[{"data":1,"prerenderedAt":482},["ShallowReactive",2],{"blog-why-we-are-introducing-pro-plus":3,"related-how-we-use-ai-why-ai-chat-sustainability-at-capacities":260},{"id":4,"title":5,"authorKey":6,"body":7,"category":236,"date":237,"dateFormatted":238,"description":239,"extension":240,"icon":241,"iconColor":241,"imagePath":242,"keywords":243,"meta":249,"navigation":250,"path":251,"readingTime":252,"relatedArticles":253,"seo":257,"stem":258,"__hash__":259},"blog\u002Fblog\u002Fwhy-we-are-introducing-pro-plus.md","Why we are introducing Pro+","steffen",{"type":8,"value":9,"toc":219},"minimark",[10,14,23,26,29,34,37,40,44,47,50,53,56,60,63,66,69,73,76,79,89,92,101,105,110,114,117,122,125,132,138,144,147,151,159,170,173,176,184,188,191,195,198,204,212,216],[11,12,13],"p",{},"Today we're introducing Capacities Pro+ and Believer+.",[11,15,16,17,22],{},"Plus is for heavier AI use. You get a much larger monthly AI budget, and if that's not enough, you can top up in the app (including with auto top-up). You can find the current Plus and top-up prices on the ",[18,19,21],"a",{"href":20},"\u002Fpricing","pricing page",".",[11,24,25],{},"This is a choice, not a requirement. AI will become more capable over time, but Capacities still works fully without it, and we will always keep improving every part of the app. We made Plus a separate subscription so you can decide based on how much AI you need and want to use.",[11,27,28],{},"Here's our thinking: why Plus exists, why we're discontinuing Bring Your Own Key, and why MCP is the better path for using your own AI stack with Capacities.",[30,31,33],"h2",{"id":32},"a-clean-split-between-two-kinds-of-users","A clean split between two kinds of users",[11,35,36],{},"Pro+ creates a clean split between people who use a lot of AI and people who use little or none.",[11,38,39],{},"Both groups matter, and they have different needs. If you rarely touch AI, you shouldn't pay for someone else's heavy usage. If you use AI heavily, or for professional work, you shouldn't feel held back. We didn't want AI costs to create tension inside the normal Pro plan. A separate add-on lets both be true: Capacities Pro stays a full product that accounts for simple AI usage, and power users can scale AI without pulling everyone else along for the cost. We care about every Capacities user having the best experience possible, with or without AI. Pro+ makes this possible.",[30,41,43],{"id":42},"why-a-single-subscription-couldnt-carry-this","Why a single subscription couldn't carry this",[11,45,46],{},"Some AI features are genuinely expensive to run. Transcribing audio, analyzing PDFs, understanding images, and asking complex questions about your notes all cost real money. We couldn't sustain this cost inside one flat subscription without raising the price for everyone or watering down the experience. Neither felt right to us.",[11,48,49],{},"We also didn't want to compromise the experience for Pro users who do want AI. If you need to transcribe a long recording or make sense of a stack of documents, that should simply work. Pro+ makes that possible without putting the cost on people who will never use it.",[11,51,52],{},"For the AI credits included in Pro, we keep making usage more efficient: cheaper models where they're good enough, and smart routing so the included budget goes further. That's right for everyday AI. For serious work (running AI daily, supporting several workflows, having it research for you), there's no way around substantially higher token usage. Efficiency alone can't cover that. Plus is the optional path for heavier use.",[11,54,55],{},"Capacities Pro and Believer fund us as a small independent team, and make it possible to keep growing Capacities. Plus finances AI usage within Capacities.",[30,57,59],{"id":58},"the-vision-for-capacities-ai","The vision for Capacities AI",[11,61,62],{},"We believe AI can be a valuable companion in knowledge work: extract information, look up facts, check your work, automate repetitive tasks, find blind spots, and more.",[11,64,65],{},"Capacities AI already includes semantic search, related content, autofill, image analysis