Welcome to our video on pre processing Intersight webhooks with Cisco workflows. Integrating events from platforms like Cisco Intersight into operational tools often hits a roadblock with data format and compatibility.00:06We can leverage the power of Cisco workflows as a lightweight low code data translator to ensure seamless 3rd party system integration. Cisco Workflows is a low code, NO code platform with a drag and drop interface leveraging pre made automations that solve common use cases.00:20Workflows is currently available at NO additional cost within the Meraki dashboard and unifies automation across Cisco and 3rd party environments. You can visit dashboard.meraki.com for additional information on getting started with workflows. Now let's pivot to the demonstration.00:37We'll walk through the full integration path configuring a Cisco Intersight webhook to target a Cisco workflows webhook endpoint where the low code logic will pre process the data and seamlessly forward the alert to our 3rd party chat system. We'll go ahead and take a look at our demo setup.00:55The 1st thing that we would need to do is log into a Meraki dashboard. Once we've been logged into Meraki dashboard, we can go down to automation over here, and then down here we'll click on rules. What we're gonna do is we're gonna set up a webhook endpoint in Meraki to send our inter site webhook to. So we'll click webhooks right here.01:15And we have one already set up for intersite, so we'll just click on that over here. All we needed to do was specify the display name and then the request content type, and then Meraki is gonna provide us with the webhook URL down here. So we would just copy that.01:35And now we'll move over to Intersight. So within Intersight, just go down to systems and webhooks, and we can click add webhook right here, but we've already predefined this Meraki one over here, so we'll just go ahead and edit it and take a look at it.01:51So here's where we would paste our payload URL from Meraki dashboard, and then down here under our events, so we're looking at object type condition alarm, and then we're looking for any created or updated alarms. We can also add additional filters on the alarm, so if we only wanted the web.02:10Have to go out for critical alarms, e.g., we could do severity equals critical over here. So once we have that defined, the next step would be to go back to Meraki over here and go underneath automation and then targets.02:30And then here we're gonna define our destination webhook endpoint on our 3rd party chat system. So here we can do new target. We've already got it defined right here under 3rd party chat, so we'll just open that up and take a look. So all we needed to do is specify the display name.02:50Over here, whether or not we're using account keys, so this would be any kind of authentication to that endpoint. In this case we don't need authentication. And then down here our protocol, our host name, and then the path to our particular webhook endpoint.03:08And then we would just go ahead and save that. So once we have that saved, the next step would be to go under workspaces and take a look at the workflows themselves. Here we have a workflow already defined for intersite webhook.03:25Processor, so we'll just go ahead and click on that.03:45And view workflow, and then within the workflow properties, if we scroll down, we'll see automation rules that are defined. So here we have an automation rule for a webhook rule.03:48So when Intersight sends an alarm to that Meraki dashboard webhook endpoint, it'll actually kick off this particular workflow. There's other automation rule types as well, so you could actually do schedules or emails or approval task rules, but in our case, we're gonna use the webhook.04:05So once the webhook has been received, what we have over here is we have a JSON path query task and what's that's gonna do is it's gonna go ahead and extract the different perimeters from the inter site alarm webhook.04:26So right here we have our source JSON to query, so this would be the webhook body, and then if we click right here on this little icon over here, we can actually see what kind of environments or rules or workflow.04:44Inputs or outputs are available and it makes it easy to just go ahead and select it from there. So in, in our case, we have the webhook rule. We were looking at the output and then the request body of that. So we're using that as our input to the task. Down here we've defined a couple of different.05:02Json path queries. So we're gonna extract the creation time, the affected MO display name, so this is the object that's affected within inner site, the event code, and then the event description and event severity.05:21From the webhook. So once those have been extracted from the webhook, right here, we actually have an LLM prompt that we're just gonna use to enrich that data. So over here, what we do is we just specify our open AI target.05:38And then our account keys if needed, the model name in this case GPT four.one mini, and then over here, so we have our user chat message and what we're gonna do is we're just gonna send it the extracted perimeters, so the expected MO display name, code description, and severity.05:56The.06:16And those are easily found if you click this button over here and if you go over here, you can look at the JSON path query and you can see what's available and select it from there. Further down here we have our system prompts so it's just letting the LLM know that.06:17You're an infrastructure engineer responsible for enriching alarms for the NOC, and then we want to include the original alarm, the alarm's potential impact, and then potential troubleshooting next steps for the NOC engineer, and that we want it to be in markdown format.06:37And then the final step would be this HTTP request over here. So this is gonna take our enriched webhook from Intersight and send that to our 3rd party chat system. So if we scroll down here, we've selected our target, so this is our 3rd party chat target that we had previously created.06:57Down here we have our method which is set to post, and then down here we have our request body. So this is what our 3rd party chat system is expecting inside of the payload, so it's looking for blocks, type and text, and then down here, what we're doing is we're doing a substitution.07:18Of the output of this LLM prompt inside of this text field. Down here we can specify additional headers if needed, in our case that wasn't necessary. And now what we'll do is what we would go ahead and validate this particular workflow, in this case it's already been.07:36Validated. So we'll go ahead and actually go to our inter site alarms over here and we'll go ahead and unacknowledge one of these alarms, which will cause the webhook to be sent. So we'll click this one e.g. and unacknowledge it.07:56And then if we go to our 3rd party chat system over here, the alarm just came in. So we have our original alarm information from the inter site webhook, and then here we have the enrichment from the LLM. And that concludes our demo.08:16
