[{"data":1,"prerenderedAt":232},["ShallowReactive",2],{"blog-how-we-use-ai":3,"related-why-ai-chat-building-capacities-transparency":72},{"id":4,"title":5,"authorKey":6,"body":7,"category":50,"date":51,"dateFormatted":52,"description":53,"extension":54,"icon":55,"iconColor":55,"imagePath":56,"keywords":57,"meta":61,"navigation":62,"path":63,"readingTime":64,"relatedArticles":65,"seo":69,"stem":70,"__hash__":71},"blog/blog/how-we-use-ai.md","How we use AI at Capacities","steffen",{"type":8,"value":9,"toc":46},"minimark",[10,14,17,20,23,26,29,32,43],[11,12,13],"p",{},"AI is everywhere now. The recent innovations around large language models are a huge breakthrough and fundamentally change how we work. It might not be an overnight change, but it will transform many areas of our lives and work.",[11,15,16],{},"At Capacities, we constantly try to adapt our processes to benefit from these new, exciting possibilities. We don't want to hop on every hype but, at the same time, use it as effectively as possible to do better work in less time. Here's a collection of examples of how we use AI at Capacities today as a team.",[11,18,19],{},"With the introduction of copilots and intelligent coding environments, our job as developers fundamentally changed. We're using auto-complete to code faster or write short prompts to get a first draft of a few lines of code written. We use the AI chat in our IDE to find bugs and flaws in our code.",[11,21,22],{},"At the moment, we're also experimenting with code composers. They allow you to specify what you want to do in natural language, and the AI will then manipulate and extend your code to achieve that goal. They don't work well in many cases, but they sometimes blow our minds. We found them to be very useful for writing encapsulated units of code or writing small functionalities in frameworks or libraries we're not very familiar with. Here, they can really reduce the time from multiple hours to a few minutes. That is just incredible.",[11,24,25],{},"Next to the AI in our IDEs, we constantly use the AI assistant in Capacities for development. We use it to understand new technologies, libraries, or frameworks, draft prototypes for new implementations, or iterate on our concepts. It's truly remarkable how valuable this process is. Sometimes, you're not experienced in a field, and you can tremendously benefit from the \"common wisdom\" on the internet by asking the AI. It helped us to find new libraries or convinced us to use one approach over the other by outlining its pros and cons.",[11,27,28],{},"We also heavily rely on the AI assistant for writing. We don't use it to generate articles or posts for us, but we use it to critique our chain of thought, find flaws in our arguments, improve our grammar and style of writing, and much more. The AI is like a writing tutor if prompted with the written questions. You don't have to accept everything, but you can learn a lot by getting an opinion on your writings.",[11,30,31],{},"Next to that, we're, of course, constantly using all integrated AI features in Capacities. Lately, we realized that AI tagging and property autofill are absolute game changers. It removes a lot of mental load by helping you to connect new content to what you already have.",[11,33,34,35,42],{},"There are many more ways of using AI, and it will for sure revolutionize many more workflows. We have ",[36,37,41],"a",{"href":38,"rel":39},"https://docs.capacities.io/reference/ai-roadmap",[40],"nofollow","exciting ideas for AI in Capacities"," and for using LLMs to improve the overall user experience, like providing a chat interface for asking questions about Capacities and much more!",[11,44,45],{},"The possibilities are endless, and one big challenge is understanding when AI is useful and equally important when it's not. We had to learn how to Google, and now we need to learn how to use LLMs. That journey is fascinating!",{"title":47,"searchDepth":48,"depth":48,"links":49},"",2,[],"team-product","2024-10-14","October 14, 2024","We rely on AI to work more efficiently and to create a better product.","md",null,"/blog/how-we-use-ai.jpg",[58,59,60],"AI","Generative AI","LLMs",{},true,"/blog/how-we-use-ai","5 min",[66,67,68],"why-ai-chat","building-capacities","transparency",{"title":5,"description":53},"blog/how-we-use-ai","4AnF70gKV0UnEE_l0rH4D7pMzfCKzAMLLw0ue7sfH0Q",[73,120,169],{"id":74,"title":75,"authorKey":6,"body":76,"category":50,"date":104,"dateFormatted":105,"description":106,"extension":54,"icon":55,"iconColor":55,"imagePath":107,"keywords":108,"meta":111,"navigation":62,"path":112,"readingTime":113,"relatedArticles":114,"seo":117,"stem":118,"__hash__":119},"blog/blog/why-ai-chat.md","Why did we add an AI chat to Capacities, although ChatGPT already exists?",{"type":8,"value":77,"toc":102},[78,81,84,87,90,93,96],[11,79,80],{},"Capacities has a built-in AI chat