The IT support world is flooded with chatbots and ticketing tools that claim to use AI, but most only surface knowledge. A true ITSM agent doesn't just provide information. It understands context, takes secure actions, and resolves issues on your behalf. Today, you'll see how Tray's Merlin Agent Builder powers a modern ITSM agent that streamlines employee onboarding, provisions application access, and even creates tickets when things go wrong, all with the right guardrails in place. We'll walk through how this ITSM agent helps reduce backlog, shorten response times, and free up IT staff to focus on strategic initiatives. Let's dive in. Here, I've configured an ITSM agent with a clear scope, assists with access management, account issues, and general IT ticket triage. You'll notice down here, I've selected the model that powers the agent, which can be swapped in just a few clicks. In addition to its system instructions, this agent has a set of tools it can call, like our HR system, our identity provider, and Jira for ticketing. This gives it the ability not just to answer questions, but to actually take action across systems. Let's see it in action with a simple onboarding example. I'm a new employee and I'm going to ask my agent, "What applications do I have access to?" You can see the agent pulls in my identity context. It knows who I am, what department I'm part of, and which applications I'm entitled to based on my department. As you can see, it comes back with a personalized list. Salesforce, GitHub, DocuSign, and Notion are among the apps I should have access to. The agent also provides us with a nice note to let us know that we're entitled to these applications, but we don't actually have them assigned in our Okta account as you can see within our Okta account here. So let's go a step deeper. I'll ask my agent to please provision me access to DocuSign. The agent checks my entitlements, confirms that who I am as a team member should have DocuSign, and then kicks off that provisioning process. So within seconds, it completes the request and if we go ahead and refresh our Okta instance here, we can see that the agent logged the change in our identity system of record all without requiring IT staff to get involved. But now let's try to say that we're logging into DocuSign but running into an issue. So what happens when things don't work? I'll come to my agent and share a screenshot of the error directly with the agent. The agent recognized that, based on the error message that I sent to it via screenshot, I'm locked out of my DocuSign instance and automatically creates a Jira ticket on my behalf. It provides the link to that Jira ticket. It also captures all of the relevant context about my identity and then categorizes the issue as an access lockout so IT can respond quickly. So in just a few minutes, we've seen how the ITSM agent can surface my application entitlements during onboarding, provision new access securely, and handle issues proactively by logging tickets with full context. This isn't just fast for employees. It reduces repetitive workload for IT teams and ensures every action is auditable and secure. And it doesn't stop there. You can extend this agent with tools for automated password resets, escalate critical incidents with missing SLAs, or even proactive incident correlation for common issues. The agent is fully empowered to take those actions within the defined guardrails. With Tray's Merlin Agent Builder, IT support shifts from reactive to proactive, enabling employees to get what they need instantly while freeing IT teams to focus on higher-value projects. That's the power of AI driven automation on Tray. One platform, every agent. Hi. I'm Luke. If your HR team still answers routine questions about travel policy or PTO by email, this is the kind of agent you could build. It runs in Slack, checks policy, and can even submit or escalate requests automatically. So let's say I've got some travel coming up next week. So my first question is going to be, I need to fly from London to Dubai next week. Can I fly business? And so in this case, it's going to be a question that's going to be related to some of our travel policies across our organization. And so let's see what the agent comes back with in this circumstance. And so in this case, we can see that our agents come back with a response. In this case, it's saying that based on our company travel policy, business class is allowed for international flights over eight hours. However, it's noticed that in this case, because my route is London to Dubai, that it knows the flight is six to seven hours. So it's actually shorter than our policy threshold for automatic business class approval. And so in this case, it's also got a tool here that can help with some live flight price information so that I've got a good background on some of the pricing. And what's really great is that it's also provided me with some documentation down here around some of the expense reimbursements and policies that we have as it relates to things like that business class threshold, as well as some items around the expense thresholds as well. Now all of these policies currently, in my case, sit within Google Drive, and it's really easy for you to be able to configure new data sources for your agent. In my case, I selected Google Drive, to be able to ingest pieces of information that your agent's able to make use of in order to allow it to help it come back with suitable responses to some of those queries. But let's go ahead and take a look at a slightly different example where I want to book some PTO in this circumstance. So what I'm going to do is I'm going to ask my agent, I would like to book some holiday. And so in this case, let's take a look to see what our agent comes back with in this particular circumstance. And so in this case, what we can see is our agent's come back with and it's provided us with some information on our holiday entitlement. So it's been able to reach into our HR system and pull back my specific holiday allowance. It's also been able to pull back my existing holiday requests that exist within our HR system as well and also provide me some information on my remaining entitlement. It's also asking for some extra information around the exact times that I want off. And so let's go ahead and ask it, in this case, for the 21st of May as the date that I want to book. Now this is interesting because this is just a day in advance. So let's take a look to see what happens when there's a difference between what I'm requesting and some of those HR policies that my agent has ingested. In this case, you can see that the agent has come back and actually pushed back on this particular request because it's got that HR policy on our PTO requirements that says that PTO must be booked at least seven days in advance. And because it doesn't meet that, the agent has not been able to go ahead and create that holiday request for us. However, to be even more helpful, what it's done is actually created a support ticket for us so that our HR team can go ahead and review that if there are any requirements or exceptions to that rules. So as you can see, it's really easy when you