[{"data":1,"prerenderedAt":1047},["ShallowReactive",2],{"blog-article-en-ai-clinical-documentation-consultations":3,"blog-related-en-ai-clinical-documentation-consultations":729},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"seoTitle":10,"locale":7,"translationSlug":11,"date":12,"updated":13,"image":14,"author":15,"tags":18,"takeaways":22,"faq":28,"body":47,"_type":723,"_id":724,"_source":725,"_file":726,"_stem":727,"_extension":728},"/blog/ai-clinical-documentation-consultations","blog",false,"en","AI for Clinical Documentation: Fewer Hours Writing, Without Losing Control of the Note","How AI transcribes and summarises consultations, drafts letters and writes into clinical software, with the clinician signing off. GDPR, MDR and costs.","AI clinical documentation: notes and records","ia-documentacao-clinica-consultas","2026-10-19","2026-11-14","/images/blog/ia-documentacao-clinica.jpg",{"name":16,"role":17},"Pedro Santos","Principal Software Architect",[19,20,21],"Healthcare","Artificial Intelligence","Compliance",[23,24,25,26,27],"A clinical documentation assistant does not write the note for the clinician. It prepares a structured draft from the consultation, and it is the doctor, dentist, physiotherapist or vet who reviews, corrects and signs it.","The errors that matter are not spelling mistakes. They are flipped negations, the wrong side of the body, misheard doses and findings nobody mentioned but the model added because they \"are usually there\". The system has to be designed to make them visible.","The line between documentation and clinical decision support is the most important decision in the project. The more the system limits itself to recording what was said and done, the closer it stays to documentation; once it starts suggesting diagnoses, doses or priorities, it moves towards being a medical device and a different regulatory regime. Even transcription needs assessing, because products of this kind have been certified as medical devices.","Health data is a special category under the GDPR. In practice that means EU hosting, contracts that rule out retention and training, the patient's permission to record, short retention periods for audio and a log of who accessed what.","A first use case in production, one specialty and one note template, typically falls between €7,500 and €15,000. When documentation is part of a custom-built clinical platform, the investment follows the scope of that platform.",[29,32,35,38,41,44],{"q":30,"a":31},"Is an assistant that transcribes and summarises consultations a medical device?","It depends on the intended purpose it is designed and marketed for, and there is no automatic answer. A system that only records what was said, for the clinician to review and sign, sits closer to documentation; one that suggests diagnoses, alerts or treatments moves towards clinical decision support, which may fall under Regulation (EU) 2017/745. This boundary should be assessed case by case with whoever provides the clinic's legal and regulatory advice.",{"q":33,"a":34},"Do we need the patient's consent to record the consultation?","The legal basis for processing health data in the provision of care is not, as a rule, consent, but recording the patient's voice is an additional processing activity they have to be informed about, and in practice it makes sense for them to be able to refuse it. That is why we always design a clear, simple request for permission, logged in the patient record, and a way of working without recording for anyone who declines. The final decision on the legal basis belongs to the clinic's data protection officer.",{"q":36,"a":37},"Will our consultations end up training AI models?","Not if the architecture and the contracts are built to prevent it. We use providers with hosting in the European Union and clauses that rule out retention of, and training on, the data sent, and the audio is deleted as soon as the note is signed, unless the clinic decides otherwise.",{"q":39,"a":40},"Does it work with the clinical software we already use?","Almost always, with different levels of integration. If the software has a ready-made connection, the reviewed note is written straight into the patient record; if it does not, the draft sits on a screen alongside it, ready to be transferred section by section, which already saves most of the time. Full integration is decided once we have seen the system from the inside.",{"q":42,"a":43},"How much does it cost and how long does it take?","A first use case in production, with one specialty and one note template, typically falls between €7,500 and €15,000, with six to ten weeks to a pilot with real clinicians. As part of a custom clinical platform, the figure follows that platform's ranges, from €15,000 to over €40,000 depending on the number of clinics and whether billing is integrated.",{"q":45,"a":46},"Does it also work for psychology or veterinary practice?","It does, but with different designs. In psychology many people prefer not to have the session recorded, and the more sensible model is dictation by the clinician at the end, with a structured summary built from that. In veterinary practice the person speaking is the owner, not the patient, and the note has to handle species, weight and doses per kilo, which changes the note templates and the checks.",{"type":48,"children":49,"toc":701},"root",[50,58,63,70,75,81,86,91,97,137,143,148,159,169,179,189,194,200,205,328,333,338,343,349,363,373,383,393,403,408,414,424,434,444,454,460,467,472,478,483,489,494,500,505,511,524,530,565,621,626,632,637,642,654,660,688],{"type":51,"tag":52,"props":53,"children":54},"element","p",{},[55],{"type":56,"value":57},"text","It is a quarter past eight in the evening and the lights are still on in three\nconsulting rooms. The last appointment finished at seven, but the doctor who saw\nit is finishing the notes for the eighteen patients she saw during the day, the\nphysiotherapist is writing up the afternoon's progress notes and, in the room at\nthe end of the corridor, someone is preparing the referral letter the four\no'clock patient needs for tomorrow. Nobody complains out loud, because it has\nbeen like this for years. The clinical director knows this is