Googles 6 NEW AI AGENTS Takes The INUDSTRY BY STORM! (Google Gemini AGENTS)

so 2024 is the year of agents and Google just hit the scene with an amazing update because they just announced these six agents that they are going to be continually working on for the rest of the year and into the future you can see customer agents employee agents creative agents data agents code agents and security agents and this video is going to show you some of the demos that Google actually recently talked about that are quite impressive and it seems that we're gearing up for a year of Agents as we previously talked about so with that being said let me know which of these agents you're going to be most excited for in the future now let's look at the types of Agents customers are building on Google Cloud using generative AI first customer agents you know similar to great sales and service people customer agents are able to listen carefully understand your needs recommend the right products and services they work seamlessly across all your channels the web your mobile app your point of sale and your call center and they can integrated into product experiences with voice and video mercedesbenz is working with us on customer agents to help people in their amazing cars let's hear from their CEO Ola at Mercedes-Benz we want to offer our customers an exceptional digital experience that's why we're equipping our cars with high-end computers each car should only get better over time just like a good wine and with the power of Google cloud and AI we will make the user experience even more personalized our partnership across Google helps us build more intuitive and customized experiences last year we announced our partnership with Google Maps and today more than 3 million customers are using Google places in their Mercedes cars and we are applying Google Cloud AI across a number of other use cases ranging from a smart sales assistant improving customer service in our call centers and optimizing our marketing the sales assistant for example helps customers to seamlessly interact with Mercedes when booking a test drive or navigating through mercedes's offerings to find their next favorite vehicle and now we're exploring further opportunities to work with Google Cloud AI such as Next Level navigation features in addition we're partnering on one of the most exciting technology topics in our industry automated driving this beautiful car right here is equipped with a level three system for conditionally automated driving we were the first manufacturer to get it certified in Germany California and Nevada for our next Generation internal development and test platform we will use Google Cloud as the backbone helping us to become even more efficient and flexible in our product development and Google Cloud's expert knowledge in processing massive amounts of data and scaling AI workloads will ensure that our cars get even more intelligent and AI driven partnering with the very best in their respective Fields is an important part of our software strategy and Google is the perfect example of that with Google Cloud Mercedes-Benz is building new ways to deliver the most intelligent vehicles to our customer customers and to create personalized intuitive experiences we're really excited about working together thank you for having me thanks Ola and team in addition to these great Innovations we're very excited to collaborate with Mercedes bands and work towards bringing Gemini models to their inv vehicle conversational system another great example is Samsung who's deploying Gemini Pro and imagine on vertex AI to the Galaxy s24 smartphones users can now take advantage of amazing features text summarization organization and magical image editing Gemini Pro also provides Samsung with critical Google Cloud features including security safety privacy and data compliance we're inspired by the agents customers are

creating using our gen generative AI platform and our models InterContinental Hotels group will launch a travel planning capability to help each of you their guests plan their next vacation ADT is building an agent to help customers select and set up home security systems Verizon gives agents better recommendations magalo one of Brazil's largest retailers has put generative AI right at the heart of its customer service ing built a chatbot to enhance self-service and improve answer quality and Target uses AI on the Target app and website to personalize offers for Target Circle and Starbucks at drive up Minnesota's Department of Public Safety helps non-english speakers get licenses and other services with real-time translation Best Buy is building an assistant that will help troubleshoot product issues reschedule or combine order deliveries or manage software discover Financial Services is using search and synthesis across detailed policies and procedures during customer service calls and oranges French language agent is grounded in support knowledge trans transforming their help and contact site and their customer experience Oppo and OnePlus leaders and smart devices are incorporating our Gemini models and Google Cloud AI into their phone to deliver Innovative customer experiences including news audio recording summaries AI toolbox and much more you know the opportunity for customer agents is tremendous to help each of you build customer agents faster we're introducing vertex AI agent Builder you can now create customer agents that are amazingly powerful in just three key steps first you can use Gemini Pro to create free flowing humanlike conversations with text voice images and video as inputs and personalize them with custom voice models second you can use natural language instructions to control the conversation flow and guide it on specific topics you don't want it to discuss such as current events in the same way that you train your human agents you can also control