give your agent that knowledge that if there's any scenarios where it's not able to take that action, you could bake in and build in those guardrails so that it's only responding and acting accordingly based on those existing policies that you might have. Again, as before, it's also provided a link straight through to that documentation around our PTO policy. So let's go ahead and give it some valid dates. So in this case, let's do June 9th to June 10th as the dates that I would like to request. And so this should fit within all those policy requirements that we just went through previously. In this case, what we can see is that our agents come back. And because it's got a tool that's been able to reach into our HR system and actually book this PTO, it's been able to submit that new request. In addition to the previous days, it's also updated and given us some information around our remaining holiday entitlement so that we're able to go ahead and take a look at that. If we go ahead and look at our HR system, what we should see is that it's not gone ahead and created that one on May 21st because it did not meet those requirements. But if we take a look at June, we should see that June 9th to June 10th vacation time added in there as well. So So it's been able to book that successfully because it meet those requirements. Just one example of what you can build on one platform, every agent. Does your team spend countless hours trying to find answers to queries within your CRM, searching through endless records, then trying to make sense of it all once they eventually find it? I'm going to walk through just two of the many possibilities of how easy it is to build a CRM agent with Tray's Merlin Agent Builder. Let's dive in. Alright. So I'm going to put my marketing hat on here for a second, and what I want to do is interface with my agent to help me create a marketing campaign. So on the left hand side, I have my agent. On the right hand side, I have my Salesforce dev environment. So first thing I'm going to do is I'm going to ask it to create a campaign within Salesforce. So I've provided it with some basic information that might come from a marketing brief, the campaign name, as well as the start date and the end date of the campaign. Just some rough information. Now if I didn't provide this information, it would actually ask me to provide it. So in this case, I gave it everything it needed to fill out the rest of the information. So here we go. It's repeating back to me that, hey, our naming convention actually needs to be in this format. So it's renaming it for me to follow my internal SOP documentation it's been trained on. So that could be referenced within a Google Doc or a Notion Doc or just directly uploaded into Tray. It can ingest that information to ground the agent in how we should be thinking about completing tasks like nomenclature. So here's the information. It's asking me to confirm it. I'm just going to confirm it real quick just to make sure. Human in the loop and just to verify when creating records I've asked to, confirm with me. Now you don't have to have that, if you wanted to move much, much quicker, but I figured it's a nice little review, approve, and then you can just move on. So here's the campaign that's been created. I'm going to just refresh Salesforce. Here's my campaign. Everything here looks great. Now what I'm going to do is add some contacts. So I'm going to jump back to my agents. I'm going give it, submit additional instructions. Find all contacts within Salesforce where VP is in the title, and I want to add them to the campaign that we just created. So we were working with the campaign object. Now we're going to be querying the contact object, finding contacts, and then creating those contacts as campaign membership records within the campaign object within Salesforce. So our agent has the ability to go from object to object as well as, fill in any field within the object that you've given it access to. The ability to either update or or create. So campaign membership records have been created. There were two of them. So if I go back to Salesforce, I refresh this real quick. Now we can see here our our two contacts, Brandon Walton and Steven Smith have been added to those campaigns. So this is just a quick overview of how marketing might think about creating campaigns leveraging a Tray agent, within their CRM. Alright. So I'm going to switch gears here for a second, put on my go-to-market hat. So, what I'm going to do is I'm going to leverage the same agent just a little bit differently, and I am going to ask it to check to see if there are any accounts, up for renewal within the next 30 days that might be at risk. So we have two different custom fields on the account right now. One of them is an account health score, and then the other one, of course, is their renewal date whenever their contract is up for renewal. So I'm I'm asking it to create a custom query for me just on the fly. So as a salesperson, I I don't want to have to create a report and navigate Salesforce very slowly and clunkily and having to know what fields are there and and what values to put in. It it can be very cumbersome for a salesperson to understand all of that. Certainly with an agent, we can have the agents handle all of that for the salesperson. So here we go. There's actually one account at risk, which I happen to know is correct because I I have updated it. The account name is Cypress Learning, and then the renewal date is July 10, and the account health is poor. So yikes. I might want to actually follow-up with that account before the renewal date just to make sure everything is going good, and maybe I can address any concerns ahead of it. So what I'm going to ask the agent to do here is I'm going to ask it to create a task for me. So I want to create a task, related to the contact of the account as well as, the account itself. So it's going to create the task on on the task object. It's going to relate it to the account. It's going to relate it to the contact. And then I've also asked it to draft an email for me and put it into the details of that task. So here we go. The task has been created. It's been related to Brandon Walton, which is the contact. Follow-up date is July 3, which is a week out from the renewal dates. And then I've also have the draft email there. So let's just double check that it's there. Let me go into my, Cypress Learning account. So here's my account. Here's my task that was just created. Let me jump into that here real quick. So it's assigned to me, which is great. It's assigned. It's related to Brandon. It's related to Cypress Learning. All of that looks great. And then, here's a draft of my email. And you can see that, has the personalization already because it knows, who the contact is, And then it has drafted an email that I can just copy and paste into my email client, maybe tweak it and edit it a little bit, and then, click send. So you could see here how, an agent can actually help sales manage their book of business. And this is just one clear use cases around maybe opportunities and putting in call notes, on those different opportunities and managing the different