[{"data":1,"prerenderedAt":348},["ShallowReactive",2],{"update-en-20260804-memory":3,"related-posts-20260721-asks-questions-back-20251111-personal-data-detection-en":155},{"id":4,"title":5,"body":6,"description":136,"extension":137,"meta":138,"navigation":148,"ogImage":149,"path":150,"robots":149,"seo":151,"sitemap":152,"stem":153,"__hash__":154},"updates/en/updates/20260804-memory.md","Ask Aletta now remembers how you work",{"type":7,"value":8,"toc":128},"minimark",[9,13,16,19,22,27,30,52,55,58,61,65,68,71,74,78,81,92,95,101,104,109,112,115,119,122,125],[10,11,12],"p",{},"You should not have to reintroduce yourself to your AI assistant every day.",[10,14,15],{},"Ask Aletta already kept track of some context about you: your organisation, your language, your region and your discipline. That helped, but it was only a starting point. Until now, a new conversation still largely meant starting again - repeating which guidelines matter most to your work, how you want patient communication written or which details should be included in documents.",[10,17,18],{},"Ask Aletta now goes a step further: it learns from you.",[10,20,21],{},"As you use Ask Aletta, it builds a concise working context from your recurring preferences and behaviour - on top of the organisation, language, region and discipline it already knew. That context helps future answers better reflect how you work, without requiring you to explain the same things each time.",[23,24,26],"h2",{"id":25},"what-ask-aletta-can-remember","What Ask Aletta can remember",[10,28,29],{},"Memory is intended for information about you and your way of working. For example:",[31,32,33,37,40,43,46,49],"ul",{},[34,35,36],"li",{},"your profession, specialty or clinical setting;",[34,38,39],{},"the language and level of detail you prefer;",[34,41,42],{},"the types of questions or documents you commonly work on;",[34,44,45],{},"how you want patient-facing communication structured;",[34,47,48],{},"which sources, guidelines or regional context are most relevant to you;",[34,50,51],{},"recurring professional details that should be included in documents.",[10,53,54],{},"Suppose you regularly use Ask Aletta to draft patient letters. You can ask it to remember that these letters should use language at B1 level, follow a particular structure and end with the general contact details of your practice.",[10,56,57],{},"The next time you request a letter, Ask Aletta can apply those preferences without requiring you to repeat them.",[10,59,60],{},"Memory is for persistent professional context - not information about individual patients. Patient information should not be added to memory.",[23,62,64],{"id":63},"it-updates-as-you-work","It updates as you work",[10,66,67],{},"You do not have to manually build a profile before memory becomes useful. When memory is enabled, Ask Aletta updates its working summary as you use the product and recurring patterns become clear.",[10,69,70],{},"This does not mean that every previous conversation is inserted into every new answer. Instead, Ask Aletta maintains a concise summary of useful context that may be applied when relevant.",[10,72,73],{},"The aim is not to make every response feel artificially personal. It is to remove unnecessary repetition and make Ask Aletta fit more naturally into the way you already work.",[23,75,77],{"id":76},"you-remain-in-control","You remain in control",[10,79,80],{},"A useful memory should never be invisible or impossible to correct.",[10,82,83,84,91],{},"You can ask Ask Aletta what it remembers about you. The same overview is available under ",[85,86,90],"a",{"href":87,"rel":88},"https://app.askaletta.com/settings/context",[89],"nofollow","Settings → Context",".",[10,93,94],{},"If something is incomplete or incorrect, simply tell Ask Aletta what should change. You can also add a preference directly - for example:",[96,97,98],"blockquote",{},[10,99,100],{},"Remember that I prefer concise answers based primarily on Dutch guidelines.",[10,102,103],{},"Or:",[96,105,106],{},[10,107,108],{},"When drafting patient communication, use language at B1 level and include our practice's general contact details.",[10,110,111],{},"Ask Aletta then updates its working context.",[10,113,114],{},"You can turn memory off at any time. When it is switched off, the existing memory is retained so it can be used again if you re-enable the feature. If you want to start completely fresh, you can permanently delete everything Ask Aletta remembers from the same settings page.",[23,116,118],{"id":117},"an-assistant-that-adapts-to-your-work","An assistant that adapts to your work",[10,120,121],{},"Good assistance depends on context. A colleague who knows your specialty, preferred sources and way of communicating can usually help you more effectively than someone who has to ask the same introductory questions every time.",[10,123,124],{},"An AI assistant should be able to develop that same kind of working context, while keeping the user in control of what is remembered.",[10,126,127],{},"Ask