when it hands over to a human agent with transcription and summarization of its conversation history to make these transitions extremely smooth third can improve response quality with vector-based and keyword-based search to connect your internal information and the entire web you can also use extensions to complete tasks for customers like updating contact information booking a flight ordering food and many more and you can integrate Enterprise data from operational databases like allb Predictive Analytics with big quy and SAS applications like service now let's take a look at an example of a customer agent in action please welcome developer Advocate Amanda Lewis thank you Thomas so last night I was watching a video of this band and I love the keyboard player shirt so I was thinking I'd really like to be wearing that shirt tomorrow night but can I find it in my size and in time to be rocking it at the concert here in Vegas let's head over to my favorite store simple fashion they just launched a customer agent and it leverages Gemini and Vector search to deliver a seamless shopping experience what can we help you find well I'd like that shirt but I guess I have a few other specifications as well so find me a checkered shirt like the keyboard player is wearing I'd like to see prices where to buy it and how soon can I be wearing it going to include the video now the customer agent is using Gemini's multimodal reasoning to analyze the text and video to identify exactly what I'm looking for then Gemini turns

it into a searchable format okay how cool is this it found the checkered shirt I'm looking for right and some other great options in no time and that's because these results harness Google's trusted search Technologies which ensures customers like me get the right results in record time the suggested products are grounded in Syle Fashions inventory and historical performance data to make sure customers leave happy and with that purchase in hand okay the first one is perfect it looks like I can have it delivered in 4 days or pick it up nearby today like I said I want to be wearing it tomorrow night so I'm going to go with the local store to be safe of course it never fails they only have three left in my size I don't want to miss out on wearing this shirt so I'm going to go ahead give the store a call and ask them to set it aside for me but first let me tell you what's happening behind the scenes symol Fashions customer agent is using Google Cloud's full Suite of AI capabilities to offer customized support interactions you know facilitate transactions like purchases and returns and ensure that I'm receiving the most up-to-date information in real time I'm so close to having this shirt for the concert let's give the store a call hi there this is the symbol fashion customer agent at South Las Vegas Boulevard am I speaking with Amanda yes this is Amanda great thanks for reaching out Amanda I see you had a session on another device I've sent you an SMS message with a link to our live chat companion if you would like to switch to chat please click the link how can I help you today I I'd like to purchase the shirt in my cart with the cart I have on file absolutely I see you're also a symbol fashion Rewards member looks like you have a 20% off voucher available to use would you like to apply it to this purchase yes please that would be great the shirt you're purchasing goes well with these items also available for pickup in your preferred size would any of these be interesting to you absolutely please add the white shirt and the boots to my cart great your total is $23. 76 okay to proceed with the card on file yes your purchase is confirmed do you need anything else today no I'm all set thank you incredible thank you for shopping with symbol fashion you'll get a text when the items are ready for you in less than 5 minutes I was able to find and order the shirt I wanted and an outfit to match I'm ready for the concert back to you Thomas many of our customers are building employee agents using Gemini for Google workspace and vertex AI to help their employees be more productive and work better together for hundreds of millions of people around the world Uber is an essential mobile app that makes it easy to get a ride or home delivery there are many complex processes that must run smoothly behind the scenes for Uber to keep providing its magical user experiences generative AI opens up opportunities across all parts of our business but the opportunity I'm particularly excited about is developer and employee productivity our partnership with Google cloud is helping us create a stronger and more empowered Workforce Gemini for Google workspace helps us save time on repetitive tasks frees up Developers for higher value work reduces our agency spending and enhances employee retention we're also using Google Cloud's AI platform to build our own AI agents to help our support teams better help our customers for Frontline support we've launched new tools that intelligently summarize user Communications and surface context from previous interactions anything that helps our teams go faster helps our platform go faster so our customers can get where they want to go or what they want to get delivered all at Uber speed with Google Cloud Uber's creating new ways to empower Workforce and better serve our customers thanks for having me Gemini for Google workspace is our AI powered agent built right into Gmail docs sheets and more Gemini doesn't just help our customers be more productive it's a member of their team need a quick answer on something just ask Gemini