which you can open as a small window next to your notes. You can use your current note as context; you can apply commands like \"Critique my thinking,\" rephrase your questions and add the results back to your notes. Here are some thoughts about why we decided to do it that way.",[11,82,83],{},"First: Context switching is costly. We do a lot of work in and with our notes. We think, create, and have questions. Leaving our thinking context is distracting and increases cognitive load. We want to use an assistant while we're working on our notes. We don't want to copy/paste and switch windows. By having a chat right next to our notes, we can compare different results or replace our version with a single click.",[11,85,86],{},"We decided to use a chat because we think conversations are essential to working with Generative AI. It rarely produces great results on the first shot. We might have follow-up questions, need to ask it to rephrase its results, or want it to justify its arguments. Once we come to a result, we can use it, but we do not simply want to rely on what we got on the first try.",[11,88,89],{},"Some conversations are so insightful or helpful that we want to store them. Capacities allows you to capture a conversation as an object, tag it, and add it to your notes. AI conversations become part of your knowledge base. You can reference them and come back if needed.",[11,91,92],{},"And last, but most important: LLMs can hallucinate; they don't know us; they don't know what we work on and what your context is. They have flaws, and we need to be aware of that. But: We can also substantially improve its results by giving it some context about us, our knowledge, and what we work on. At the moment, you can use your current note as a context. In the future, the AI will be able to use all your notes and resources to assist us. We can encourage it to prove its argument, cite its sources, and draw conclusions based on facts and data.",[11,94,95],{},"Exciting times ahead!",[11,97,98],{},[99,100,101],"em",{},"By the way, I used the AI Assistant to sharpen and develop my thoughts here. I did not use it to write my essay. We can use LLM to generate a lot of content, but we can also use it to improve our own thinking and increase the quality of our own work. It's you who chooses how you use it.",{"title":47,"searchDepth":48,"depth":48,"links":103},[],"2024-04-05","April 5, 2024","Here are some thoughts about why we decided to integrate an AI chat into Capacities.","/blog/why-ai-chat.jpg",[59,109,110],"ChatGPT","AI Chat",{},"/blog/why-ai-chat","3 min",[67,115,116],"how-it-started","how-we-developed-tables",{"title":75,"description":106},"blog/why-ai-chat","qpq76uOBuiJJVn4wZWuTQyxs8UuTXKarBDkJe5CiQ7I",{"id":121,"title":122,"authorKey":6,"body":123,"category":50,"date":154,"dateFormatted":155,"description":156,"extension":54,"icon":55,"iconColor":55,"imagePath":157,"keywords":158,"meta":161,"navigation":62,"path":162,"readingTime":163,"relatedArticles":164,"seo":166,"stem":167,"__hash__":168},"blog/blog/building-capacities.md","How we decide which new features to add",{"type":8,"value":124,"toc":152},[125,128,131,134,137,140,143,146,149],[11,126,127],{},"We often get asked how we decide which features we add to @CapacitiesHQ. 🗺️",[11,129,130],{},"Here’s the answer. 👇",[11,132,133],{},"Very important: Every feature starts with a need or problem. There should never be a feature if it’s not solving a real problem. This cannot be stressed enough. Otherwise, you’re building a product with no real value and a lot of clutter.",[11,135,136],{},"We draw most feature inspiration from our community's feedback and by using the product ourselves. This helps us identify problems and friction points that stop users from getting their work done. We sometimes joke that our community is our first employee: a rigorous tester, opinion consolidator, and key source of inspiration.",[11,138,139],{},"Feature requests and explicit product improvements can be added to our feedback board, voted and commented on by other users. We review and cluster all requests and analyze their importance. This helps us to get a better understanding of the different needs and problems of our users.",[11,141,142],{},"In long and intense discussions, we combine all requests, comments, and ideas with our intuition and vision for what Capacities should become. We always radically aim for usefulness and simplicity – Capacities should just work and help, nothing else.",[11,144,145],{},"When features are big and fundamental, we share proposals or plans in our community for feedback. This ensures that we constantly have our users at the table with us. We fine-tune and iterate until we find a draft that fits into the greater picture.",[11,147,148],{},"Then we start creating. After a first draft, we introduce an early version to a small, selected group of alpha testers. In intense and incredibly helpful discussions, we optimize the last 20% in a combined effort. We refine the feature by addressing issues, polishing details, and enhancing interactions.",[11,150,151],{},"After a feature is released to all users, it’s not done. We constantly improve, iterate, and measure how it fits into users' workflows. Every feature is part of a continuous evolution of the overall product. We constantly strive to build a unified and consistent product – a beautiful environment to think and work in: a Studio for your Mind.",{"title":47,"searchDepth":48,"depth":48,"links":153},[],"2024-03-04","Mar 6, 2024","What's our decision making process? Here's the answer.","/blog/building-capacities.jpg",[159,160],"Feature development","Build in public",{},"/blog/building-capacities","2 min",[165,115],"why-the-name-capacities",{"title":122,"description":156},"blog/building-capacities","yUEsybivkdEpilRjL0YjnGhgRSjIYeDYSFuYsPOVPcQ",{"id":170,"title":171,"authorKey":6,"body":172,"category":50,"date":216,"dateFormatted":217,"description":218,"extension":54,"icon":55,"iconColor":55,"imagePath":219,"keywords":220,"meta":223,"navigation":62,"path":224,"readingTime":225,"relatedArticles":226,"seo":229,"stem":230,"__hash__":231},"blog/blog/transparency.md","Why we are as transparent as possible",{"type":8,"value":173,"toc":214},[174,177,180,183,186,189,192,195],[11,175,176],{},"Just last week, we published our latest \"What's next\" article and received a lot of positive feedback on our general transparency. Here's why we try to be as transparent as possible.",[11,178,179],{},"For us, there are four big reasons.",[11,181,182],{},"First, it's fair. If I were a Capacities user, I'd want to know it, too. Capacities is a tool you work with every day. You trust us with your content and rely on it to get work done. You have all the right to know which direction this tool is going, why we focus on some things and not others, who we collaborate with, who's working on Capacities, and so on. By being transparent, we try to answer these questions as best we can.",[11,184,185],{},"Second, it helps you to make the best decision possible. Capacities is not the tool for everyone, and we don't want to persuade you to believe that. There might be some short-term gains for us as a company by making users believe stuff that might not come true. We are 100% convinced that this will backfire in the long run. Sharing how we think about topics and being honest about evolving our thoughts will make sure that there's no mismatch between what's going to happen and what you think what's going to happen. And it helps you find out if Capacities works for you.",[11,187,188],{},"Third, it's by far the best way to create the best Capacities possible. Our \"What's next\" articles are based on hundreds if not thousands of user comments and ideas mixed with our ideas and vision. If our perception is wrong, users in our community will let us know. So even before committing to a topic or idea, we already got the feedback, and we can adjust without losing much time and resources.",[11,190,191],{},"Forth, we can do it. Nothing, and nobody is preventing us from sharing it. There's no secret plan or hidden incentives we have to follow. Capacities is 100% owned by us. There's no outside influence that requires us to trade long-term goals and our vision for short-term interests.",[11,193,194],{},"And if you're curious, here's how we try to be as transparent as possible:",[196,197,198,202,205,208,211],"ul",{},[199,200,201],"li",{},"We regularly share our \"What's next\" articles outlining our short- to long-term roadmap, including the reasoning behind it.",[199,203,204],{},"We share roadmaps and planned features in the docs so you can better understand what to expect.",[199,206,207],{},"A lot of ideas and feature requests get shared on our feedback board. With pinned comments, we try to be precise about our plans and thoughts regarding these feature requests. We also communicate when features are not planned for the near-term future.",[199,209,210],{},"Many questions about features and the future of Capacities get asked in our community. We try to be as responsive as possible or share overall thoughts in articles and our roadmap.",[199,212,213],{},"We write about it on our blog. We create blog posts on many topics, including articles on how we operate, how our company is structured, and how we develop Capacities.",{"title":47,"searchDepth":48,"depth":48,"links":215},[],"2024-10-02","October 2, 2024","We're very public about our roadmap, ideas, and plans. Here's why.","/blog/transparency.jpg",[221,222,68],"startups","product development",{},"/blog/transparency","4 min",[227,228,67],"what-if-capacities-was-gone-tomorrow","why-offline-first",{"title":171,"description":218},"blog/transparency","lC4f9OaPkKfBNxMljOmPVDsfhzjn0U2uUHt8lwaQ76k",1780666696154]