Generative AI-assisted configuration of application analytics features
In one embodiment, a device generates a prompt for a large language model that returns a set of transactional milestones for a particular type of transactional workflow in an application, based on input from a user interface that indicates the particular type of transactional workflow. The device identifies a set of monitored transactions in the application that match any of the set of transactional milestones and aggregates telemetry data for the set of monitored transactions into a transactional workflow of the particular type. The device also provides information regarding the transactional workflow for display by the user interface.
1. A method, comprising:
generating, by a device, a prompt for a large language model that returns a set of transactional milestones for a particular type of transactional workflow in an application, based on input from a user interface that indicates the particular type of transactional workflow;
identifying, by the device, a set of monitored transactions in the application that match any of the set of transactional milestones;
aggregating, by the device, observability data for the set of monitored transactions into a transactional workflow of the particular type; and
providing, by the device, information regarding the transactional workflow for display by the user interface.
2. The method as in claim 1 , wherein the observability data comprises metrics, events, logs, and traces regarding the application.
3. The method as in claim 1 , wherein the prompt indicates an output format for the set of transactional milestones.
4. The method as in claim 1 , wherein the input from the user interface comprises at least one of: voice data or text data.
5. The method as in claim 1 , wherein the set of transactional milestones include endpoints of the application associated with those transactional milestones.
6. The method as in claim 5 , wherein the device identifies the set of monitored transactions based on the endpoints of the application.
7. The method as in claim 1 , wherein the transactional workflow is a transaction funnel.
8. The method as in claim 7 , wherein the information regarding the transactional workflow indicates a count of users that performed each of the set of transactional milestones.
9. The method as in claim 1 , further comprising:
sending the prompt to the large language model via an application programming interface.
10. The method as in claim 1 , wherein the set of monitored transactions in the application are monitored via instrumentation inserted into the application.
11. An apparatus, comprising:
one or more network interfaces;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
generate a prompt for a large language model that returns a set of transactional milestones for a particular type of transactional workflow in an application, based on input from a user interface that indicates the particular type of transactional workflow;
identify a set of monitored transactions in the application that match any of the set of transactional milestones;
aggregate obtained observability data for the set of monitored transactions into a transactional workflow of the particular type; and
provide information regarding the transactional workflow for display by the user interface.
12. The apparatus as in claim 11 , wherein the obtained observability data comprises metrics, events, logs, and traces regarding the application.
13. The apparatus as in claim 11 , wherein the prompt indicates an output format for the set of transactional milestones.
14. The apparatus as in claim 11 , wherein the input from the user interface comprises at least one of: voice data or text data.
15. The apparatus as in claim 11 , wherein the set of transactional milestones include endpoints of the application associated with those transactional milestones.
16. The apparatus as in claim 15 , wherein the apparatus identifies the set of monitored transactions based on the endpoints of the application.
17. The apparatus as in claim 11 , wherein the transactional workflow is a transaction funnel.
18. The apparatus as in claim 17 , wherein the information regarding the transactional workflow indicates a count of users that performed each of the set of transactional milestones.
19. The apparatus as in claim 11 , wherein the process when executed is further configured to:
send the prompt to the large language model via an application programming interface.
20. A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
generating, by a device, a prompt for a large language model that returns a set of transactional milestones for a particular type of transactional workflow in an application, based on input from a user interface that indicates the particular type of transactional workflow;
dentifying, by the device, a set of monitored transactions in the application that match any of the set of transactional milestones;
aggregating, by the device, observability data for the set of monitored transactions into a transactional workflow of the particular type; and
providing, by the device, information regarding the transactional workflow for display by the user interface.