need a world-class notetaker in an important meeting bring Gemini along need insights from a dozen analyst reports Gemini is your research partner customers really appreciate the quality of output that gini for workspace provides More than 70% of help me write users in Google Docs and Gmail accept giz suggestions and more than 75% of people who have created images in slides insert them into their presentations we're seeing the impact of this every day with our customers peine university has students and faculty who speak many languages Gemini in Google meet enables realtime translated captioning and notes PennyMac is accelerating recruiting hiring and new employee onboarding and Woolworths the leading retailer in Australia is seeking to unlock greater productivity for over 10,000 administrative employees by providing them with Gemini for Google workspace now today we have quite a few announcements with Gemini for workspace first many customers have asked for a way to get AI powered Google meet and chat companywide at a lower price particularly to move away from zoom in a recent benchmarking study that tested the top video conferencing applications Google will meet outperformed Microsoft teams zoom and WebEx in overall video and audio performance so we're announcing the AI meetings and messaging add-on with take notes for me chat summarization and realtime translation and it will only cost $10 per user per month second we're making AI powered data protection available with our brand new AI security add-on now workspace admins can automatically classify and protect sensitive files and data using privacy preserving AI models trained for their organization third Gemini and chat can now catch you up on long conversation threads summarize decisions and be a real-time creative partner let's have product lead for workspace collaboration apps Christina be give you a quick look at Gemini for workspace thanks apara there are lots of ways Gemini for workspace is helping our customers save time let me show you the magic of one example in action I've been asked to evaluate two proposals for a new payroll system I open up my drive and I see that there are two statements of work here or SS that outline the vendor proposals Google Drive is AI ready without any additional pre-work and everything here is protected with our industry leading security all I need to do to get started is drag and drop the two files over into the Gemini side panel which is currently in preview in just a few seconds Gemini for workspace will give me an outline of these proposals so that I can have a good idea of what they're about and I could go even further and ask compare the uh the price let's see price of the two offers each page is each of these documents is over 70 Pages it would have taken me hours to review these docs but instead Gemini is going to help me find a clean answer to save me a ton of time and as you can see I have the answer right here in the Gemini side panel let's go ahead and dive into one of these proposals so I'm going to pick this one of the things that you'll notice about Gemini in docs is that it will proactively show me a summary of this file so that I can get a sense of what's going on without needing to take the time to read the whole thing but before I proceed with this vendor I need to ensure that no compliance issues exist and I'm going to be honest I have not memorized every rule in our compliance rule book because it is over a 100 pages I would have to need to scour the 80 pages of this proposal and compare it manually with 100 pages of the rule book so instead in the side panel I asked ask does this offer comply whoops with the following and I'm going to at mention our compliance rulebook hit enter and see what Gemini has to say okay so interesting Gemini has found an issue because the supplier does not list their security certifications because Gemini is grounded in my company's data with Source citations to specific files I can trust this response and start to troubleshoot before selecting a vendor

Gemini for workspace was terrific in this example saving me a lot of time without compromising on accuracy and this technology can be applied in so many other use cases a sales team analyzing rfps a recruiter developing interview questions and so much more back to youa thank you Christina many of our customers are building employees agents to automate workflows that are tedious and repetitive for example Bristol Meers squib is transforming its document processing for clinical trials something that took scientists weeks now takes them just minutes to get a first draft Dasa the largest Medical Diagnostic company in Brazil is helping Physicians detect relevant findings in test results southernland a digital transformation company is boosting its custom customer service by suggesting better responses and automating insights and employee agents can work across people and teams to complete a task one of the nation's leading Healthcare Providers HCA Healthcare is using our generative AI technology to help caregivers spend more time with patients and less on paperwork they're testing Katy so Katy is a nurse handoff digital assistant helping to ensure continuity of care when one caregiver shift ends and another begins it delivers summaries in everyday language to ensure that caregivers can share information easily and provides them up to the- minute patient data to expedite the discharge process it also helps prepare patients for Recovery at home by simplifying post-d discharge tasks like posttop physical therapy and more Victoria Secret in company is looking to help in store associates offer tailored recommendations to customers the Home Depot app called sidekick helps store associates manage inventory and keep Shel stocked Etsy uses vertex AI to improve search provide more personalized recommendations to buyers optimize their ad models and increase the accuracy of delivery dates vertex AI especially when combined with workspace lets you create powerful employee agents first you create a custom model in the ways that we've shown before from there you connect them to all your company and web data this can also be done with translation so