stages of the opportunities. Just keep everything clean, and tidy within Salesforce. So this is really good go to market kind of sales, use case where sales teams, might want to use an agent. The sales world is filled with tools claiming to leverage AI, yet many merely provide information without meaningful assistance. True AI agents don't just inform, they actively solve problems and execute tasks on your behalf guided by secure guardrails. Today, you'll see how Merlin Agent Builder addresses common sales pipeline challenges by summarizing pipeline health, flagging stalled deals, and proactively suggesting and taking actions to advance deals during daily briefings. Let's go ahead and take a look at this agent in action. So my agent's being configured here with this overall agent scope, which is this overarching instructions about what it's designed to help with. In this case, helping account executives analyze their pipeline. I've got the model selected of my agent down at the bottom here. I can easily adjust this if I wanted to in just a few clicks. In addition to this, my agent has a set of tools. Now, we're using CRM as the HubSpot here. And there's various tools here that my agent is going to be able to make use of to help it get the information that it needs when it's analyzing that pipeline. So one of those tools will be reaching in and getting the full pipeline information for a particular account executive, a tool to help it identify and understand who the account executive is to make sure that we're getting the correct pipeline information, as well as tools to help get things like the full deal details, things like activity and the contact from the deal themselves, and the tools that actually help us take action in our CRM by updating deal activity when it makes sense as part of our pipeline analysis. Let's go ahead and take a look at how this all comes together in the agent itself. So I'm going to start with my questions to the agent. I want it to go ahead and imagine that I'm, obviously, an account executive. And I'm starting my day. I want to get an overview of my pipeline health. So I'm going to ask my agent here to give me an overview of my pipeline health. I will see how the agent is able to take those tools into account and perform some analysis on my pipeline to provide us with some recommendations about things that I could potentially take a look at or deals that I potentially want to explore and make sure that they are at the top of my mind so I can resolve any potential risks with them. As we can see, my agent has come back and it's provided us an overview of our pipeline health broken down into different stages, as well as our high-priority opportunities and it highlighted some deals that might require some immediate attention. It's also provided us with some recommended actions and some suggested actions that it is now able to help with at the bottom here. But I'm going to go ahead and ask it to "Can you flag any deals at risk, please?" So I'm going to ask it to do a deeper analysis and actually pull back those deals that it's going to identify as potentially at risk so that it can take some action to help prevent that. As you can see, my agent's come back, and it's highlighted some deals. So it's got some high risk deals that have some close dates approaching, those that have limited recent engagements. So they might be stalled, for example, or they've got no activity on the deal themselves, as well as some moderate risk deals that are risk too. You can also see it's got some immediate action required as well as some suggested actions that you can actually help with to overcome that. So I'm going to ask it to draft some emails for the high risk deals, please. And we'll see how the agent is actually able to go ahead and take some action for us by drafting an email to those high risk accounts in our pipeline and logging that in our CRM so that we could take a look and review that and decide if we need to make any tweaks if necessary and go ahead and actually send that email as well. As we can see, my agent has gone ahead and drafted us those emails for us and created that as an activity in our CRM and provided us a link down to HubSpot, and included some next steps. So it suggested to review the draft emails, make any necessary adjustments. Let's go ahead and follow those links, and we can take a look to see what my agent has been able to create for us within these deals. So as you can see, for the first one, we've got our email here. We've got a logged email for Alice Smith. As you can see, it's taking into account the contact information for this one and provided us with a quick follow-up to recommend scheduling a review. We've also got our email on the second one as an email draft that's been logged. So as we can see, the agent's been able to take that pipeline analysis, be able to draft those emails for us, and actually go ahead and take that action by adding that to our CRM as an activity. Of course, if you wanted to, you could take that a step further and actually create an activity to go ahead and send the emails as well. But, of course, there's a lot of possibilities that you have. Now this is just the tip of the iceberg in terms of the options that you have for the functionality that you want to add to your sales pipeline agent. There's a ton of extra tools that you can add for adding on additional functionality. As you just saw, Merlin Agent Builder instantly highlights pipeline issues, identifies stalled deals, and proactively suggests and executes actions, enabling you to focus more on closing deals and less on the administrative tasks. This is just one example of what you can build with one platform, every agent. How many hours does your team lose each week just trying to fill out RFPs? Today, we're going to show you an RFP agent built on Tray's Merlin Agent Builder for an employee who wants to speed up the process of completing an RFP. Now, RFPs typically ask for a wide variety of information about your organization, especially technical knowledge. And so, having a good grounding of knowledge is super important. So, let's take a look at this agent in action. Now my agent here has been configured firstly with an overall agent scopes. These are kind of the overarching instructions and guidance that I've given the agent. It's also easy for me to configure the model down here, so I can tweak this around as necessary and use different models if I so wish. But most importantly, my agent also has access to a set of agent tools. Now most of the tools here for this RFP agent are going to be grounded in knowledge. So I've ingested in things like our CAIQ document, previous RFPs, because, of course, there's a wealth of information that exists within those. It also has a tool down here that's ingested in our Tray technical knowledge, so any information around the platform and the functionality from a technical standpoint, so a good knowledge base that it can use for that. Now it's really easy for you to be able to bring in new data sources. So if you want to bring in more data from different systems, you can select the data source, point it at the system that you're using and where that data