Aletta now does exactly that.",{"title":129,"searchDepth":130,"depth":130,"links":131},"",2,[132,133,134,135],{"id":25,"depth":130,"text":26},{"id":63,"depth":130,"text":64},{"id":76,"depth":130,"text":77},{"id":117,"depth":130,"text":118},"Ask Aletta can now remember recurring preferences and working patterns, so you no longer have to provide the same context in every conversation.","md",{"date":139,"publishAt":140,"category":141,"author":142,"translations":143,"relatedPosts":145},"2026-08-04","2026-08-04T10:00:00+02:00","product","aram.zegerius",{"nl":144},"20260804-geheugen",[146,147],"20260721-asks-questions-back","20251111-personal-data-detection",true,null,"/en/updates/20260804-memory",{"title":5,"description":136},{"loc":150},"en/updates/20260804-memory","KJFZYJ0poPopjxy9-x-D1nJsAF4GFXy8eSeAgvqmSbM",[156,287],{"id":157,"title":158,"body":159,"description":275,"extension":137,"meta":276,"navigation":148,"ogImage":149,"path":282,"robots":149,"seo":283,"sitemap":284,"stem":285,"__hash__":286},"updates/en/updates/20260721-asks-questions-back.md","Ask Aletta now asks questions back",{"type":7,"value":160,"toc":269},[161,164,167,170,174,177,180,189,192,196,199,202,205,208,212,215,220,223,226,237,240,253,257,260,263,266],[10,162,163],{},"A good AI answer starts with a good question. In practice, however, many questions are only a few words long or leave out context that could materially change the answer.",[10,165,166],{},"Until now, an AI assistant would usually fill in those gaps itself. It would assume the most common situation, produce a generic answer and leave it to the user to check whether those assumptions were correct.",[10,168,169],{},"Ask Aletta now takes a different approach. When it does not yet have enough information to understand what the user is trying to achieve, it asks a small number of focused follow-up questions before answering.",[23,171,173],{"id":172},"helping-people-use-ai-well","Helping people use AI well",[10,175,176],{},"We have a history of building features that help people get more out of Ask Aletta.",[10,178,179],{},"We warn users when they are about to share personally identifiable information, before that information is sent for processing. Our prompt coach provides up to three suggestions for making a question more precise. We also maintain a growing prompt library where users can discover useful applications and start with a proven prompt, leaving only the relevant context for them to complete.",[10,181,182,183,188],{},"These features contribute to AI literacy: the knowledge and skills people need to use AI effectively and responsibly. The ",[85,184,187],{"href":185,"rel":186},"https://digital-strategy.ec.europa.eu/en/faqs/ai-literacy-questions-answers",[89],"EU AI Act"," rightly requires providers and deployers of AI systems to take measures to ensure a sufficient level of AI literacy among the people who work with those systems.",[10,190,191],{},"But regulation is not the reason we started building these features. We build them because better use leads to better outcomes, faster adoption and ultimately more value for healthcare professionals. Many of our customers tell us that this guidance is one of the reasons they choose Ask Aletta.",[23,193,195],{"id":194},"when-important-context-is-missing","When important context is missing",[10,197,198],{},"The principle “garbage in, garbage out” applies to every AI model. Our product design philosophy is therefore to make it as easy as possible to get a useful result, even when the first input is incomplete.",[10,200,201],{},"We frequently see questions consisting of only a few words. Other questions are clearly phrased but omit information that is necessary for a specific answer.",[10,203,204],{},"A question about a clinical guideline, for example, may have a different answer depending on whether it concerns a baby, a child, an adult or an older patient. The relevant steps may also change because of comorbidities, kidney function, current medication or the severity of the clinical presentation.",[10,206,207],{},"The same applies to drafting. Asking an AI assistant to write a patient message without specifying the intended outcome, relevant patient characteristics or prescribed treatment will usually produce a generic template. It may sound convincing while still missing information that matters in that particular situation.",[23,209,211],{"id":210},"from-assumptions-to-questions","From assumptions to questions",[10,213,214],{},"Consider this request:",[96,216,217],{},[10,218,219],{},"Draft a message with instructions about allopurinol. Explain what the patient needs to know about taking it, possible side effects and what to do if they have questions.",[10,221,222],{},"Previously, Ask Aletta would have drafted a general message based on the most common scenario. The healthcare professional would then have needed to check whether its assumptions matched the patient's situation.",[10,224,225],{},"Ask Aletta now first asks for the context