and OCR, a context-aware assistant over your notes, and models from OpenAI, Anthropic, Google, and more. This is still the beginning. Pro+ helps us keep going.",[11,67,68],{},"Ultimately, we are working towards a future where Capacities AI will be able to replace your existing AI subscriptions entirely. Imagine the power of AI, built on top of your set of notes and knowledge.",[30,70,72],{"id":71},"what-plus-adds","What Plus adds",[11,74,75],{},"All AI workflows and all models in the picker stay available on Pro and Believer. You can try them within the included monthly budget. More expensive models simply use budget faster.",[11,77,78],{},"Pro is sized for light daily use and occasional media. If you analyze media or chat heavily most days, expect to need Plus. Plus adds:",[80,81,82,86],"ul",{},[83,84,85],"li",{},"A much larger monthly AI budget (what you pay becomes AI budget, minus transaction fees)",[83,87,88],{},"Top-ups when you need more, including auto top-up (Plus required)",[11,90,91],{},"You don't need Plus until the included budget isn't enough for how you work. We deliberately didn't lock AI workflows or models behind an extra tier, because we want everyone to be able to use the AI features they need.",[11,93,94,95,22],{},"For concrete examples of what a Plus budget typically covers, see ",[18,96,100],{"href":97,"rel":98},"https:\u002F\u002Fdocs.capacities.io\u002Freference\u002Fsubscriptions#what-a-plus-budget-covers-in-practice",[99],"nofollow","What a Plus budget covers in practice",[30,102,104],{"id":103},"pro-funds-ai-not-our-margins","Pro+ funds AI, not our margins",[11,106,107,108,22],{},"Plus is not an add-on for us to earn more money on AI. It keeps running AI in Capacities sustainable. What you pay for Pro+ becomes AI budget, minus transaction fees. Exact costs for Pro+, Believer+, and top-ups are on the ",[18,109,21],{"href":20},[30,111,113],{"id":112},"why-were-discontinuing-bring-your-own-key","Why we're discontinuing Bring Your Own Key",[11,115,116],{},"With this release, bring your own API key (BYOK) is discontinued. The setting is removed. If you relied on it, here's why, and what replaces it.",[118,119,121],"h3",{"id":120},"byok-couldnt-keep-up-with-capacities-ai","BYOK couldn't keep up with Capacities AI",[11,123,124],{},"BYOK meant: paste a provider API key into Capacities, and the in-app assistant routes chat through that key. That worked for a narrow class of text chat. It doesn't work for Capacities AI today.",[11,126,127,131],{},[128,129,130],"strong",{},"Media is the clearest example."," Image analysis, weblink analysis, audio transcription, PDF understanding, and related pipelines aren't a single \"call the model with your key\" path. Providers differ in file handling, modalities, pricing, rate limits, preprocessing, and outputs. Behind BYOK we can't own a shared media pipeline, pick the right model per step, or guarantee the same feature works the same way for every key. Either media ships only on Capacities AI, or we maintain a weaker BYOK mode. The second option isn't acceptable to us.",[11,133,134,137],{},[128,135,136],{},"Capacities AI is more than a proxy to one LLM."," Much of what makes the assistant useful lives around the model call: retrieval over your space, routing between models, tool use in the app, structured extraction, and other algorithms a customer key doesn't cover. A key gives access to a provider's chat API. It isn't a substitute for the systems that make Capacities AI coherent.",[11,139,140,143],{},[128,141,142],{},"We're not building DIY AI."," Capacities AI is one product experience: same features, same pipelines, same behaviour for everyone. Supporting BYOK meant forever carrying a parallel mode that couldn't share the pipelines the rest of Capacities AI depends on. If you want to bring your own models and tooling, that belongs outside Capacities with the MCP.",[11,145,146],{},"So discontinuing BYOK was necessary. Keeping it would have blocked media features and around-the-model algorithms, while forcing two unequally capable product modes.",[118,148,150],{"id":149},"mcp-is-the-better-replacement","MCP is the better