sits, and start to bring that data into the fold so that your agent can make use of it. Now, of course, knowledge is just one part of an agent. Where a lot of the power starts to come in is when your agent is able to take action as well. So in the case of an RFP, that might be incorporating in human in the loop, maybe cross checking and pulling information from other systems, or going ahead and maybe creating a ticket for us so that our team can manually review certain questions assigned to them and have visibility that they need to do so. Let's go ahead and test our agent here. Now I'm going to start with the question, quite a generic one around security. So how does Tray approach security? Now, of course, I'm testing the agent here in isolation with individual questions, which might be a scenario where if you might have one or two questions, you can ask the questions directly. But I'll also show you in a moment how this agent can ingest in and process a whole RFP document as well. Let's take a look at this question. Let's take a look to see what the response comes back with. And we'll take a look at the format and the information that it's going to pull from to actually come back with a suitable response to quite a generic question. And so as we see, the response coming back is quite comprehensive. It's given us a great overview of our approach to security. But what's really cool is it's also provided the sources at the bottom. So you can see it actually pulled from several places this information for this response from those knowledge sources, including directly the parts of those CAIQ documents and our technical knowledge base. Now let's take a look, though, at a scenario where I want to incorporate human in the loop. So I'm going to ask a question around pricing. So what I wanted to happen in this scenario is not come back with any generic pricing. I wanted to create a ticket in our ticketing system assigned to our account team so they can actually put together a tailored pricing proposal for this RFP. So let's take a look to see what the agent does in this scenario. And so in this case, you can see that it's come back with a response, but it's actually gone ahead and created that ticket for us in our ticketing system. So this is a great example of the agent taking action. It's figured out that this question is about pricing. It doesn't have a suitable response for pricing in its knowledge base. And so it's gone ahead and taken the action to actually create a ticket, assign it to the relevant team, in this case, our sales team, so that they can manually review this and put together a tailored pricing proposal. So you're starting to see this agent is also able to take action in these systems too. Let's go ahead and take a look at an example of processing a whole RFP document. So I've got my agent also deployed here into Slack. Now what I'm going to do is I'm going to upload a RFP into the chat here, and I'm going to ask it, "Can you process this RFP, please?" And so in this case, the agent is also going to take action again. In this case, instead of just keeping the RFP here in Slack, it's going to upload that to a collaborative file store, in this case, Google Drive. But that might be something like a SharePoint so that multiple people can access it and collaborate on the completion of that as well. So you can see it's taken that action and actually provided us a link directly to that RFP that's been uploaded. And what we will see is the questions over on the left hand side for what this RFP includes, and we should see the responses coming through in just a moment because our agent's going to go ahead and process that sequentially with that information in. And so in this case, what we're starting to see is just as before, the agent's coming back with its responses. It's given it a really good grounding set of data that is using pulling from those knowledge sources and just working through these questions, as it sees them and pulls them through in that RFP document directly as as well. So this is really great. Of course, this is much more applicable maybe to completing a whole RFP, which is awesome. And it will go through in exactly the same way by looking at the question, looking at its knowledge base, kind of provide that response, and, of course, if it needs to bring that human in the loop into that scenario if required as well as it kind of does go through and sequentially processes it. So you can see that it's more or less finished with this RFP processing now, which is fantastic. Now what's nice is that once it has finished going through, it would also come back and let the user know over in the Slack channel that it's completed. And you can see here that it's also provided that link back so they can go through and click to see that completed RFP. So as you can see, it's really powerful to be able to build out an agent that's, one, grounded in that knowledge, but also, two, when needed, taking that action, whether that's uploading the RFP to a collaborative file store, incorporating in that human in the loop for any of that iterative responses to these RFP questions, and building that altogether with the Merlin Agent Builder functionality. And this is just one example of what's possible when you build on one platform for every agent. Today we'll show you how Merlin Agent Builder efficiently handles budget checks and proactively manages your financial tasks during your quarterly business reviews, seamlessly integrating data from your ERP and various other systems across your organisation. In this case, let's imagine you're preparing for an important QBR and you need instant visibility into your spending and the ability to act quickly on financial decisions. Merlin Agent Builder can really help streamline this process. Let's take a look at this agent in action. So one of the things my agent has here is its overall agent scope. This is critical for guiding the agent to be able to help with the common requests that you're going to be asking it and help provide it and give it the direction about what type of things it might be helping with. You've also got your AI model selected down here and I can easily adjust this around across the various different models if I wanted to, depending on the use case that I might be building for. In addition to this, my agent also has a set of tools and these tools are the pieces of functionality that allow my agent to take different things, whether that's reaching into a system to pull back information or taking action in any of those downstream systems if I wanted to. So one of these tools is going to be able to look into, for example, NetSuite and pull back things like our accounts payable information. They'll also be able to be a tool that's going to make use of the NetSuite SOAP API to pull back our budget information as necessary, as well as a tool here that can look into HubSpot and actually pull back campaign information. So what my agent has is access to a lot of different tools and a few different systems to start being able to build out and pull in data from multiple different sources, which can really help when we're looking to do maybe some additional analysis in some of this financial data. So let's go ahead and start chatting with our agent. So I'm going to start with a relatively simple question. I'm going to ask it, can you show me the invoices paid to Magic Marketing over the last six months? So I'm asking my agent to pull back and look into, in this case, NetSuite, the invoice information for a certain organization. And I gave it a time range that I wanted to use when it is searching for that, because it has got that tool that's able to reach into NetSuite. It's going to allow my agent to have that additional contextual awareness about the account's payable data. And so that's data that can now be used by my agent when it's helping to make decisions or maybe running some analysis on that. So we can see in this case, it's come back and pulled back through the last three invoices from the last six months that have been paid and actually broken down what they're including within there as well. Let's go ahead and take this to the next level. So I'm going to ask it, what is our marketing budget for the year? So I want to start doing some analysis on this data now. I want to see what is our current marketing budget that's been allocated that currently sits within NetSuite. So it's going to use that tool that's going to be able to reach in and pull back the specific budgeting information for the marketing team. And we'll be able to compare this with some of the data that we're pulling back. And so as we can see, our agent has come back and pull back our marketing team's budget for the financial year, broken down onto the individual months accordingly there as well. So now what we've pulled through is we've pulled through our budgeting information. We've got some information around the invoices for one of our marketing consultancies. Let's go ahead and ask our agent to do some interesting items. So I'm going to ask it to run a cost analysis on our current campaign spend against these budgets and summarize each month in a table. So I wanted to pull in and use this data from these various different sources and actually run some analysis on this data as well. So we're pulling in, I'm going to reach into HubSpot now using that tool to pull back the campaign data, get an understanding of that information. And hopefully our agent is going to be able to bring all of this together and provide some helpful recommendations against how our marketing budget is doing and our overall spend so far. And so as we can see, we've now got a nice breakdown of our kind of campaigns that we've run, their overall spend, the variance against our budget from this analysis, which is really fantastic. And we can also get some key insights around these different items as well. Let me go ahead and include that invoice data in there as well. So include the marketing, include the Magic Marketing invoices as well. And so we can add in some of this additional insight into this analysis that is running as well. And so as we can see now that we've added in that invoice data as well, we can see it's updated our analysis that we're running. Some updated key insights and some critical observations around how at the moment things look like they're trending upwards from a spend perspective. Let's go ahead and actually make this into something tangible as well that we can maybe share around. So please create this as a Grafana dashboard for us. Create a visualization with this data. So not only is our agent able to pull in this data from multiple sources, it's actually able to take action with this as well. So as you can see, our agent here has gone ahead and created us and taken that action to create us a visualization of this budget analysis that is just done. And if you take a look at this link here, what we should be able to see is that information now showing up for us in a nice dashboard for the information around how our information has been spent, how our budget has been allocated for us, which is great. Now let's go ahead and send this to our marketing team as well. So can you send this to the marketing team as well, please? And so what we can do is we can let the marketing team know about our budget analysis. As we can see, our agent has gone ahead and taken and sent this as a notification to our marketing team so they can get an understanding of the budget. So if we head on over to Slack, what we should see is some important information around the analysis that's been done, including a link for the visualization dashboard that's just been created for that piece as well. So as we can see, just through a very simple conversation with our agent, we're able to do some really good analysis and our marketing budget by looking into our NetSuite for our accounts payable information, looking at our budgets, adding on that extra layer of information from some of the core systems that our marketing team use as well, like HubSpot, which has got all of our campaign data in to be able to bring this all together and do a really nice comprehensive analysis for us. The agent was then able to take that action, actually create this as a visualization for us, and then go ahead and send that to the relevant team so they can take any necessary action and just be kept in the loop here as well. This will help save a tremendous amount of manual effort and time from needing to go through and look through all this information in the various different places and run the analysis manually in that case as well. As you saw, Merlin Agent Builder not only provides instant and clear budget insights, but also takes proactive steps on your behalf, significantly reducing manual efforts and enhancing your strategic decision-making capabilities. This is just another example of what's possible when you build on one platform for every agent. The market is flooded with what everyone claims to be AI agents, but not all agents are created equal. Simply providing information through AI is not an agent unless that agent is able to take complex actions on the user's behalf, but of course with guardrails in place. Today, I'm going to show you how an AI knowledge agent built on Merlin Agent Builder can not only provide intelligent and thoughtful responses, but can take complex actions across multiple systems. Let's go ahead and take a look at this agent in action then. So I'm going to start with my initial prompt. I'm going to ask it: I wanted to go ahead and take a look at the last six months of tickets related to feature x because we want to go ahead and update our FAQ page. Now what we've got here is a site that's got a relatively straightforward set of FAQs. So you can see that it's just common technical questions and technical responses. But what I want the agent to do is go ahead and look at the last six months of tickets that exist within our Jira instance. And it should take a look and compare that against the current FAQ page to see if there's any improvements or extra pieces of information we can use to make sure that it's kept up to date in line with some of the challenges that we're seeing being asked the most frequently. In this case, we can see the agent's come back. It's completed its feature analysis and has taken a look back at around a