I'm so excited to be with you today, to provide an update on what we've been building recently and how the next six to twelve months looks like in terms of innovation. I'd like to start with an update on our platform. The Coveo platform is really a composable AI search and generative Experience Platform that supports now semantic search. AI recommendations generative answering, which is critically important, and we'll dig a little bit deeper, on that in the second part of the presentation. And, of course, unified personalization. We power multiple use cases, as most of you know, across websites, commerce, service, and workplace. So that's our engagement in app layer. And we leverage content from a wide variety of data sources and content sources with our native connectors with our, custom connector frameworks. And also, we leverage behavioral old data from various data sources too, and we capture a lot, on our own. So we have this connector layer, and we also have this Unified index that now does both keyword search and semantic search with the ability of keeping vectors or embeddings directly within the index. We have multiple AI models around machine learning, deep learning, and now the ability to deal with generative AI and large language models and we have a whole set of API frameworks and native integrations to allow us to integrate with those various cases at the top. So we have analytics, finally, and a whole set of admin tools. If we get into the details, you will see that those in the middle, those different AI models around machine learning, deep learning, and gen AI. And I wanna highlight also those native integrations around Salesforce, around SAP, around Sitecore, around Adobe Zendesk that we maintain to make those, Coveo integrations more natively integrated. We have use cases extensions like merchandising in the context of commerce, also, and then whole sets of Way to build dashboards and administer the platform. So this is our broad platform, and our large customers will leverage multiple use cases from those platform, multiple components of those platforms. But this platform is built on the same core principles. As always, we position ourselves as the intelligence behind. While we can build and use our experiences, most of the time, we are behind the experience. From an API perspective or native integration perspective. We aim at high scale projects with a focus on behavioral data so we can build specialized AI. And we do all of this with yet most respect for privacy and security. So I'd like to, I'd like to now move on the generative AI side and, provide an update on what we already announced, earlier this summer about our GenAI initiatives. So most of the large organizations that customers, out there, have either are using Coveo AI have a form of advanced enterprise search capability inside their organization. So this is Coveo here on the left side that you see where there's all of this connectivity layer that allows the platform to reach all of the areas of their organization where there's high value content. So We have an index, and we have advanced, AI relevance to power great results search box. And with, of course, different UI frameworks, administration, and analytics. What we've seen since the beginning of the year is some areas of those organizations have been experimenting starting those projects, those question answering projects that would involve a separate vector database to power semantic searches and Dan to ground a prompt and ask a large language model to provide an answer. While this may work in niche application, this brings multiple issues. For the enterprise. The first one is that by doing this, you have different search boxes to go after the same content basically. So on the left side, that's the surge box that people are used to. Know and are familiar with. And on the right side, this is a question answering system that doesn't have the ability to reach all of the content, all of the the information of the organization, and that quite frankly has little to no admin situation, no dashboarding, no analytics, limited security, and so on. So big deal at the end of the day is Those two different search boxes for the same question will provide different results. So that's bad because they're dealing with different set of facts. So what we have done is consolidate those two systems into a single one. So now with Coveo, We've got integrated search and question answering. The left side of this, of this slide is still the traditional advanced AI powered search, but then we've added vectors, as you can in the middle within the index so we can do semantic search and basically deal with complex questions. The most relevant excerpts or passages from the result set from the semantic search will then be used to ground, prompt to a large language model. Currently, we're using, GPT three dot five on our Azure infrastructure, and this allows us to keep the data of our customers within the Coveo cloud. So the advantages are obvious from a back end perspective. So we have death, breath, and freshness of content. Their security and governance that comes with the Coveo platform, administration analytics, and it's optimized for scale and cost. On the front end, there's an obvious advantage at having one unified search box for all the queries questions, and we think it's now an intent box There's their generated answers on the most relevant paragraphs only if we believe that a generated answer is bringing value So there's personalization, contextualization that comes with the Coveo system. And then we have, we have all of the capability to link to the source of truth. So there is truth, it's truthful, current, and verifiable lineage. So All of this, provides basically maximum protection against hallucination in the context of large language model. That's key, especially in the enterprise. So at this time, what I would do is, show you the system in action with, which real demos. So I will start with, customer zero. Customer zero is, is Coveo. It's our own partner, community that includes technical documentation how to, and basically calendar of events, basically everything that is useful and, informative for our own partners. It starts with a surge box here. So I will I will search things like if I search for Service Cloud, you can see that I have query suggests here. Is based on AI that is predictive, and provides, provides query completion. If I search for it, I have results here that are ranked by relevance, and I have facets allowing me to slice and dice the content. Okay? So this is the advanced AI search and recommendation, paradigm. But let's say I want to, ask a question. How does Coveo determine relevance? For instance, So again, I have the results set here that came, very quickly, but out of those results, We at the semantic search will surface the most important passages or excerpts that are then used to ground A call to a large language, a prompt to the large language model, which Dan provides an answer. And the answer here is great. It specific to Coveo, it's build based on those results at the bottom. Let's get a step further. Let's type how does Coveo leverage permissions? That's an interesting question. Because I know, that we leverage permissions differently depending on the environment and depending on the product. So that's a great answer. That's a detailed answer. But then maybe, I wanna be more specific and I wanna click and understand how this could be leveraged permission in the context of Salesforce. And there you go, The answer is contextualized in real time with Salesforce, about Salesforce. So the answer is about Salesforce here. So that's quite powerful. Obviously there are