that could affect the document, such as:",[31,227,228,231,234],{},[34,229,230],{},"What are the prescribed dosage and timing?",[34,232,233],{},"What is allopurinol being prescribed for?",[34,235,236],{},"Are there relevant patient factors, such as reduced kidney function, that need to be considered?",[10,238,239],{},"The healthcare professional remains in control and supplies the missing clinical context. Once those questions have been answered, Ask Aletta can produce a document that is specific to the intended situation rather than a generic template built on hidden assumptions.",[241,242,243,244,243,249],"figure",{},"\n  ",[245,246],"img",{"src":247,"alt":248},"/images/updates/ask-question-back-en.png","Ask Aletta asking focused follow-up questions before drafting a patient message about allopurinol",[250,251,252],"figcaption",{},"Ask Aletta asks a few focused follow-up questions before answering.",[23,254,256],{"id":255},"ask-first-answer-second","Ask first, answer second",[10,258,259],{},"This may appear to be a small interface change, but it represents a meaningful shift in how people work with AI.",[10,261,262],{},"Most AI tools are designed to answer immediately. That can make them feel fast, but speed is not useful when the system has misunderstood the question or silently filled in a crucial gap.",[10,264,265],{},"Sometimes the best way for an AI assistant to help is not to answer straight away. It is to recognise what it does not yet know, ask the right questions and only then continue.",[10,267,268],{},"That is what Ask Aletta now does.",{"title":129,"searchDepth":130,"depth":130,"links":270},[271,272,273,274],{"id":172,"depth":130,"text":173},{"id":194,"depth":130,"text":195},{"id":210,"depth":130,"text":211},{"id":255,"depth":130,"text":256},"When a question is missing important context, Ask Aletta now asks a small number of focused follow-up questions before answering.",{"date":277,"category":141,"author":142,"translations":278,"relatedPosts":280},"2026-07-21",{"nl":279},"20260721-vragen-terug",[281,147],"20251118-realtime-feedback","/en/updates/20260721-asks-questions-back",{"title":158,"description":275},{"loc":282},"en/updates/20260721-asks-questions-back","a_nL9JMKkngeqtS-jbzuQH99w3jPJXmWpbbQwlNPtZQ",{"id":288,"title":289,"body":290,"description":338,"extension":137,"meta":339,"navigation":148,"ogImage":149,"path":343,"robots":149,"seo":344,"sitemap":345,"stem":346,"__hash__":347},"updates/en/updates/20251111-personal-data-detection.md","Automatic detection of personal data",{"type":7,"value":291,"toc":333},[292,295,299,302,305,309,312,320,323,327,330],[10,293,294],{},"We know how important privacy is in healthcare. That's why we've made Ask Aletta even smarter. With a new feature that helps you prevent accidentally sharing personal data. Over the past months this feature was already running behind the scenes, and from today it's visible to all users.",[23,296,298],{"id":297},"the-problem","The problem",[10,300,301],{},"As a healthcare professional, you copy and paste dozens of times a day. From EHR to letter, from report to email, from note to search query. It's efficient and inevitable.",[10,303,304],{},"But in that hectic pace, it can happen: you accidentally send personal data in a question to an AI tool, such as a name or date of birth. With tools like ChatGPT, especially with a free subscription, that information disappears into a black box. You don't know where it goes and whether it will later be used in training the next version of ChatGPT.",[23,306,308],{"id":307},"our-solution","Our solution",[10,310,311],{},"Ask Aletta does this differently:",[10,313,314,315,319],{},"We automatically check every question for personal data ",[316,317,318],"strong",{},"before"," it is sent. This way we proactively help our users use AI safely. We do this with our own detection model, running entirely on our own hardware in the Netherlands. No external parties. No third-party cloud services.",[10,321,322],{},"Do we detect something? Then you as a user immediately receive a notification. With one click you anonymize the sensitive data and your search query can still be executed safely.",[23,324,326],{"id":325},"conclusion","Conclusion",[10,328,329],{},"In the hectic pace of daily practice, a mistake is quickly made. We help you prevent them.",[10,331,332],{},"Your patient data stays where it belongs. Within your organization. Not in a black box.",{"title":129,"searchDepth":130,"depth":130,"links":334},[335,336,337],{"id":297,"depth":130,"text":298},{"id":307,"depth":130,"text":308},{"id":325,"depth":130,"text":326},"A new feature that helps you prevent accidentally sharing personal data in your search queries.",{"date":340,"category":141,"author":142,"translations":341},"2025-11-11",{"nl":342},"20251111-persoonsgegevens-detectie","/en/updates/20251111-personal-data-detection",{"title":289,"description":338},{"loc":343},"en/updates/20251111-personal-data-detection","guh6pfuhsolAoz_StXQFJJr-_bpHYW9XTFB0Duh-Sss",1786722069821]