 GitLab is the most comprehensive AI power DevSecOps platform and today we are excited to show you how the power of our platform allows you to build, secure and deploy software faster. Consider this website of one of our customers that consolidates frequently asked questions for a financial services provider. This FAQ became quite extensive and the info it contains doesn't address other type of questions that are not frequently asked but should be easy to respond to and the customer experience is being impacted by this. The leadership from this financial services company chooses to have their team use GitLab to improve and automate the FAQ experience. Let's take a look. First they leverage GitLab planning capabilities. Here we can see how the team in charge of working on these improvements has been collaborating and coming to a solution that should be developed and put in the hands of end users as soon as possible. The team agrees that they will use AI to replace the long FAQ with a chatbot that can respond to these questions using natural language. They'll build their solution using GitLab's AI power platform. Once the product management team has agreed on the solution they connect with the development team to start building. Here we see that when a developer gets involved in the discussion he doesn't need to read all the discussion since GitLab is leveraging AI capabilities and will automatically summarize all this information and provide what he needs to understand the context so he can start working on the solution quickly. Since the developer now knows what needs to be implemented he uses GitLab IDE to start coding the solution. Thanks to co-suggestions he doesn't have to spend time writing boilerplate code. GitLab co-suggestions allows him to add code changes quickly to be more productive. If he wants to add a function to load the chatbot configuration file he simply prompts the model writing a natural language with what he needs to do and receives a co-suggestion that helps him to achieve that. He presses staff to add the AI generated code and commit these changes. We see here that the added changes triggered a continuous integration pipeline that will check the quality and security of the code contribution. This ensures he's not introducing vulnerabilities or degrading the quality of the code base and therefore the solution. It's best practice to always keep a human in the loop for any code contribution. Therefore the developer will need this code to be reviewed by another team member. However, it can be challenging to find the right person to do that. Luckily for this developer GitLab provides a set of recommender reviewers using machine learning and the suggested reviewers are people with the proper knowledge and expertise that are more suitable to review his code. This saves the developer time in finding the best person to review. The suggested reviewer adds her review and comments. In this case she's pointing out that the function added to the code doesn't have a test associated with it and code that hasn't been tested cannot be part of the solution. The reviewer suggests that the developer can use AI generated tests and once the review is done Delany the suggested reviewer uses AI in GitLab to summarize all the comments and feedback. The reviewer suggests that the developer can use AI generated tests and once the review is done Delany the suggested reviewer uses AI in GitLab to summarize all the comments and feedback given to the developer and his code changes. This will allow him to quickly understand what needs to be improved. Now back to the developer point of view we see that he can quickly grasp what needs to be improved by reading the AI summary. But there is one thing he isn't sure of how to use the AI generated test mentioned in the code review. Luckily he doesn't have to leave GitLab to find out how to do that and uses the GitLab chatbot which allows him to ask questions in natural language. In this case he asks how to leverage automated code testing capabilities with the help of AI. We see he gets his answer right in the GitLab experience. This saves him time by not forcing him to switch context by leaving the tool to go find his answer somewhere else and allowing him to stay focused. Now he knows how to leverage AI to generate the missing test and can put in action the step-by-step instructions given by GitLab AI. Let's do it. We can see here the test code has been generated. It looks good and now the developer has everything he needs to act upon the feedback and contribute new code changes towards the solution of replacing the long FAQ on his website. Since the GitLab security scanners also gave a warning that code has vulnerability he will use the GitLab IDE to add the AI generated test and remove the code vulnerability. We see that this improved contribution is running the continuous integration pipeline and when it is done it was easy to remove the vulnerability and add the testing generated by AI. This not only helped the developer to save time but also to make sure that the solution being built remains secure. Remember that security issues are the ones that make headlines and with GitLab's integrated security and privacy first approach this can be prevented. Since we don't have any more errors we will merge this contribution into the main code base and use it to build and deliver the FAQ solution to production. GitLab CI CD takes care of all of the steps to build the application, test it, check that security vulnerabilities are not being introduced and finally deploy the application so the end users can benefit from it right away. By opening the deployment job a URL is produced with the application GitLab helped us to automatically build, test and deploy. Let's click on it and here it is. This is a chatbot solution built using GitLab. The solution is using a large language model able to understand natural language and respond to customer queries. Let's give it a try by adding one question. Looks like a solid answer. Now let's try with one of the frequently asked questions and here we see step by step how to achieve that. Gone are the days of scrolling in long FAQ pages. A solution built quickly and securely thanks to GitLab. Lastly we cannot improve what we can't measure. Since GitLab is a single application it provides a way to measure our software development lifecycle end to end and helps identify areas of improvement. Value stream analytics measures the time it takes to go from planning to monitoring for each project in our portfolio, empowering teams to ship better software faster to customers by providing a unified view across value streams and software value delivery metrics. Thanks to GitLab's AI power platform this customer shipped their website chatbot to market quickly and securely allowing them to stay ahead of the competition.