Scaling the Cisco AI Assistant for Support with Splunk

[ad_1] Cisco wanted to scale its digital assist engineer that assists its technical assist groups all over the world. By leveraging its personal Splunk expertise, Cisco was capable of scale the AI assistant to assist greater than 1M circumstances and unlock engineers to focus on extra complicated circumstances, making a 93+% buyer satisfaction ranking, and making certain the vital assist continues working within the face of any disruption.

If you happen to’ve ever opened a assist case with Cisco, it’s possible that the Technical Help Heart (TAC) got here to your rescue. This around-the-clock, award-winning technical assist staff companies on-line and over-the-phone assist to all of Cisco’s clients, companions, and distributors. In reality, it handles 1.5 million circumstances all over the world yearly.

F ast, correct , and constant assist is vital to making certain the shopper satisfaction that helps us preserve our excessive requirements and develop our enterprise . Nonetheless, m ajor occasions like vital vulnerabilities or outages can trigger spikes within the quantity of circumstances that s low response instances and shortly swamp our TAC groups , influence ing buyer satisfaction because of this . we’ll dive into the AI-powered assist assistant t hat assist s to ease this difficulty, in addition to how we used our personal Splunk expertise to scale its caseload and improve our digital resilience .

Constructing an AI Assistant for Assist staff of elite TAC engineers with a ardour for innovation set out to construct an answer that might speed up difficulty decision instances by increase ing an engineers ’ potential to detect and remedy buyer issues . the was creat ed — it’s greater than an AI bot and fewer than a human, designed to work alongside the human engineer.

Fig. 1: All circumstances are analyzed and directed to the AI Assistant for Assist or the human engineer based mostly on which is most acceptable for decision. By instantly plugging into the case routing system to investigate each case that is available in, the AI Assistant for Assist evaluates which of them it may possibly simply assist remedy, together with license transactions and procedural issues, and responds on to clients of their most well-liked language.

With such nice success, we set our eyes on much more assist for our engineers and clients. Whereas the AI Assistant for Assist was initially conceived to assist with the high-volume occasions that create a big inflow of circumstances, it shortly expanded to incorporate extra day-to-day buyer points , serving to to cut back response instances and imply time to decision whereas constantly sustaining a 93+% buyer satisfaction rating.

Nonetheless, as the usage of the AI Assistant grew, so did the complexity and quantity of circumstances it dealt with. An answer that when dealt with 10-12 circumstances a day shortly ballooned into lots of, outgrowing the methodology initially in place for monitoring workflows and sifting via log information.

Initially, we created a technique generally known as “breadcrumbs” that we tracked via a WebEx area. These “breadcrumbs,” or actions taken by the AI Assistant for Assist throughout a case from finish to finish, had been dropped into the area so we may manually return via the workflows to troubleshoot. When our assistant was solely taking a small quantity circumstances a day, this was all we wanted.

The issue was it couldn’t scale. Because the assistant started taking up lots of of circumstances a day, we outgrew the dimensions at which our “breadcrumbs” technique was efficient, and it was now not possible for us to handle as people.

Figuring out the place, when, and why one thing went unsuitable had change into a time-consuming problem for the groups working the assistant. We shortly realized we wanted to:

Implement a brand new methodology that might scale with our operations Discover a resolution that would supply traceability and guarantee compliance

Scaling the AI Assistant for Assist with Splunk We determined to construct out a logging methodology utilizing Splunk, the place we may drop log messages into the platform and construct a dashboard with case quantity as an index. As a substitute of manually sifting via our “breadcrumbs,” we may instantaneously find the circumstances and workflows we wanted to hint the actions taken by the assistant. The troubleshooting that may have taken us hours with our unique methodology could possibly be achieved 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 information administration and troubleshooting. Its potential to ingest giant volumes of information at excessive charges was essential for our operations. As an trade chief in case search indexing and information ingestion, Splunk may simply handle the elevated information circulate and operational calls for that our earlier methodology couldn't.

Tangible advantages of Splunk Splunk unlocked a degree of resiliency for our AI Assistant for Assist 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 appropriately and gives the flexibility for TAC engineers to observe and troubleshoot workflows, permitting the assistant to effectively scale. The AI Assistant for Assist has efficiently labored on over a million circumstances up to now. Enhanced visibility: With dashboards that permit 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 quicker 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 show 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 influence our AI Assistant’s potential to function, permitting for fast remediation earlier than buyer expertise is impacted. Larger worker and buyer satisfaction: Engineers are outfitted to deal with greater caseloads and effectively reprioritize efforts, decreasing burnout whereas optimizing buyer expertise . Lowered complexity: The dashboards have a easy interface, making it a lot simpler to coach and onboard new workers. The benefit 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 take care of our dedication to distinctive customer support via our AI Assistant for Assist.

Extra Assets:

PS: A ttending Cisco Dwell in San Diego this June ? Y ou’ll have a particular alternative to speak reside with Cisco IT consultants to dive into these success tales and different deployments! L <span class="NormalTextRun SCXW147207735 BCX4" data-ccp-charstyle="normaltextrun" data-ccp-charstyle-defn="18","ClassId":1073872969,"Properties":[201342446,"1",201342447,"5",201342448,"1",201342449,"1",469777841,"Aptos",469777842,"Arial",469777843,"Aptos",469777844,"Aptos",201341986,"1",469769226,"Aptos,Arial",268442635,"24",469775450,"normaltextrun",201340122,"1",134233614,"true",469778129,"normaltextrun",335572020,"1",469778324,"Default Paragraph Font"]">ook for Cisco on Cisco in every of the showcases and be sure you search Cisco on Cisco within the session catalog t o add our classes to your schedule!