that your company information is available regardless of language similarly we support multimodal inputs including videos call Audio images in addition to text now you will want to ground that in Enterprise truth using databases like alloy DB big query and data from Enterprise apps like sap and announcing today HubSpot let's take a look at an example of an employee agent in action please welcome developer Advocate Gabe Vice thanks Lea hi folks so I know you all want to hear about awesome AI stuff that's coming but I need to talk to you for a minute about my annual benefits enrollment see I forgot I have to finish signing up by today and as you can see I might a little bit busy so if you don't mind let's go ahead and look at this open enrollment email together okay yep I've got a deadline I knew that thank you I've got FSA stuff I've got an online portal for my company HR Ben okay there's a lot here uh H they included video let's see if this makes my life easier and the video is ah okay so it's almost an hour long yeah I'm not going to have time to review all of this stuff let's see how this employee agent that we've developed using Google workspace Gemini models and vertex AI might be able to help me as you can see it's integrated directly into my Google Chat so I don't have to contact switch while I'm figuring all this stuff out first things first let's have it summarize the email and the video that it sent me summarize the body and attached video from my recent email with subject open enrollment closing so behind the scenes the agent is referencing that email body and its attachments as context in the prompt using retrieval augmented generation that way its response is limited to the content that matters to me the Gemini models multimodal capabilities allows the agent to understand and reason across text audio and video from a single prompt I mean this is a way quicker read okay good and I can immediately see that the medical plant have been completely revamped this year let's go ahead and jump into the benefits portal to see more now I've already done my dental and my vision but I procras I mean saved the most important plan for

last my medical plan let's see how this option Stacks against my existing coverage compare these coverage options to the PDF doc I have on the Platinum plan the Gemini model's long context window paired with vertex extensions enables the agent to cross reference large amounts of data from a variety of sources including unstructured data like PDFs leveraging Gemini's Advanced reasoning capabilities the agent is able to understand the complex details of my current plan and compare it with the new options for 2025 and since the Enterprise grounding features links me to the exact data that Gemini used to draw its conclusions which you can see linked here I can confidently trust its recommendation that the gold plan is best for me and done so now let's get a summary of my coverage let's say my house is multilingual so I'd like to have it in Japanese also please generate a summary of 2025 benefits in a Google doc in both English and Japanese although my source material is in English the Gemini model support for over 40 languages enables it to understand and respond in Japanese and here we go by engaging with employees in their native language the agent can help everyone feel comfortable navigating their healthare needs for the next year so one last thing now that I've officially completed enrollment my daughter's going to need braces this year let's use the agent to help me find the right orthodontist my daughter will need braces this year help me find the best in network orthodontist near my home with vertex extensions the Gemini model can integrate with any external or internal API this allows the agent to join my dental coverage details directly with real-time Google Maps and places data to help deter determine the best ranked in network providers near me taking a quick look at my options okay so it looks like symbol Orthodontics is the only one that offers Saturday appointments which works best for my family schedule but what do I really know about them how do I know that the agent actually pick the best orthodontists because the Gemini model natively supports grounding with Google search I can see what the agent found summarizing saving me hours of scouring the internet for fresh information the best part is I can get the annotations to see where the information came from which means if I want to look for myself I can I have great places to start and a quick scan of the summary shows me that they're great with kids which is great I particularly love this customer review I'll go with them let's schedule a call I don't know how it's going to find a schedule though I mean I'm here the agent knows that I'm a Google class next because it's integrated with Google Calendar and it can find a time to schedule the call yes please awesome I've got a call do I need anything else nope I'm good no thanks perfect nice and easy just imagine what else an employee agent can help you with thanks back to you partner next up creative agents generative AI is transforming how marketing teams are creating content personalizing it and making real-time campaign adjustments creative agents can supercharge your design and production teams working across images slides and other modalities we're seeing really interesting creative Agents from customers for example car 4 one of the world's leading food retailers is pioneering new ways to use generative AI for marketing Now using vertex AI they were able to deploy car 4 marketing studio in just 5 weeks an Innovative solution to streamline the process of creating Dynamic campaigns across various social networks empowering the marketing teams to efficiently promote products and engage with their target audience in just a few clicks they can build Ultra personalized campaigns to deliver customers advertising that they care about other customers such as canva are using vertex AI to power its magic design for video helping users skip tedious editing steps from dror and gamble is accelerating the development of photorealistic images and creative assets giving teams more time back to focus on higher level plans wpp the creative transformation company built a performance brain using Gemini 1. 5 Pro on vertex AI to power its media activation tool called wpp open media Studio advertisers like the Google pixel team can now see predictions of which ads are going to work the best