replacement",[11,152,153,154,22],{},"If what you wanted from BYOK was \"use my own models and tooling with Capacities,\" that path is ",[18,155,158],{"href":156,"rel":157},"https:\u002F\u002Fdocs.capacities.io\u002Freference\u002Fai-chat-connectors",[99],"AI Chat Connectors (MCP)",[11,160,161,162,166,167,169],{},"The architecture is flipped in a useful way. BYOK pulled your key ",[163,164,165],"em",{},"into"," Capacities so our UI could call your provider. MCP connects Capacities ",[163,168,165],{}," the AI setup you already use: Claude, ChatGPT, Cursor, other MCP clients, and local models. Capacities becomes a tool in the environment where you already work with other systems, not a second place that needs its own key setup.",[11,171,172],{},"In practice you can search and read your space, create and update objects, append content, work with media through the connector, and keep the model choice and agent setup of your preferred client. BYOK only substituted the model bill for in-app chat. MCP lets an external agent operate on your knowledge base with a proper tool interface.",[11,174,175],{},"You can still use Capacities AI from the inside through your AI budget. Or simply use both: Capacities AI in-app, MCP for the setup you use across other tools.",[11,177,178,179,183],{},"If you used BYOK, set up an ",[18,180,182],{"href":156,"rel":181},[99],"AI Chat Connector"," now to use Capacities through your preferred client or local models.",[118,185,187],{"id":186},"were-actively-investing-in-mcp","We're actively investing in MCP",[11,189,190],{},"MCP isn't a consolation prize for BYOK. It's how we want Capacities to sit in a modern AI stack, and we're actively making it more powerful: stronger retrieval, better editing, broader media and object tools, and more ways for an agent to operate inside your space.",[30,192,194],{"id":193},"what-this-means-for-you","What this means for you",[11,196,197],{},"If you're on Pro or Believer, your plan price and AI feature set stay the same. You also get the larger monthly AI budget (monthly instead of daily). You don't need to do anything for Plus unless you want more budget.",[11,199,178,200,203],{},[18,201,182],{"href":156,"rel":202},[99]," now. That's the supported path going forward.",[11,205,206,207,211],{},"Pro+ enters the picture when you need more Capacities AI budget. You can add or remove it anytime in ",[208,209,210],"code",{},"Settings > Subscription & Billing",". With Plus, you can also buy one-time top-ups or enable auto top-up.",[30,213,215],{"id":214},"looking-ahead","Looking ahead",[11,217,218],{},"As a small independent team, we can't subsidize unlimited AI usage. Capacities Pro+ lets us offer a strong AI experience while staying sustainable. That's good for the product and for you. Thank you for being part of the journey and making Capacities possible.",{"title":220,"searchDepth":221,"depth":221,"links":222},"",2,[223,224,225,226,227,228,234,235],{"id":32,"depth":221,"text":33},{"id":42,"depth":221,"text":43},{"id":58,"depth":221,"text":59},{"id":71,"depth":221,"text":72},{"id":103,"depth":221,"text":104},{"id":112,"depth":221,"text":113,"children":229},[230,232,233],{"id":120,"depth":231,"text":121},3,{"id":149,"depth":231,"text":150},{"id":186,"depth":231,"text":187},{"id":193,"depth":221,"text":194},{"id":214,"depth":221,"text":215},"team-product","2026-08-17","August 17, 2026","The thinking behind Pro+, our AI add-on, why we are discontinuing bring your own key, and why MCP is the better replacement.","md",null,"\u002Fblog\u002Fpro-plus-cover.jpg",[244,245,246,247,248],"AI","Pro+","pricing","MCP","BYOK",{},true,"\u002Fblog\u002Fwhy-we-are-introducing-pro-plus","8 min",[254,255,256],"how-we-use-ai","why-ai-chat","sustainability-at-capacities",{"title":5,"description":239},"blog\u002Fwhy-we-are-introducing-pro-plus","Af3ajia8W7NWvIFmN2oikP573U0n9_1W-SJWBlZcYfU",[261,317,363],{"id":262,"title":263,"authorKey":6,"body":264,"category":236,"date":301,"dateFormatted":302,"description":303,"extension":240,"icon":241,"iconColor":241,"imagePath":304,"keywords":305,"meta":308,"navigation":250,"path":309,"readingTime":310,"relatedArticles":311,"seo":314,"stem":315,"__hash__":316},"blog\u002Fblog\u002Fhow-we-use-ai.md","How