[{"data":1,"prerenderedAt":356},["ShallowReactive",2],{"update-en-20260728-guideline-images-flowcharts-tables":3,"related-posts-20260721-asks-questions-back-20251118-realtime-feedback-en":148},{"id":4,"title":5,"body":6,"description":129,"extension":130,"meta":131,"navigation":141,"ogImage":142,"path":143,"robots":142,"seo":144,"sitemap":145,"stem":146,"__hash__":147},"updates/en/updates/20260728-guideline-images-flowcharts-tables.md","Ask Aletta now reads images, flowcharts and tables in clinical guidelines",{"type":7,"value":8,"toc":121},"minimark",[9,13,16,19,22,27,30,33,36,40,43,46,49,53,56,62,65,68,81,84,93,97,100,103,106,109,113,116],[10,11,12],"p",{},"We're pretty excited about this one.",[10,14,15],{},"Clinical guidelines are not made up of text alone. Some of their most useful information is contained in images, flowcharts and tables: a decision tree showing the next treatment step, a dosing table organised by age or weight, or a diagram comparing two clinical approaches.",[10,17,18],{},"That information can be essential to answering a question correctly. Yet it is also the kind of information AI systems can easily miss.",[10,20,21],{},"Ask Aletta can now retrieve and use the information contained in these visual elements - and show the original table, diagram or flowchart directly in its answer.",[23,24,26],"h2",{"id":25},"why-visual-information-is-difficult-for-ai","Why visual information is difficult for AI",[10,28,29],{},"When a PDF is processed only as a layer of text, visual elements can become effectively invisible. The paragraphs surrounding a flowchart may be available, while the decisions, arrows and relationships inside the flowchart are not.",[10,31,32],{},"Simply extracting the words from an image does not necessarily solve this problem. A table is more than a collection of separate numbers and labels: their position in rows and columns determines what they mean. In a flowchart, the arrows and branches are often just as important as the text inside the boxes.",[10,34,35],{},"If that structure is lost, an AI system may overlook the part of the guideline that contains the actual answer.",[23,37,39],{"id":38},"processing-the-complete-guideline","Processing the complete guideline",[10,41,42],{},"When we add a new guideline to Ask Aletta's knowledge base, we now process both its written and visual content.",[10,44,45],{},"Images, tables and flowcharts are converted into a representation that Ask Aletta can retrieve alongside the surrounding text. The original visual element remains connected to its source and page, allowing Ask Aletta to use it when answering and display it directly to the healthcare professional.",[10,47,48],{},"This has two advantages. First, information contained only in a visual element is no longer automatically excluded from the answer. Second, the user can inspect the original table or flowchart and verify how it relates to the response.",[23,50,52],{"id":51},"from-a-question-to-the-relevant-flowchart","From a question to the relevant flowchart",[10,54,55],{},"Consider this question:",[57,58,59],"blockquote",{},[10,60,61],{},"Which steps should I follow when treating functional constipation in a child under 1 year old?",[10,63,64],{},"The relevant Dutch paediatric guideline contains a flowchart showing the treatment pathway. It covers alarm symptoms, initial advice, evaluation moments, first-choice medication and the circumstances in which further investigation or referral should be considered.",[10,66,67],{},"Instead of relying only on the surrounding paragraphs, Ask Aletta can use the information in the flowchart and show it in the answer.",[69,70,71,72,71,77],"figure",{},"\n  ",[73,74],"img",{"src":75,"alt":76},"/images/updates/20260728-visual-guidelines-constipation.png","Ask Aletta displaying the treatment flowchart for functional constipation in a child under 1 year old",[78,79,80],"figcaption",{},"Ask Aletta uses and displays the relevant flowchart from the Dutch paediatric guideline.",[10,82,83],{},"The same applies to diagrams that compare different approaches. When asked about the top-down and bottom-up variants of a low-FODMAP diet, Ask Aletta explains the distinction and displays the schematic overview from the underlying guideline.",[69,85,71,86,71,90],{},[73,87],{"src":88,"alt":89},"/images/updates/20260728-visual-guidelines-fodmap.png","Ask