before a single impression has been served avoiding millions of dollars of media waste over the life of campaigns now while these examples are about professional creative teams we believe that everyone can be a great Creator and a great Storyteller but the formats and tools for storytelling at work haven't really changed that much how many times have you heard should we start with a dock or a deck well we can do a lot better I'm absolutely thrilled to announce our newest workspace app Google vids sitting alongside Google Docs sheets slides Google vids is an AI powered video creation app for work with Gemini in vids you have a video writing production and editing assistant Allin one let me show you how simple it is to get started with bids now after a full week with all of you here at next I'm going to want to share a recap video to share all the excitement with my organization when I open up vids Gemini helps me get started I simply type in a prompt using an existing document for context now based on that prompt Gemini suggests a narrative outline for the story that I could easily customize and edit I choose an expressive style and vids Works its magic let's see what I get so wow just like that I get the first draft with beautifully designed fully animated scenes complete with relevant stock media and music and even a generated script I'll be able to add fun videos and photos that I captured this week from my media directly by accessing Google Drive and Google photos and even without any video expertise I can build out scenes like a pro just as easily as I make slides but it doesn't have to stop there with vids you can personalize your story your way by recording yourself or by using one of our preset voices by Gemini and by enriching scenes with high quality media from our stock Content Library or from your own to really make your story shine and because Google bids is a workspace app it comes with all of the collaboration capabilities that your teams already know and love V doesn't just help you create videos it helps you become a better Storyteller with a rich new medium at work this isn't just a vision vids is already in the hands of alpha customers who have been giving us really great feedback as we work towards expanding to workspace labs in June I'm looking forward to sharing more about vids with all of you in my Spotlight session tomorrow Beyond vids many customers are building agents for their marketing teams audio and video production teams and all of the creative people out there who could use a hand we provide a tremendously powerful platform and stack to build creative agents first it takes the best image generation model imagine 2. 0 our most advanced Tex to image technology helps businesses create images that match their specific brand requirements this is now generally available in Vortex AI image imagine strong language comprehension and photo realism capabilities contributed to Google securing the leadership position in the recent Foresta computer vision wave second as a part of Imagine we're now introducing text to live image in preview today marketing and creative teams can generate anim ated images from a text prompt including product images ads gips and storyboards here's an example of a day lily opening in the Morning Dew and a pot of something delicious simmering on the stove or an aerial view of a mountain range third we are proud to announce the general availability of digital watermarking for AI generated images produced by imagine it's powered by Google deep Minds synth ID finally we're announcing new editing modes for Imagine 2. 0 which will make it really easy to remove unwanted elements in an image add new elements and expand the borders of the image to create a wider view for all of you when all of these tools come together it's a powerful combination our symbol Outfitters product team is working on designing a new tent that

we're eager to bring to market the tent itself is still in development but we want to get started on a marketing strategy right away let's see how the creative agent we developed with Gemini models imagine 2. 0's API and Google workspace can help first things first let's get a look and sense for the look and feel of our brand what are the key Styles and themes of our brand the creative agent can analyze previous campaigns to understand our unique brand style and apply it to new ideas in this case the creative agent has analyzed over 3,000 brand images descriptions videos and documents of other products that we have in our catalog contained within Google drive to create this summary and as you can see it summarized our brand identity as bold adventurous and aspirational this is exactly the look and feel that we're going for the creative agent was able to use Gemini Pros 1 million token context window and its ability to reason across text images and video to generate this summary next I'm going to cre prompt our creative agent using imagine to dynamically generate amazing new images of our tents in iconic and real outdoor settings this will help us bring brain storm campaign locations all of this of course will match our unique brand style now because I'm a terrible typist I'm going to use Chrome's builtin clipboard history so we've asked it to create these images we'll give it just a second