we use AI at Capacities",{"type":8,"value":265,"toc":299},[266,269,272,275,278,281,284,287,296],[11,267,268],{},"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.",[11,270,271],{},"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.",[11,273,274],{},"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.",[11,276,277],{},"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.",[11,279,280],{},"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.",[11,282,283],{},"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.",[11,285,286],{},"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.",[11,288,289,290,295],{},"There are many more ways of using AI, and it will for sure revolutionize many more workflows. We have ",[18,291,294],{"href":292,"rel":293},"https:\u002F\u002Fdocs.capacities.io\u002Freference\u002Fai-roadmap",[99],"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!",[11,297,298],{},"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":220,"searchDepth":221,"depth":221,"links":300},[],"2024-10-14","October 14, 2024","We rely on AI to work more efficiently and to create a better product.","\u002Fblog\u002Fhow-we-use-ai.jpg",[244,306,307],"Generative AI","LLMs",{},"\u002Fblog\u002Fhow-we-use-ai","5 min",[255,312,313],"building-capacities","transparency",{"title":263,"description":303},"blog\u002Fhow-we-use-ai","4AnF70gKV0UnEE_l0rH4D7pMzfCKzAMLLw0ue7sfH0Q",{"id":318,"title":319,"authorKey":6,"body":320,"category":236,"date":347,"dateFormatted":348,"description":349,"extension":240,"icon":241,"iconColor":241,"imagePath":350,"keywords":351,"meta":354,"navigation":250,"path":355,"readingTime":356,"relatedArticles":357,"seo":360,"stem":361,"__hash__":362},"blog\u002Fblog\u002Fwhy-ai-chat.md","Why did we add an AI chat to Capacities, although ChatGPT already exists?",{"type":8,"value":321,"toc":345},[322,325,328,331,334,337,340],[11,323,324],{},"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.",[11,326,327],{},"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\u002Fpaste 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.",[11,329,330],{},"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.",[11,332,333],{},"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.",[11,335,336],{},"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.",[11,338,339],{},"Exciting times ahead!",[11,341,342],{},[163,343,344],{},"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":220,"searchDepth":221,"depth":221,"links":346},[],"2024-04-05","April 5, 2024","Here are some thoughts about why we decided to integrate an AI chat into Capacities.","\u002Fblog\u002Fwhy-ai-chat.jpg",[306,352,353],"ChatGPT","AI Chat",{},"\u002Fblog\u002Fwhy-ai-chat","3 min",[312,358,359],"how-it-started","how-we-developed-tables",{"title":319,"description":349},"blog\u002Fwhy-ai-chat","qpq76uOBuiJJVn4wZWuTQyxs8UuTXKarBDkJe5CiQ7I",{"id":364,"title":365,"authorKey":6,"body":366,"category":236,"date":469,"dateFormatted":470,"description":471,"extension":240,"icon":241,"iconColor":241,"imagePath":472,"keywords":473,"meta":477,"navigation":250,"path":478,"readingTime":356,"relatedArticles":241,"seo":479,"stem":480,"__hash__":481},"blog\u002Fblog\u002Fsustainability-at-capacities.md","Sustainability at Capacities",{"type":8,"value":367,"toc":463},[368,371,374,383,387,390,393,396,400,403,406,410,419,422,428,431,442,450,452,460],[11,369,370],{},"Transitioning to a sustainable future is one of the most important challenges of our time. Every organization has a role to play in shaping that future, including us. Our work may be rooted in the digital world, but our impact extends beyond it. Because of that, we are taking real responsibility for the footprint we create.",[11,372,373],{},"We also believe this approach should become the standard, and we hope to contribute to that shift by being transparent about what we do and the steps we’re taking towards sustainability practices.",[11,375,376,379,380],{},[128,377,378],{},"Legal disclaimer:"," ",[163,381,382],{},"We do not claim to be carbon-neutral or “fully