Session Smart Routing Demo: Automated Troubleshooting with Mist

Demo Drop SD-WAN
Predictive Capabilities, Automation and AI/ML.

Automation and AI/ML functionality for troubleshooting and day two operations

See how the Mist’s intuitive and simple-to-use dashboard offers actionable insights and a complete client-to-cloud perspective unmatched in the industry. Get the full scoop in this short demonstration.

Show more

You’ll learn

  • How Mist helps identify root causes of issues impacting service-level experiences (SLEs)

  • Ways the AI engine can drill down into the application to easily uncover issues

  • How your virtual network assistant Marvis provides real-time answers about your network

Who is this for?

Network Professionals Business Leaders

Resources

Transcript

0:01 this demonstration will describe our

0:03 automation and aiml functionality for

0:06 troubleshooting and day two operation

0:08 device network and application

0:10 performance telemetry from each wan

0:12 router is streamed to the wan assurance

0:15 portal this telemetry enables the ai

0:18 engine to measure end user sles or

0:20 service level experiences for every user

0:23 on the network across the full stack

0:26 wireless wired and wan and deliver

0:28 actionable insights

0:30 there it is analyzed and correlated with

0:32 data coming from wired and wireless

0:34 devices for a complete client to cloud

0:37 perspective that is unmatched in the

0:39 industry

0:40 here you can see some of the dashboards

0:42 being populated by data from the wan

0:45 looking at insights gives operators an

0:47 at a glance view of recent events and

0:49 metrics

0:50 next we see our service levels for the

0:52 site sles show a measure of user

0:55 experiences and helps identify the root

0:57 causes of issues that are impacting it

1:00 sles for gateway health can indicate

1:02 when issues with the device itself such

1:04 as hardware failures or high resource

1:07 utilization are impacting experience the

1:10 wan link sle shown here provides

1:12 indication of when issues with the

1:14 network links and paths may be impacting

1:17 user experience the application sle

1:20 measures user experience for the app

1:22 itself

1:23 here we see the gateway and wan link

1:25 health scoring very well but the

1:27 application sle is low drilling into the

1:30 application sle enables the ai engine to

1:33 identify whether the root cause for a

1:36 user having a bad app experience is

1:38 actually due to the app side latency

1:40 itself not the wan not the router not

1:43 the wired and the wireless network as we

1:46 examine the app sle affected items we

1:48 can see what applications have been

1:50 impacted through correlation of data

1:52 from wired and wireless devices we can

1:55 even see which user devices were

1:57 affected

1:58 finally meet marvis your virtual network

2:00 assistant who brings this all together

2:03 in a conversational interface get

2:05 real-time answers about your network or

2:07 troubleshoot issues about actual user

2:09 and application experiences by just

2:12 asking questions

2:13 marvis is the first network assistant in

2:15 the industry to bring conversational ai

2:18 to networking transforming the way i t

2:20 teams interact with enterprise networks

2:23 let's ask marvis about appease team's

2:25 call experience in response marvis

2:28 pinpoints exactly where the issue was

2:30 after analyzing correlating and using ml

2:33 models on the rich telemetry data coming

2:35 from the miss juniper full stack access

2:37 network a true client to cloud

2:40 experience delivered the juniper

2:42 solution delivers a high performance

2:45 session smart when producing telemetry

2:47 that is analyzed and correlated using

2:49 the power of the cloud and ai

2:52 missed when assurance helps the operator

2:54 ensure that up times are maximized

2:56 faults are minimized and user experience

2:59 is upheld

Show more