Flexible artificial intelligence agent infrastructure for adapting processing of a shell
A computer system adapts processing of expressions by a command-line interface. An expression provided to the command-line interface is analyzed, wherein the command line interface includes pre-defined expression processing. One or more artificial intelligence agents are selected from a plurality of artificial intelligence agents based on the analysis of the expression. The expression is evaluated by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing. The expression is processed in accordance with the determined processing modifications and results are provided to the command-line interface. Embodiments of the present invention further include a method and program product for adapting processing of expressions by a shell in substantially the same manner described above.
1. A computer-implemented method for adapting processing of expressions by a command-line interface, the computer-implemented method comprising:
analyzing an expression provided to the command-line interface by a user, wherein the command-line interface includes pre-defined expression processing;
selecting one or more artificial intelligence agents of a plurality of artificial intelligence agents based on the analysis of the expression, wherein each artificial intelligence agent comprises a particular machine learning model trained to modify processing of expressions provided to the command-line interface, wherein each of the plurality of artificial intelligence agents are trained to perform a different functionality from a group of: an error-correcting feature, a natural language processing feature, an automated troubleshooting feature, an expression sequence automation feature, and a user feedback feature, and wherein the one or more artificial intelligence agents are selected by:
processing the expression with the plurality of artificial intelligence agents to indicate a confidence score for a decision of each artificial intelligence agent of the plurality of artificial intelligence agents; and
selecting the one or more artificial intelligence agents based on the indicated confidence scores;
evaluating the expression by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing; and
processing the expression in accordance with the determined processing modifications and providing results to the command-line interface.
2. The computer-implemented method of claim 1 , wherein an artificial intelligence agent of the plurality of artificial intelligence agents provides the expression to the command-line interface, and further comprising:
adjusting the artificial intelligence agent based on the processing of the expression in accordance with the determined processing modifications.
3. The computer-implemented method of claim 1 , further comprising: analyzing one or more percepts captured from a computing device associated with the command-line interface to select the one or more artificial intelligence agents.
4. The computer-implemented method of claim 3 , further comprising: analyzing the one or more percepts with the selected one or more artificial intelligence agents to determine the processing modifications.
5. The computer-implemented method of claim 1 , wherein selecting the one or more artificial intelligence agents is further based on an identity of the user.
6. The computer-implemented method of claim 1 , wherein the one or more artificial intelligence agents are selected by an orchestration layer, and further comprising:
in response to processing the expression and providing the results to the command-line interface, obtaining feedback from a computing device associated with the command-line interface; and
processing the feedback to indicate a modification to one or more of: the orchestration layer, and an artificial intelligence agent of the plurality of artificial intelligence agents.
7. The computer-implemented method of claim 6 , wherein the feedback is based on one or more from a group of: user-provided feedback, and feedback based on user actions performed subsequent to providing the results to the command-line interface.
8. A computer system for adapting processing of expressions by a command-line interface, the computer system comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising instructions to:
analyze an expression provided to the command-line interface by a user, wherein the command-line interface includes pre-defined expression processing;
select one or more artificial intelligence agents of a plurality of artificial intelligence agents based on the analysis of the expression, wherein each artificial intelligence agent comprises a particular machine learning model trained to modify processing of expressions provided to the command-line interface, wherein each of the plurality of artificial intelligence agents are trained to perform a different functionality from a group of: an error-correcting feature, a natural language processing feature, an automated troubleshooting feature, an expression sequence automation feature, and a user feedback feature, and wherein the one or more artificial intelligence agents are selected by:
processing the expression with the plurality of artificial intelligence agents to indicate a confidence score for a decision of each artificial intelligence agent of the plurality of artificial intelligence agents; and
selecting the one or more artificial intelligence agents based on the indicated confidence scores;
evaluate the expression by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing; and
process the expression in accordance with the determined processing modifications and providing results to the command-line interface.
9. The computer system of claim 8 , wherein the program instructions further comprise instructions to: analyze one or more percepts captured from a computing device associated with the command-line interface to select the one or more artificial intelligence agents.
10. The computer system of claim 9 , wherein the program instructions further comprise instructions to: analyze the one or more percepts with the selected one or more artificial intelligence agents to determine the processing modifications.
11. The computer system of claim 8 , wherein the instructions to select the one or more artificial intelligence agents are further based on an identity of the user.
12. The computer system of claim 8 , wherein the one or more artificial intelligence agents are selected by an orchestration layer, and wherein the program instructions further comprise instructions to:
in response to processing the expression and providing the results to the command-line interface, obtain feedback from a computing device associated with the command-line interface; and
process the feedback to indicate a modification to one or more of: the orchestration layer, and an artificial intelligence agent of the plurality of artificial intelligence agents.
13. The computer system of claim 12 , wherein the feedback is based on one or more from a group of: user-provided feedback, and feedback based on user actions performed subsequent to providing the results to the command-line interface.
14. A computer program product for adapting processing of expressions by a command-line interface, the computer program product comprising one or more computer readable storage media collectively having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:
analyze an expression provided to the command-line interface by a user, wherein the command-line interface includes pre-defined expression processing;
select one or more artificial intelligence agents of a plurality of artificial intelligence agents based on the analysis of the expression, wherein each artificial intelligence agent comprises a particular machine learning model trained to modify processing of expressions provided to the command-line interface, wherein each of the plurality of artificial intelligence agents are trained to perform a different functionality from a group of: an error-correcting feature, a natural language processing feature, an automated troubleshooting feature, an expression sequence automation feature, and a user feedback feature, and wherein the one or more artificial intelligence agents are selected by:
processing the expression with the plurality of artificial intelligence agents to indicate a confidence score for a decision of each artificial intelligence agent of the plurality of artificial intelligence agents; and
selecting the one or more artificial intelligence agents based on the indicated confidence scores;
evaluate the expression by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing; and
process the expression in accordance with the determined processing modifications and providing results to the command-line interface.
15. The computer program product of claim 14 , wherein the program instructions further cause the computer to: analyze one or more percepts captured from a computing device associated with the command-line interface to select the one or more artificial intelligence agents.
16. The computer program product of claim 15 , wherein the program instructions further comprise instructions to: analyze the one or more percepts with the selected one or more artificial intelligence agents to determine the processing modifications.
17. The computer program product of claim 14 , wherein the instructions to select the one or more artificial intelligence agents are further based on an identity of the user.