Cisco wanted to scale its digital assist engineer that assists its technical assist groups around the globe. By leveraging its personal Splunk expertise, Cisco was in a position to scale the AI assistant to assist greater than 1M instances and release engineers to focus on extra complicated instances, making a 93+% buyer satisfaction ranking, and guaranteeing the important assist continues working within the face of any disruption.
In case you’ve ever opened a assist case with Cisco, it’s doubtless that the Technical Help Heart (TAC) got here to your rescue. This around-the-clock, award-winning technical assist staff providers on-line and over-the-phone assist to all of Cisco’s clients, companions, and distributors. In actual fact, it handles 1.5 million instances around the globe yearly.
Fast, correct, and constant assist is important to guaranteeing the client satisfaction that helps us keep our excessive requirements and develop our enterprise. Nevertheless, major occasions like important vulnerabilities or outages can trigger spikes within the quantity of instances that slow response occasions and rapidly swamp our TAC groups, impressioning buyer satisfaction because of this. we’ll dive into the AI-powered assist assistant that assists to ease this subject, in addition to how we used our personal Splunk expertise to scale its caseload and improve our digital resilience.
Constructing an AI Assistant for Help
staff of elite TAC engineers with a ardour for innovation set out to construct an answer that might speed up subject decision occasions by increaseing an engineers’ capacity to detect and remedy buyer issues. the was created — it’s greater than an AI bot and fewer than a human, designed to work alongside the human engineer.
Fig. 1: All instances are analyzed and directed to the AI Assistant for Help or the human engineer based mostly on which is most applicable for decision.
By immediately plugging into the case routing system to investigate each case that is available in, the AI Assistant for Help evaluates which of them it will probably simply assist remedy, together with license transactions and procedural issues, and responds on to clients of their most popular language.
With such nice success, we set our eyes on much more assist for our engineers and clients. Whereas the AI Assistant for Help was initially conceived to assist with the high-volume occasions that create a big inflow of instances, it rapidly expanded to incorporate extra day-to-day buyer points, serving to to scale back response occasions and imply time to decision whereas persistently sustaining a 93+% buyer satisfaction rating.
Nevertheless, as using the AI Assistant grew, so did the complexity and quantity of instances it dealt with. An answer that when dealt with 10-12 instances a day rapidly ballooned into tons of, outgrowing the methodology initially in place for monitoring workflows and sifting by way of log knowledge.
Initially, we created a technique generally known as “breadcrumbs” that we tracked by way of a WebEx house. These “breadcrumbs,” or actions taken by the AI Assistant for Help throughout a case from finish to finish, have been dropped into the house so we might manually return by way of the workflows to troubleshoot. When our assistant was solely taking a small quantity instances a day, this was all we would have liked.
The issue was it couldn’t scale. Because the assistant started taking up tons of of instances a day, we outgrew the size at which our “breadcrumbs” technique was efficient, and it was not possible for us to handle as people.
Figuring out the place, when, and why one thing went improper had change into a time-consuming problem for the groups working the assistant. We rapidly realized we would have liked to:
- Implement a brand new methodology that might scale with our operations
- Discover a resolution that would offer traceability and guarantee compliance
Scaling the AI Assistant for Help with Splunk
We determined to construct out a logging methodology utilizing Splunk, the place we might drop log messages into the platform and construct a dashboard with case quantity as an index. As a substitute of manually sifting by way of our “breadcrumbs,” we might instantaneously find the instances and workflows we would have liked to hint the actions taken by the assistant. The troubleshooting that might have taken us hours with our authentic methodology may very well be completed in seconds with Splunk.
The Splunk platform provides a sturdy and scalable resolution for monitoring and logging that allows the capabilities required for extra environment friendly knowledge administration and troubleshooting. Its capacity to ingest giant volumes of knowledge at excessive charges was essential for our operations. As an trade chief in case search indexing and knowledge ingestion, Splunk might simply handle the elevated knowledge move and operational calls for that our earlier methodology couldn’t.
Tangible advantages of Splunk
Splunk unlocked a stage of resiliency for our AI Assistant for Help that positively impacted our engineers, clients, and enterprise.
Fig. 2: The Splunk dashboard provides clear visibility into capabilities to make sure optimized efficiency and stability.
With Splunk, we now have:
- Scalability and effectivity: Splunk displays the assistant’s actions to make sure it’s working accurately and offers the flexibility for TAC engineers to watch and troubleshoot workflows, permitting the assistant to effectively scale. The AI Assistant for Help has efficiently labored on over a million instances to this point.
- Enhanced visibility: With dashboards that enable for fast entry to case histories and workflow logs of our assistant, the TAC engineers overseeing the processes save time on case evaluations to ship sooner than ever buyer assist.
- Optimized processes with real-time metrics: The visibility into useful resource allocation permits us to optimize our enterprise processes and workflows, in addition to display the worth of our resolution with real-time metrics.
- Proactive monitoring: Splunk ensures all APIs are absolutely functioning and displays logs to alert us of potential points that might impression our AI Assistant’s capacity to function, permitting for fast remediation earlier than buyer expertise is impacted.
- Increased worker and buyer satisfaction: Engineers are outfitted to deal with larger caseloads and effectively reprioritize efforts, lowering burnout whereas optimizing buyer expertise.
- Diminished complexity: The dashboards have a easy interface, making it a lot simpler to coach and onboard new workers. The convenience of use additionally serves to enhance the capabilities of the people working our AI Assistant by enhancing their accuracy and effectivity.
By offering a scalable and traceable resolution that helps us keep compliant, Splunk has enabled us to keep up our dedication to distinctive customer support by way of our AI Assistant for Help.
Further Sources:
PS: Attending Cisco Stay in San Diego this June?
You’ll have a particular alternative to speak reside with Cisco IT specialists to dive into these success tales and different deployments! Look for Cisco on Cisco in every of the showcases and you’ll want to search Cisco on Cisco within the session catalog to add our classes to your schedule!
Share: