Digital SRE Agents for Splunk ITSI - Combined

Discover the transformative capabilities of Cisco Splunk ITSI combined with AI agents from our partner Fabrics AI.

Traditional incident management often involves juggling multiple tools to reconstruct timelines and topology for root cause identification.

With Splunk ITSI and Fabrics AI Digital SRE agents, you can effortlessly unify signals, automate root cause analysis, and initiate safe, approved remediations.

We're currently exploring Splunk ITSI where we can view technical and business services plus underlying infrastructure domains like SD Van, Meraki Wireless Network, Campus Network, Data Center, VMware, ACI and UCS.

This enriched data is ingested into ITSI complete with topology and dependency mapping.

Here's our crown jewel application, the AD E Commerce app with all KPIs automatically generated in ITSI, showcasing its efficiency and thoroughness.

Here we see the KPIs for SD van infrastructure, Meraki KPIs and KPIs for UCS server infrastructure.

We can observe KPIs for both infrastructure and the AD E commerce application.

These KPIs are auto created using solution packs and the application appears healthy functioning as expected.

An alert just came in from one of the digital SRE agents into indicating an issue with the application.

Let's delve into it.

There's an active episode on the AD E Commerce app with multiple notable events.

By clicking the link we discover two impacted application KPIs.

Let's check on the AI agents.

The SRE agents are working behind the scenes.

Let's delve into the details.

The digital SRE agent has already conducted root cause analysis providing recommendations.

It has gathered data from all underlying infrastructure domains revealing a significant issue with the Meraki network and identifies problems with the web app, RTT, payment gateway setup and uplink configurations.

We see a clear impact analysis with both application layer issues and network bottlenecks.

Recommendations include escalating payment gateway issues and jitter mitigation.

Tools executed for RCA are detailed with a focus on immediate attention to payment gateway network connectivity behind the sc, the SRE agent uses MCP protocol to execute multiple tool calls assessing health and operational states across domains, synthesizing information for root cause analysis upon verification, there is indeed an issue affecting the Meraki Wireless and parent network service.

The Digital SRE remediation agent has identified suggested changes with a change request pending my review and approval.

It's currently in pending state created by the remediation agent suggesting temporary changes to Meraki MX QoS settings.

I'll proceed to approve the request.

Request approved.

Now a new notification indicates the application state is healthy and normal.

It seems the remediation agent has completed its tasks.

Checking the logs we see it has made several QoS related adjustments with a comprehensive log of all actions taken.

Viewing the service map, everything appears healthy.

The Meraki network and application are both in good condition.

This wraps up our digital SRE agents demonstration.

Thank you for tuning in.

See you in another video.