sustainable.” We avoid emissions whenever feasible and compensate the remainder, but we are not certified as a carbon-neutral company and make no guarantees beyond the documentation we share publicly.",[118,384,386],{"id":385},"avoidance-over-compensation","Avoidance over Compensation",[11,388,389],{},"Our philosophy is simple. We reduce our carbon footprint wherever we can, because avoiding emissions is always better than compensating for them later.",[11,391,392],{},"This means being intentional about how we operate. We fly infrequently, try to use the train whenever possible, aim for efficient use of compute, and choose data centers powered 100% by renewable energy.",[11,394,395],{},"For anything we cannot avoid or choose not to avoid, we compensate.",[118,397,399],{"id":398},"offsetting-our-remaining-emissions","Offsetting our Remaining Emissions",[11,401,402],{},"We aim to be efficient and pragmatic. We estimate our emissions, add a safety margin to account for uncertainties, and then offset our emissions equivalents through a hand-selected project we trust.",[11,404,405],{},"While there are standards to be certified by, we chose to save resources, money and time. This means we cannot claim to be “carbon-neutral”. By adding a significant safety margin, we focus on the impact, not a label.",[118,407,409],{"id":408},"forestal-río-aquidabán","Forestal Río Aquidabán",[11,411,412,413,418],{},"To compensate for our emissions, we decided to work with ",[18,414,417],{"href":415,"rel":416},"https:\u002F\u002Fglobal-woods-international.com\u002F",[99],"Global Woods",". We know the management team personally and trust their know-how and long-standing commitment to responsible forestry.",[11,420,421],{},"While we have had direct exchanges with the team, our decision is not based on personal relationships. It is based on independently reviewed project documentation and publicly available registry records on ICR. The fact that ICR is ICROA-endorsed provides additional, third-party assurance on the programme level.",[11,423,424],{},[425,426],"img",{"alt":409,"src":427},"\u002Fblog\u002Fsustainability-1.webp",[11,429,430],{},"In transparent and open conversations, we learned a lot about carbon removal, including:",[80,432,433,436,439],{},[83,434,435],{},"Removing CO2 from the atmosphere is not everything. Sustainable development, biodiversity and social impact are factors that should be accounted for as well.",[83,437,438],{},"Removal certificates are usually stronger than avoidance certificates when it comes to long term climate impact. Their impact can be measured and guaranteed.",[83,440,441],{},"Certification matters. There were and for sure still are scandals and issues with carbon offsetting projects. But today, there are good international certifications that guarantee removal and compliance with standards.",[11,443,444,445,22],{},"You can read more about the project in the ",[18,446,449],{"href":447,"rel":448},"https:\u002F\u002Fwww.carbonregistry.com\u002Fprojects\u002Fforestal-rio-aquidaban-349",[99],"International Carbon Registry",[118,451,215],{"id":214},[11,453,454,455,459],{},"All our calculations and removal certificates are public. You can read more about it on our ",[18,456,458],{"href":457},"\u002Fabout\u002Fsustainability","sustainability page",". We see this as an ongoing effort rather than a one-time gesture, and we are open to any feedback.",[11,461,462],{},"Our goal is to continuously reduce and offset our footprint, support projects that genuinely help the planet, and be open about how we do it.",{"title":220,"searchDepth":221,"depth":221,"links":464},[465,466,467,468],{"id":385,"depth":231,"text":386},{"id":398,"depth":231,"text":399},{"id":408,"depth":231,"text":409},{"id":214,"depth":231,"text":215},"2025-12-06","December 6, 2025","Knowledge work should not come at the planet's expense.","\u002Fblog\u002Fsustainability.jpg",[474,475,476],"Sustainability","Environment","Carbon Footprint",{},"\u002Fblog\u002Fsustainability-at-capacities",{"title":365,"description":471},"blog\u002Fsustainability-at-capacities","8IkUD80_zwHYnia6sjWVpVuGey9VjrLJfSDtmc_I4PE",1787825181233]