Aletta explaining and displaying the top-down and bottom-up approaches to a low-FODMAP diet",[78,91,92],{},"The original diagram remains visible alongside the explanation and source reference.",[23,94,96],{"id":95},"showing-the-evidence-not-hiding-it","Showing the evidence, not hiding it",[10,98,99],{},"Understanding visual information is only half of the feature. We also want healthcare professionals to see the evidence for themselves.",[10,101,102],{},"A written summary can help someone find an answer quickly, but it should not replace the underlying guideline. That is why Ask Aletta displays the original visual element together with its source and page reference. The healthcare professional can review the image in context and decide how it applies to the situation in front of them.",[10,104,105],{},"This builds on a principle that has guided Ask Aletta from the beginning: every answer should be traceable to its source. That now includes the parts of a guideline that cannot be captured in paragraphs alone.",[10,107,108],{},"Want to try it yourself? Ask:",[57,110,111],{},[10,112,61],{},[10,114,115],{},"Or:",[57,117,118],{},[10,119,120],{},"What are the top-down and bottom-up approaches to a low-FODMAP diet?",{"title":122,"searchDepth":123,"depth":123,"links":124},"",2,[125,126,127,128],{"id":25,"depth":123,"text":26},{"id":38,"depth":123,"text":39},{"id":51,"depth":123,"text":52},{"id":95,"depth":123,"text":96},"Important clinical information is often captured in a table or flowchart rather than the surrounding text. Ask Aletta can now retrieve, use and show that information.","md",{"date":132,"publishAt":133,"category":134,"author":135,"image":75,"translations":136,"relatedPosts":138},"2026-07-28","2026-07-28T10:00:00+02:00","product","aram.zegerius",{"nl":137},"20260728-afbeeldingen-stroomschemas-tabellen",[139,140],"20260721-asks-questions-back","20251118-realtime-feedback",true,null,"/en/updates/20260728-guideline-images-flowcharts-tables",{"title":5,"description":129},{"loc":143},"en/updates/20260728-guideline-images-flowcharts-tables","6PaGssDjt3YFdaGZdEJVXFEYlmuyno95dRIwJZg7cLg",[149,280],{"id":150,"title":151,"body":152,"description":268,"extension":130,"meta":269,"navigation":141,"ogImage":142,"path":275,"robots":142,"seo":276,"sitemap":277,"stem":278,"__hash__":279},"updates/en/updates/20260721-asks-questions-back.md","Ask Aletta now asks questions back",{"type":7,"value":153,"toc":262},[154,157,160,163,167,170,173,184,187,191,194,197,200,203,207,210,215,218,221,234,237,246,250,253,256,259],[10,155,156],{},"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.",[10,158,159],{},"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.",[10,161,162],{},"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.",[23,164,166],{"id":165},"helping-people-use-ai-well","Helping people use AI well",[10,168,169],{},"We have a history of building features that help people get more out of Ask Aletta.",[10,171,172],{},"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.",[10,174,175,176,183],{},"These features contribute to AI literacy: the knowledge and skills people need to use AI effectively and responsibly. The ",[177,178,182],"a",{"href":179,"rel":180},"https://digital-strategy.ec.europa.eu/en/faqs/ai-literacy-questions-answers",[181],"nofollow","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.",[10,185,186],{},"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.",[23,188,190],{"id":189},"when-important-context-is-missing","When important context is missing",[10,192,193],{},"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.",[10,195,196],{},"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.",[10,198,199],{},"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.",[10,201,202],{},"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.",[23,204,206],{"id":205},"from-assumptions-to-questions","From assumptions to questions",[10,208,209],{},"Consider this request:",[57,211,212],{},[10,213,214],{},"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.",[10,216,217],{},"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.",[10,219,220],{},"Ask Aletta now first asks for the context that could affect the document, such as:",[222,223,224,228,231],"ul",{},[225,226,227],"li",{},"What