hundred tickets and has summarized it really nicely for us around the different areas. Some of the recommended FAQ updates because it's taking into account the current FAQ page and provided us some recommendations for things to improve as well. But it's also asking me for the ability to take some action here as well, which is great. So being able to take this knowledge and actually take that a step further and take some action, whether that's updating the FAQ page with a new content once approved or creating a Google Doc with the full analysis and proposed changes. But I'm going to ask it to go ahead and update the FAQ page, please. And we'll see how the agent is now able to actually take action and actually go ahead and update this FAQ page with new information for us too. So you can see the agent's come back and completed all of its actions. So it's taken those two actions of one updating our FAQ page. So if we take a quick look at the current page, and we can give that a quick refresh, we should see that it's now got a much more detailed set of responses to some of these based on some of those common criteria found across our ticket. And our agent has also created for us an update summary document as well for internal analysis. So we can see kind of what it took into account. Obviously, this is different from the public facing FAQ page, but it gives us an idea of the recommendations and where they're stemming from, things like the actual load and the tickets that are analyzed there as well. Let's take a look at a slightly more intricate example. So I'm going to ask my agent to go ahead and take a look at some analysts briefings that we've currently got sitting across a wide variety of document formats in our Google Drive folder. We also want it to go ahead and take a look at some areas for improvements against our competitors based on that. Then I also want it to have a take a look into our Productboard feature request to see if we've got common requests from customers that align with some of these improvement areas from those analysts briefings. So let's go ahead and take a look to see how the agent is able to crunch this data from a wide variety of data sources. And we'll see in just a moment how it's also able to take action on that data as well. And so we can see the agent has come back after conducting its analysis and has broken it down into the key product areas from the scoring and also identified a few areas for improvement where the score might be slightly lower. It's also gone ahead and correlated that against some of the Productboard feature requests, providing a link through to some of the notes that they're related to. So we can see that cross correlation that is done there as well. Now we can also see at the bottom here, it's asking us if it wants to go ahead and take some action so we can go ahead and create a detailed product plan for us and also creating a new Jira project. So I'm going to go ahead and ask it to please create this as a Jira project. And so what we'll start to see is the agent is, again, able to take action with this knowledge that it's done. So it's done that analysis, and now it's going to take that data and create that as a new Jira project for us with all the necessary epics, assigning timelines to each individual area so that we can start assigning issues to each section as well. And so in this case, we can see it's gone ahead and created us a Jira ticket for all of these initiatives. So we've got our PEI. What we'll also see is that it's gone ahead and posted this as an update in our product updates channel as well with a link straight through. What we can do is if we click onto this, we should see this created as a new project Jira instance. And if we take a look at the timeline, it's broken down those key areas and associated sometimes with that, things like the security and compliance sprints, the platform reliability, and the integration capabilities. Again, all of these are items that are analyzed as things that needed improvement based on that analysis that has been done. So as you can start to see, the agent's really powerful in not just having access to a wide variety of knowledge sources, but also being able to take action with that data as necessary as well. Now if you were to using a product born as an enterprise search tool, everything you saw wouldn't be done by the agent. It would be done by you. Without the ability to create powerful tools that can take action in a low code manner like you get with Tray, search tools will be able to surface loads of data, but you'll be left to figure out how to take the appropriate action on the other side. The Merlin Agent Builder allows you to take your agents to the next level. And the agent shown today is just one example of what's possible when you build on one platform for every agent. Every week, teams lose hours pulling data from different systems, cleaning it up, and manually building reports. What if all that work could be handled by an AI agent with speed, consistency, and zero copy and paste? With Try's Merlin Agent Builder, you can easily build this week's performance dashboards across marketing, sales, product, and a multitude of other data sources as you see fit and allow your agent to take action by creating that as a helpful visualization in your visualization tool of choice. Let's take a look at this agent in action. So I've configured my overall agent scope here about what the agent is going to help with, and I've also selected the model that I wanted to use. Most importantly for this use case, I've also got the set of tools that I've given my agent access to. So these are the various places that it's going to be able to grab data from so that we can do additional analysis on top of that when we're interacting with our agent. So some of these will be interacting with our CRM to be able to pull back opportunity data and contacts, interacting with HubSpot to be able to query campaign data. We've got some data sitting in Redshift around NPS scores and web analytic data as well. And all of these have been added as tools that my agent has so that it's able to pull information from those systems. Let's go ahead and start chatting with our agent and take a look to see how it's able to use those tools to help us do some analysis on that. So to start with, I'm just going to simply ask it to look at the open opportunities that we have, including the contact information and summarizing it for me into a table. We'll take a look to see how the agent's able to help with this. In this case, it's going to be only reaching into the single system, that CRM, to be able to pull this back. But we'll see in just a moment how we can augment that with information from the other systems as well. And so we can see the agents come back and it's provided for us a really nice summary of the currently open opportunities over the last few months, including things like the contact information that we requested. But you'll notice again the source is just that single sales Salesforce CRM lookup tool that we've added to our agent. So that's great. Let's go ahead and take a look at how our agent is able to actually pull in the information from