check this out Machu Picchu not bad half doome these are real landmarks accurately presented now let's work on a narrative to really help us land the message I want to make special note that in this prompt I'm going to ask the creative agent to provide captions in both English and Spanish and that I'm using a multilingual prompt to do so awesome the creative agent leverage Gemini Pros multimodal capabilities to brainstorm creative captions that match each photo these look great too and thanks to our multilingual capability we're able to share the same story with our customers in their native language moving along let's ask the agent to combine everything into a storyboard and share it with the team to get some feedback generate a storyboard share it with an email group The Creative agent's going to move this into slides and share it out with that group all done shared with the group they can post comments directly in Google slides and we can see them here for the agent to review we'll speed up time a little bit because it's a demo and take a look at the feedback looks great but there are three requests first something for Less experienced campers second content for the symbol Outfitters podcast and third something more visually Dynam damic for social media let's start with that new storyboard we'll use that copy paste trick again and you'll see in this case we're asking for a New Image new captions and a new storyboard with that new audience that relaxed camping audience take a look that looks pretty relaxing to me looks pretty good and there's the storyboard great just like that the creative agent modified our ideas for a new audience it understood our context and made the changes that we asked for now let's generate that podcast the Gemini models complex reasoning allows me to generate a script and an audio clip in a single prompt this much longer prompt highlights our ability to do ordered operations we're asking the agent to create a podcast script in ssml or speech synthesis markup language and then passing the output to our text to speech API the result will be an episode with two people discussing tense so we'll see the script here which we could expand if we wanted but let's just listen to a little bit welcome to the show thanks Freya it's great to be here I'm always happy to geek out about gear that sounds really good and I want you to notice the regionalisms in the speaker voices pretty impressive but we don't have time to listen to the whole thing because you're here for the keynote finally we were asked for some engaging content for social media let's see what the creative agent can do using our new live image generation capability so we'll ask it generate some live images of our tent Outdoors for clarity we've run this prompt before and so you'll be seeing cash to speed things up but these are simply beautiful creating content like this could take days of weeks days or weeks of scouting and shooting but our creative agent used imagins new text to live image capability to make them in minutes the creative Agent shows how Google's generative AI capability can make producing custom content easy seamless and a lot of fun I'll hand it

over to Brad cder then we have Partners like Onyx and data Meda who help our customers build data agents now these data agents have the potential to unlock new ways to find and act on meaningful signals from your data they're built with AI for complex analysis and they have to ensure factional Integrity of their results and to help power these data agents we're making it easy to bring your data to Google cloud with Gemini and bigquery helps with data preparation Discovery analysis and governance and comes with a new big query data canvas which is a new notebook like experience supporting natural language queries and embedded visualizations now data professionals can get assistance for building their data pipelines to improve performance reduce errors and lower costs and today we're introducing new query capabilities using vertex indexing directly in big query and alloy to be this allows you to leverage AI over your data where it is stored enabling real time and accurate responses for AI applications we're also building seamless connection from Big query to fex AI to give you direct access to AI models in vertex from Big query now bigquery and vertex together deliver up to four times faster performance and are up to three times more cost effective than the other data warehouse and AI platforms now this allows you to seamlessly combine your AI models classical ml operators and statistical functions together in your data pip pipelines for multimodal analysis and with this new capability you can analyze documents videos images and audio recording together with your structure data and finally we've improved the integration between looker and your data agents as part of the Gemini and looker preview we've added new AI capabilities that enable you to chat with your business data with seamless integration with Google workspace and together these struct these Solutions make it easier to analyze and activate your data let's see how this comes together in a demo please welcome director of outbound product management in data analytics Jasmine Amud thank you Brad we have built a great data agent one that connects all of your data incorporates geni and even has collaboration it's a custom application built with big query looker and vertex AI shoot I could have sworn my notifications were on silent but wait what's this is cool it's my data agent giving me a notification that sales are up well maybe it's because of our Cloud shoes because surely shouldn't all keynote speakers get keyote sneakers all right let's explore with our data agent what you're seeing here are realtime kpis the metrics that matter the most being continuously monitored from my Enterprise data in big query to surface anomalies and