are the prescribed dosage and timing?",[225,229,230],{},"What is allopurinol being prescribed for?",[225,232,233],{},"Are there relevant patient factors, such as reduced kidney function, that need to be considered?",[10,235,236],{},"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.",[69,238,71,239,71,243],{},[73,240],{"src":241,"alt":242},"/images/updates/ask-question-back-en.png","Ask Aletta asking focused follow-up questions before drafting a patient message about allopurinol",[78,244,245],{},"Ask Aletta asks a few focused follow-up questions before answering.",[23,247,249],{"id":248},"ask-first-answer-second","Ask first, answer second",[10,251,252],{},"This may appear to be a small interface change, but it represents a meaningful shift in how people work with AI.",[10,254,255],{},"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.",[10,257,258],{},"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.",[10,260,261],{},"That is what Ask Aletta now does.",{"title":122,"searchDepth":123,"depth":123,"links":263},[264,265,266,267],{"id":165,"depth":123,"text":166},{"id":189,"depth":123,"text":190},{"id":205,"depth":123,"text":206},{"id":248,"depth":123,"text":249},"When a question is missing important context, Ask Aletta now asks a small number of focused follow-up questions before answering.",{"date":270,"category":134,"author":135,"translations":271,"relatedPosts":273},"2026-07-21",{"nl":272},"20260721-vragen-terug",[140,274],"20251111-personal-data-detection","/en/updates/20260721-asks-questions-back",{"title":151,"description":268},{"loc":275},"en/updates/20260721-asks-questions-back","a_nL9JMKkngeqtS-jbzuQH99w3jPJXmWpbbQwlNPtZQ",{"id":281,"title":282,"body":283,"description":348,"extension":130,"meta":349,"navigation":141,"ogImage":142,"path":351,"robots":142,"seo":352,"sitemap":353,"stem":354,"__hash__":355},"updates/en/updates/20251118-realtime-feedback.md","Real-time feedback on your search queries",{"type":7,"value":284,"toc":343},[285,292,295,298,302,305,308,312,315,330,333,337,340],[10,286,287,291],{},[288,289,290],"em",{},"Constipation child"," - such short search terms are common with AI tools like Ask Aletta: two words, without context, without a concrete question, without purpose.",[10,293,294],{},"It's as if a patient walks in with just: \"Doctor, I have something.\"",[10,296,297],{},"With so little information, you can't help in a targeted way. With AI it works exactly the same. Without a good history, no good diagnosis. Without a good question, no targeted answer.",[23,299,301],{"id":300},"and-thats-completely-logical","And that's completely logical",[10,303,304],{},"AI-driven searching is a completely new way of working. Just as you once learned to delegate effectively to assistants or to hand over in a structured way with SBAR, you now have to learn to query AI effectively.",[10,306,307],{},"That requires training. And especially: direct guidance at the moment you're working with it.",[23,309,311],{"id":310},"thats-why-ask-aletta-launches-today-real-time-feedback","That's why Ask Aletta launches today: real-time feedback",[10,313,314],{},"During every search query you get immediate insight:",[222,316,317,324],{},[225,318,319,323],{},[320,321,322],"strong",{},"Clear question",": you're on the right track",[225,325,326,329],{},[320,327,328],{},"Points for improvement",": a number of concrete tips + an example question you can use immediately",[10,331,332],{},"No e-learning afterwards. No extra course. Just direct support while you're doing your daily work.",[23,334,336],{"id":335},"the-result","The result",[10,338,339],{},"A specific question leads directly to the right answer. A vague question yields a broad answer that no one is satisfied with.",[10,341,342],{},"Ask Aletta helps you ask that first question - every time.",{"title":122,"searchDepth":123,"depth":123,"links":344},[345,346,347],{"id":300,"depth":123,"text":301},{"id":310,"depth":123,"text":311},{"id":335,"depth":123,"text":336},"Ask Aletta now actively helps you ask better questions with direct feedback during every search.",{"date":350,"category":134,"author":135},"2025-11-18","/en/updates/20251118-realtime-feedback",{"title":282,"description":348},{"loc":351},"en/updates/20251118-realtime-feedback","rai-HGFt3Qf4rTZ_ixeGpxcMaUcPySGBpQiaTA6sN-Y",1786722069643]