the other system so we can do some more in-depth analysis. So I'm going to ask it to also add in the interactions with any campaigns, such as looking to HubSpot for that campaign data for each of the contacts that is just pulled. I want to also augment that with some data on page views from our web analytics that sits in Redshift, and then also flag any of these that have provided NPS scores that might be at risk as well. So looking at three additional data sources in addition to this data that is already pulled back. Let's take a look to see how the agent is able to bring all of this data together and run some analysis across these various data sources for us. And so you can see once again, the agent's been able to come back and actually compile some additional information into our view here. So it's included in information around the recent campaign activities, the NPS scores, and then also analyze which ones might potentially be at risk, and then run some analysis for us at the end here about those that might be requiring some additional attention. You'll notice that from the source's point of view, we've now included in four different ones across the various systems that we've got. You'll notice that my agent here is suggesting that he's able to go ahead and create a the Grafana dashboard for us as well. Of course, it's great to have this in this interface, but what's really powerful here is my agent is able to actually take the action and create this as a visualization in my visualization tool of choice based on this dynamic data that we've just pulled back from these four different systems. I'm going to go ahead and say yes, please, because I wanted to go ahead and create us a Grafana dashboard, and we can take a look to see how the agent's able to take that action for us as well. As we can see, the agent's come back, and it's gone ahead and created that dashboard for us, which is fantastic. So we can see that it summarized what it is, but it's also provided us a link. So let's take a look through and see what it's created for us over in Grafana. As we can see, it's come up with a really nice set of summary. We can see the campaign engagements. We can see the at risk ones, the total opportunity value, and it's been able to dynamically create this based on the data that we just interacted with our agent for across these various different systems and has built this on the fly for us by being able to take that action. So as we can see, it's really powerful allowing our agent to be able to not only pull in the data from a wide variety of data sources, interactively chat with us and allow us to analyze that information, but then also take action with that data as well. In this case, we created that visualization and dashboard, but this could also extend to multitude of other actions as well. And that's where the real power of the Merlin Agent Builder comes in to allow you to take those really impressive actions with your agent, not just reading in that data. This is just one example of what's possible when you build on one platform for every agent. How many support tickets in your queue could be handled without a human? Today, we're showing you a customer support agent built on Tray Merlin Agent Builder designed to resolve common requests like refunds and upgrades automatically across your systems, all from within a single conversation. Let's go ahead and take a look at this agent in action. So, I've got my website here and let's say I want to get some support from the customer support team. I'm going to go ahead and message the agent down in the bottom right section here. Let's go ahead and ask it a question. Let's say I've noticed a duplicate transaction in my account. So, I'm going to ask my agent to go ahead and if it's possible to refund that for me directly. In this case, the agent has a few tools that allow it to take action such as processing a refund when it makes sense and also being able to reach into our payment provider. If we take a quick look at our payment provider, you will notice that there is actually a duplicate transaction in here. So, the agent should be able to pick that up and we'll see how it responds to that. And so, in this case, we can see it's come back and it's gone ahead and actually noticed the two duplicate transactions as well as the dates. And it's asking us just to confirm that we want to go ahead and refund that. So let me go ahead and say, yes, please. We want to process that refund. We'll take a look to see how the agent is able to take the action here and actually go ahead and refund this transaction for this user all without needing to bring a human into the loop at all. And so in this case, we can see that the agent's come back and it's successfully been able to process that refund. If we come back over to our payment provider, we'll give that a quick refresh just so we can double check, and we should see that one of those transactions is now refunded just here. Now let's take a look at a slightly different example. Let's say I want to go ahead and upgrade from the basic plan that I'm currently on to the Pro plan. So I'm going to ask my agent, can I upgrade to the Pro plan, please? And let's take a look to see what the agent does in this case. Again, it's got a tool here that's able to go ahead and pull up our current subscription information as well as go ahead and process a new one. If we look at our payment provider, we can see that currently John Smith is on the basic plan. We can also see that he exists within our CRM on that basic plan as well. And so we'll take a look to see how the agent is able to upgrade that and make sure that all of that is attributed and taken action in all of those downstream systems as well. And so, in this case, we can see it's come back firstly with some helpful information around my current plan and what the new plan includes as well based on its available knowledge and its knowledge base. And it's just asking me to double check and confirm that I want to upgrade. So I'm going to go, yes, please upgrade me, and we'll take a look to see how the agent is able to actually process this and take action with it. And so we can see the agents come back, and it's actually gone ahead and successfully upgraded the plan for us. It's also provided us information around the pro rata amount, and it's also created a ticket for us to have an overview of this whole process. We double check on over at our payment provider. We should see that that John Smith has now been upgraded from the basic plan up to the Pro plan. If we take a look at our CRM system, we should see a new opportunity that was created again for this new pro plan upgrade. And then we've also sent across an email confirmation to the user as well. Now, of course, one of the things we also did do is we maintained a ticket for all of the interactions that have taken an action in here. So, that includes both that duplicate refund as well as the upgrade to the Pro plan so that our team has that visibility for that. So as we can see, the agent has a ton of tools here that are available to it to use to not only provide a suitable response but actually go ahead and take action there, whether that's