Trends let let's dig in let's explore Cloud Sho sales over customer segments and territories in a heat map our data agent uses the looker semantic layer to effectively ground its AI in specific business data and data definitions that give us trusted answers and in this case it's right down to the territory and even customer segment I also see other data details that give me source and traceability so I know I can trust this data I wonder how might this trend be impacting other kpi stored in my semantic layer let's ask how does demand correlate with other Core Business metrics okay our data agent again uses the looker semantic layer to find other business metrics that are similar and looks for anomalies in fact I've got three helpful insights I can actually dig into supply and demand levels over the next 3 months by clicking this first tile our data agent is now using big query machine learning to build a futur looking forecast and it looks like it's found a gap in supply versus demand and it's only growing I might need a substitute product to help me meet demand well isn't it great that in big query we have invented our 50,000 shoe catalog collection including multimodal data like product descriptions pricing and even images and with big query

Vector embeddings these images with different colors shapes lines and styles can be queried easily to do a similarity match so let's enter a prompt find me similar products in our catalog that look like and we're going to upload an image of our Cloud shoe and with that our agent has all of the information it needs to do that search and it's found three top matches and combined these images with structured data about pricing and delivery schedules well given I need a similar looking shoe and delivery times are important I think option one looks great isn't this incredible however we do need to make it actionable after all insights that aren't actioned aren't very useful so let's share this with the team our looker and workspace Integrations now make this super easy we can simply send a summary of the alert and search insights over chat to our symbol inventory team and with that our data agent compiles that summary and it's even come back with a sheet containing all of the raw data and insights I sure do want to share these with the team and with that our team now can make confident decisions with all of the data and insights they need all power and to ramp up on new languages and code bases faster now please welcome our product manager for Gen Paige Bailey for our final demo awesome thank you so much Brad and hey there Las Vegas so let's take a look at what's coming for code assist with Gemini 1. 5 Pro leveraging a 1 million token context window I'm a new developer with symbol Outfitters and today we show recommended products to customers only after they've made an initial selection these suggestions are powered by our custombuilt recommendation service based on previous purchases but now the marketing department has asked me to move this feature to our homepage so that customers can see products that they might be interested in as soon as they get to our site our design department has created a mockup of what they would want this experience to look like in figma and for the developers out there you know that this means we're going to need to add padding in the homepage modify some views make sure that the configs are changed for our microservices and typically it would take me a week or two to even just get familiarized with our company's code base which has over a 100,000 lines of code across 11 services but now with Gemini Cod assist as a new engineer on the team I can be more productive than ever and can accomplish all of this work in just a matter of minutes this is because Gemini's code Transformations with full codebase awareness allows us to easily reason through our entire codebase and in comparison other models out there can't handle anything beyond 12 to 15,000 lines of code and even then they struggle to get it right Gemini inside of cod assist is so intelligent that we can just give it our business requirements including the visual design so let's ask here I am prompting Gemini to add a for you recommend section on the homepage along with an image of the future state to show the improved design almost immediately Gemini code assist starts by reasoning about the code changes that it needs to make and has insights and experience teammate would have for example because we asked Gemini Cod assist to change the recommendation service it was able to find the recommendation function and extract out the exact details needed to make the call to the recommendation service it highlights the files needing to be changed and reveals the reasoning behind its recommendations using our own codebase for context Gemini Cod assist doesn't just suggest code edits it provides clear recommendations and makes sure that all of these recommendations are aligned with symbol Outfitter security and compliance requirements in code assist we've also added an option to apply the edit which keeps me as the developer and the driver seat so let's take a look at the source code changes that Gemini code assist has made in our code base it looks like we have multiple edits across two files handlers. go and also home. html Gemini Cod assist even applied these changes to the full repository and to put this in context no pun intended it would have taken me over 70 hours non-stop to even just read through all of these files and just like I would with any code change my next step is to

check the workout by testing out the modified app locally so let's try it and there we go the for you recommendations section is exactly what our marketing team was asking for and as a new developer I was able to make a meaningful contribution on my very first day so let's recap behind the scenes Gemini has analyzed my entire higher code