multiple attributes that can be carried within a user profile and those filters can be, can be set at, at log in. We are leveraging a generic large language model. The only thing that we do here is creating a prompt on the fly based on the context, what I see, what is used in terms of relevance and what is, what is filtered. There are multiple there are multiple ways to look at the source of fruit. Here, we've got the citations here. So these are the key documents that are used to for determining the answer And that's part of this part of this document that the system extracts the most important passages that are then fed again to the large language model. Let's try another one here. Let's get a step further and let's compare feature by feature, two modules of Coveo. So the sitemap and the web connectors are used by our partners to index web content. Which one which one should they use and when? So if I compare feature by feature, the sitemap and web connector, basic I see through prerequisites, content coverage, indexing speed, the differences between those two different connectors, which is quite powerful and, and interesting here. I can get into, more answer styling, explain in detail something, that is, that is quite advanced, comparing two different UI frameworks, the Coveo headless, an atomic and when to use it. So you see that it can go, it can go pretty much in detail here. And then this one is cool. So for you in the audience where maybe English is not your first language, What about querying in another language against English content and getting an answer in your own language? So this one here is in French, comma function and query pipeline. Basically, it is how does query pipeline work. Okay? So if I search for this, so what it does is it sends it sends to, to the large language model, the best excerpts from those results here at the bottom that are in English, by the way, And then the answer is returned and translated automatically in French. And, While this is a, this is a, more of a, I think, a niche use case at this point, It proves the power of the model and of the system and where this can go in the future with instant translation from both on query and the result side. And finally, I'd like to, I'd like to do this last one, which is, which is the best one as far as I'm concerned. How to create a partner organization Oh, I don't have a result here. I don't have an answer. Sorry. Why is that? Oh, because I'm not logged in, and this content is not available for anonymous or public audiences. So let's log in, and let's log in as art on our partner community. And let's do the same query here. And there you go. I've got great result. A great result here because I'm logged in. So that's a great way to enrich The search experience on our partner community, leveraging all of the information has already been indexed the security and permissions that are already in place, the wide and broad variety of content is in there, and the contextual nature of search So we're leveraging search and facets to slice and dice content, reorder content filter content, and then that's what we leverage to create great answer. Now I I would also like to show, a real customer that has recently gone live on their support portal. That's zero. So zero serves three point seven million subscribers. So small and medium businesses around the world, and it's all about providing predictive support, directly from their directly from their support portal. So Coveo has been part of the Xero experience for a long time, but recently they added generative answering directly on the portal. So I wanna show you a few examples of how it looks like. So If I start with a complex query like how does multi factor authentication work with zero, We see that the answer is pretty detailed. And again, it comes from the multiple results that are at the bottom here that are provided by that are leveraged by search or provided by search. Let's say, how do I update my subscription payment details? Those are real queries that users typically have. With zero. So there you go. You've got the answer right away. And maybe a last one. How do I had How do I add a credit to an invoice? There you go. Detailed, precise relevant answer, no need to go through multiple documents and come up with your own answer. So that's live. Xero is doing a great job on their support portal, and we're quite excited of, of this implementation So going back to the presentation, I'd like to give a glimpse of our future capability please provide a little bit of, outlook of what we think is important as next step. So answer styling is something that, will appear very soon. So the ability to ask for broader answers, step by step, bullets, and so on. This is, this is coming very soon. In line citations, this is something that we will provide to with citations details, of course. Conversational search is super strategic for us. So the search box for us is the universal away for users to interact with information. So we wanna make this conversational. With the answer provided by the, generative answering, We are going to have a follow-up, box here directly within the answer so the user can have a dialogue or a conversation with the system. And then we will also provide suggestions about what to ask, how to ask, and so on. So this is, this is coming in early twenty four. And finally, in the context of commerce, we are experimenting with what we call guided discovery. Where, some some of our large customers have a lot of rich content about buying guides how to, and, those types of this type of knowledge that typically enriches the commerce experience. So this is an experiment that, we are doing, and we're expecting if there's if it creates the value we think, we're expecting that this will become, this will become a product in the future. So the example here for a home improvement store. The example here I'm typing is tips to build outside kitchen with a barbecue. So the generative answering will look at all these buying guys and how to documents, and surface an answer that is, pretty darn good. So It provides various, various tips and various steps that need to be considered, but also we're going to provide links to products directly in there. So it's really a way connect the generative answering with a product catalog in the context of commerce. Basically, it's a new way to shop and it's a new way to buy. And then we will have top categories that are linked to that answer. And we will have the ability to navigate slice and dice and get more into a classic commerce experience where you want to navigate shop discover, by yourself products. So connecting those two experiences has for us, huge value. And, we expect this to move forward in the coming months. So as a summary in closing, I'd like to also say that all of those generative AI experience need to consider, cost large language model and semantic search are expensive technologies in terms of computing So, cost matters. Trust is not an option. So all of the data, all of the content from a from a large organization cannot go outside to an external large language model system. There will be domain adaptation and open source domain adaptation means that there will be fine tuning. We believe of those large language model in certain verticals, certain industries, or even certain organizations. But, therefore Coveo will be a large language model agnostic. Today, we're using, a Azure hosted OpenAI GPT three point five, but down the road, we expect to be able to connect with multiple alternatives And finally, in the end, we believe that any systems will require relevance across all content and all interactions. Therefore, that's why we built this platform.