being able to use the tool that's going to help us update the subscription, process refund requests. There's a lot of power that you'll have with the Merlin Agent Builder functionality to be able to not only have your agent respond accordingly, but take any necessary actions that you might determine as well. This is just one example of what's possible when you build on one platform for every agent. In today's fast paced environment, teams waste countless hours manually performing repetitive tasks. Merlin Agent Builder is here to change that, empowering you with an intelligent AI agent that automates recurring tasks by leveraging customizable prompts and logical workflows. Today, you'll see how this powerful agent automates the daily delivery of industry news and generates fresh campaign ideas directly within Slack. Let's jump in. Let's go ahead and take a look at the different parts of our agent here. So I've got my agent scope, which allows me to define the overall instructions that I want to provide to my agent, what I wanted to help with, what it's designed to help with, and any additional guidelines I want to pass along. I've also got my AI model selected down here, and that's that's easily changeable in just a couple of clicks if I wanted to. But most importantly, my agent has a set of tools here that has been configured with to allow it to achieve a few different use cases. In this case, it's been grounded in information in its knowledge base around who it's part of as an organization, in this case, Acme Corp, which is a consumer electronics organization. It's got a tool here that's able to reach out and pull fresh news articles. So it can help with things like summarizing some of the key trends that it might be seeing, as well as a tool here that's able to reach into our project management tools so it can take that next step and actually take action and create us some tangible project plans if we wanted to as well. But let's bring all of that together and take a look at it in action. So I'm going to ask it, what is my daily briefing? And what we'll see here is that it's able to go ahead and look at those news articles that might be relevant to us in the organization that we're part of, in this case, Acme. It's going to highlight and summarize some of those key things. So instead of me having to manually go through tons of news articles, it's going to be able to pull out those main things that might be of interest to me, those key themes. And that might be something that I want to take forward and potentially maybe make into a campaign idea. And so as you can see, my agent's come back with a couple of pieces of information. So you can see it's come back with some competitor updates. So again, we're in the consumer electronics space. So it's been able to pull back some really helpful information for us on some of our key competitors in that space and some of the things that they're releasing. It's also highlighted some industry trends that might be really interesting. You know, things like extended battery life really becoming a key differentiator. It's also highlighted for us some potential campaign ideas. So things like emphasizing battery life and sustainability or highlighting unique biometric security features. And so it's also highlighted that as a key theme summary, which is great and provided us with those sources. And we can go ahead and take a look at these if we wanted to. But again, instead of me spending all of that manual time looking at some of these, pulling out the relevant competitor articles, it's really nicely summarized this for me here as well. But let me go ahead, and I'm really interested in expanding on that campaign idea of focusing on AI integration and smart home innovation. So, obviously, we've got some competitive articles that have come back here. So now I want to take that to the next level and actually create a campaign around that to highlight some of the AI features that Acme has as part of their consumer electronic devices. So in this case, I'm going to ask it to create me a campaign idea for focusing on AI integration, please. We'll take a look to see how the agent is able to help with this piece as well. It's going to take these news articles and industry trends that its highlighted and actually create a tangible campaign idea for us. So as you can see, it's come back and really created us a nice tangible campaign objective. So the overall idea there highlighting that AI integrated product ecosystem that we have based on some of those industry trends and some of those recent competitor announcements that we want to get ahead of. It's also positioning us as a leader in the intelligent community of consumer electronics space. So it's taken all of that into account, those fresh news articles, who Acme is as a company, and actually created us a really nice campaign overview from that as well, taking into account those various sources and broken that down into a few different key areas and timelines for us. Let's actually go ahead and take that to the next level. This is great. It's provided me with the summary, but now I want to create that in our project management tool. So I'm going to ask it: create this as a project plan for me, please. And we'll see how it's able to actually take that next step and actually take action and create this as a nice detailed project plan for us, in this case, in Asana. As you can see, our Agent come back and created us that nice campaign over here in Asana, which is great. It's broken it down into key areas, and it's provided us that link. So let's go ahead and take a look at that project that's been created for us. And so you can see it's come back with its overall overview. So the main goal of our campaign, the list that we've got. So it's actually broken it down nicely into these different subsections for us, which is fantastic on this campaign that we want to run. And it's also if you take a look more closely at some of these items, it's actually created those with blocking points as well, so certain tasks that need to be created previously. So as we saw, we started off with just getting that high level summary on some of the key industry trends that we were interested in and how it was able to bring that in from various sources and ultimately provide us with that high level summary so we don't have to troll through tons of that, but actually made it more bespoke and tailored to us as an organization. It highlighted some key themes that were of interest, in this case, the usage of AI and some of those smart home devices being released by those competitors and brought all of that together nicely for us to create that campaign, taking that final step and that final action to actually go ahead and create this in our project management platform for us as well. As you saw, Merlin Agent Builder not only provides instant and clear insights, but also take steps on your behalf, helping us create, in this case, that detailed campaign project plan in our project management tool, significantly reducing manual efforts and enhancing your strategic decision making capabilities. This is just one example of what you can build on one platform for every agent.