intended AI model violates one or more management rules;
sending the first request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the intended AI model should handle the first request; and
in an instance in which sending the first request to the intended AI model violates the one or more management rules, or where the results from the routing AI model indicate that the first request should not be sent to the intended AI model, blocking the first request from being sent to the intended AI model.
2. The method of claim 1 , wherein the intended AI model is a managed AI model, and the results from the routing AI model indicate that the first request should be sent to a personal AI model, and the method further comprises:
determining whether sending the first request to the personal AI model violates the one or more management rules;
in an instance in which sending the first request to the personal AI model violates the one or more management rules, blocking the first request from being sent to the personal AI model; and
in an instance in which sending the first request to the personal AI model does not violate the one or more management rules, sending the first request to the personal AI model.
3. The method of claim 1 , wherein:
the results from the routing AI model include a confidence score,
the one or more management rules include a confidence score threshold, and
determining whether sending the first request to the intended AI model violates the one or more management rules includes comparing the confidence score to the confidence score threshold.
4. The method of claim 1 , further comprising:
receiving a second request from a second window, the second window being associated with a personal AI model;
determining whether sending the second request to the personal AI model violates one or more management rules;
sending the second request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the personal AI model should handle the second request; and
in an instance in which sending the second request to the personal AI model violates the one or more management rules, or where the results from the routing AI model indicate that the second request should not be sent to the personal AI model, blocking the second request from being sent to the personal AI model.
5. The method of claim 4 , wherein the results from the routing AI model indicate that the second request should be sent to a managed AI model, and the method further comprises:
determining whether sending the second request to the managed AI model violates one or more management rules;
in an instance in which sending the second request to the managed AI model violates one or more management rules, blocking the second request from being sent to the managed AI model; and
in an instance in which sending the second request to the managed AI model does not violate one or more management rules, sending the second request to the managed AI model.
6. The method of claim 1 , wherein the first request is sent to the routing AI model with prompts, the prompts comprising information selected from a group comprising:
a score based on the one or more management rules applied to the request;
a group or role specified in a user profile;
user preferences;
compliance and security status of the user device;
a designated purpose of each AI model available; and
historical user interaction data.
7. The method of claim 1 , wherein applying one or more management rules to the request includes retrieving security and compliance data from a management agent.
8. A non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, causes the processor to perform stages for routing a request to an appropriate artificial intelligence (“AI”) model, comprising:
receiving a first request from a user device, the first request including an identification of an intended AI model;
determining whether sending the first request to the intended AI model violates one or more management rules;
sending the first request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the intended AI model should handle the first request; and
in an instance in which sending the first request to the intended AI model violates the one or more management rules, or where the results from the routing AI model indicate that the first request should not be sent to the intended AI model, blocking the first request from being sent to the intended AI model.
9. The non-transitory, computer-readable medium of claim 8 , wherein the intended AI model is a managed AI model, and the results from the routing AI model indicate that the first request should be sent to a personal AI model, and the stages further comprising:
determining whether sending the first request to the personal AI model violates the one or more management rules;
in an instance in which sending the first request to the personal AI model violates the one or more management rules, blocking the first request from being sent to the personal AI model; and
in an instance in which sending the first request to the personal AI model does not violate the one or more management rules, sending the first request to the personal AI model.
10. The non-transitory, computer-readable medium of claim 8 , wherein:
the results from the routing AI model include a confidence score,
the one or more management rules include a confidence score threshold, and
determining whether sending the first request to the intended AI model violates the one or more management rules includes comparing the confidence score to the confidence score threshold.
11. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
receiving a second request from a second window, the second window being associated with a personal AI model;
determining whether sending the second request to the personal AI model violates one or more management rules;
sending the second request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the personal AI model should handle the second request; and
in an instance in which sending the second request to the personal AI model violates the one or more management rules, or where the results from the routing AI model indicate that the second request should not be sent to the personal AI model, blocking the second request from being sent to the personal AI model.
12. The non-transitory, computer-readable medium of claim 11 , wherein the results from the routing AI model indicate that the second request should be sent to a managed AI model, and the stages further comprise:
determining whether sending the second request to the managed AI model violates one or more management rules;
in an instance in which sending the second request to the managed AI model violates one or more management rules, blocking the second request from being sent to the managed AI model; and
in an instance in which sending the second request to the managed AI model does not violate one or more management rules, sending the second request to the managed AI model.
13. The non-transitory, computer-readable medium of claim 8 , wherein the first request is sent to the routing AI model with prompts, the prompts comprising information selected from a group comprising:
a score based on the one or more management rules applied to the request;
a group or role specified in a user profile;
user preferences;
compliance and security status of the user device;
a designated purpose of each AI model available; and
historical user interaction data.
14. The non-transitory, computer-readable medium of claim 8 , wherein applying one or more management rules to the request includes retrieving security and compliance data from a management agent.
15. A system for routing a request to an appropriate artificial intelligence (“AI”) model, comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions; and
at least one hardware-based processor that executes the instructions to carry out stages comprising:
receiving a first request from a user device, the first request including an identification of an intended AI model;
determining whether sending the first request to the intended AI model violates one or more management rules;
sending the first request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the intended AI model should handle the first request; and
in an instance in which sending the first request to the intended AI model violates the one or more management rules, or where the results from the routing AI model indicate that the first request should not be sent to the intended AI model, blocking the first request from being sent to the intended AI model.
16. The system of claim 15 , wherein the intended AI model is a managed AI model, and the results from the routing AI model indicate that the first request should be sent to a personal AI model, and the stages further comprising:
determining whether sending the first request to the personal AI model violates the one or more management rules;
in an instance in which sending the first request to the personal AI model violates the one or more management rules, blocking the first request from being sent to the personal AI model; and
in an instance in which sending the first request to the personal AI model does not violate the one or more management rules, sending the first request to the personal AI model.
17. The system of claim 15 , wherein:
the results from the routing AI model include a confidence score,
the one or more management rules include a confidence score threshold, and
determining whether sending the first request to the intended AI model violates the one or more management rules includes comparing the confidence score to the confidence score threshold.
18. The system of claim 15 , the stages further comprising:
receiving a second request from a second window, the second window being associated with a personal AI model;
determining whether sending the second request to the personal AI model violates one or more management rules;
sending the second request to a routing AI model for contextual analysis;
receiving results from the routing AI model, the results indicating whether the personal AI model should handle the second request; and
in an instance in which sending the second request to the personal AI model violates the one or more management rules, or where the results from the routing AI model indicate that the second request should not be sent to the personal AI model, blocking the second request from being sent to the personal AI model.
19. The system of claim 18 , wherein the results from the routing AI model indicate that the second request should be sent to a managed AI model, and the stages further comprise:
determining whether sending the second request to the managed AI model violates one or more management rules;
in an instance in which sending the second request to the managed AI model violates one or more management rules, blocking the second request from being sent to the managed AI model; and
in an instance in which sending the second request to the managed AI model does not violate one or more management rules, sending the second request to the managed AI model.
20. The system of claim 15 , wherein the first request is sent to the routing AI model with prompts, the prompts comprising information selected from a group comprising:
a score based on the one or more management rules applied to the request;
a group or role specified in a user profile;
user preferences;
compliance and security status of the user device;
a designated purpose of each AI model available; and
historical user interaction data.