time that never\nturns back into consultations, and also knows, if they ask carefully, that at\nleast one of the clinicians is already pasting notes into an AI assistant on a\npersonal account to \"get it done faster\".",{"type":51,"tag":52,"props":59,"children":60},{},[61],{"type":56,"value":62},"That second point is usually what starts the conversation. The appetite for\nusing AI to write less already exists inside the clinic. The real question is\nwhether it happens by design, with the data in the right place and the clinician\nin control, or informally, with health data moving through tools nobody has\nassessed.",{"type":51,"tag":64,"props":65,"children":67},"h2",{"id":66},"short-answer",[68],{"type":56,"value":69},"Short answer",{"type":51,"tag":52,"props":71,"children":72},{},[73],{"type":56,"value":74},"AI can already take a large share of record-keeping time off clinicians, as long\nas it works as a draft and not as the author of the note. It listens to the\nconsultation or the dictation, returns a structured note in the specialty's\nformat and prepares letters and reports, and it is always the clinician who\nreviews, corrects and signs. To stay on the documentation side, the system\nrecords and rewrites, never suggests diagnoses or doses, and the data stays in\nthe European Union, with no retention or training. A first use case in\nproduction typically falls between €7,500 and €15,000.",{"type":51,"tag":64,"props":76,"children":78},{"id":77},"a-good-draft-signed-by-the-clinician",[79],{"type":56,"value":80},"A good draft, signed by the clinician",{"type":51,"tag":52,"props":82,"children":83},{},[84],{"type":56,"value":85},"A clinical documentation assistant listens to the consultation (or to the\nclinician's dictation), transcribes it and returns a structured draft in the\nformat that specialty uses: presenting complaint, history, examination, plan, or\nthe progress note for a physiotherapy session, or the tooth-by-tooth record of a\ndental appointment. From the same material it prepares what comes next: the\nreport for the insurer, the letter to a colleague, the summary for the patient.\nBefore the next appointment, it can pull into a single paragraph what is spread\nacross years of records.",{"type":51,"tag":52,"props":87,"children":88},{},[89],{"type":56,"value":90},"What it does not do is decide. The final text always belongs to the clinician,\nwho reads, corrects and signs it. This is not a decorative safeguard: it keeps\nclinical responsibility exactly where it sits today, and it also helps keep the\nsystem on the right side of a regulatory boundary we cover further down.",{"type":51,"tag":64,"props":92,"children":94},{"id":93},"signs-your-clinic-has-this-problem",[95],{"type":56,"value":96},"Signs your clinic has this problem",{"type":51,"tag":98,"props":99,"children":100},"ul",{},[101,107,112,117,122,127,132],{"type":51,"tag":102,"props":103,"children":104},"li",{},[105],{"type":56,"value":106},"clinicians regularly stay on after the last appointment to write up notes;",{"type":51,"tag":102,"props":108,"children":109},{},[110],{"type":56,"value":111},"some notes are written the following day, from memory, with less detail than\nthe consultation had;",{"type":51,"tag":102,"props":113,"children":114},{},[115],{"type":56,"value":116},"referral letters and insurer reports pile up and go out days late;",{"type":51,"tag":102,"props":118,"children":119},{},[120],{"type":56,"value":121},"the clinician spends part of the consultation facing the screen instead of\nthe patient;",{"type":51,"tag":102,"props":123,"children":124},{},[125],{"type":56,"value":126},"before every follow-up, someone manually works through years of records to\nunderstand where things stand;",{"type":51,"tag":102,"props":128,"children":129},{},[130],{"type":56,"value":131},"coding of procedures and diagnoses for billing is done at the end of the month\nand leads to rejected claims;",{"type":51,"tag":102,"props":133,"children":134},{},[135],{"type":56,"value":136},"you already know, or suspect, that some staff use personal AI tools with\npatient data.",{"type":51,"tag":64,"props":138,"children":140},{"id":139},"where-these-systems-fail-and-how-to-design-around-it",[141],{"type":56,"value":142},"Where these systems fail, and how to design around it",{"type":51,"tag":52,"props":144,"children":145},{},[146],{"type":56,"value":147},"Transcribing European Portuguese with clinical vocabulary, which is what clinics\nin Portugal need, already works well enough to be useful, especially with a good\nmicrophone in the consulting room. What separates a useful system\nfrom a dangerous one lies in the errors that remain, because they are errors\nthat look like correct text.",{"type":51,"tag":52,"props":149,"children":150},{},[151,157],{"type":51,"tag":152,"props":153,"children":154},"strong",{},[155],{"type":56,"value":156},"Negations and laterality.",{"type":56,"value":158}," \"Denies chest pain\" and \"reports chest pain\" differ\nby one word, just as right knee and left knee do. In a fluent draft, these swaps\nslip past anyone reading in a hurry. That is why every sentence in the draft is\nlinked to the transcript excerpt it came from, and sentences containing a\nnegation, a side of the body, a dose or a numeric value are flagged for review.",{"type":51,"tag":52,"props":160,"children":161},{},[162,167],{"type":51,"tag":152,"props":163,"children":164},{},[165],{"type":56,"value":166},"Findings nobody mentioned.",{"type":56,"value":168}," A model trained on millions of notes knows that a\nroutine consultation \"usually\" includes normal auscultation. If the doctor did\nnot mention it, the draft cannot include it. The rule we apply is simple: a field\nwith no source in the consultation stays empty, and empty looks visibly\ndifferent from normal.",{"type":51,"tag":52,"props":170,"children":171},{},[172,177],{"type":51,"tag":152,"props":173,"children":174},{},[175],{"type":56,"value":176},"Medicines, doses and units.",{"type":56,"value":178}," Similar brand names, milligrams confused with\nmillilitres, \"twice\" heard as \"three times\". We check medicine names against the\nlist the clinic actually uses and flag every dose for explicit confirmation.\nPrescribing still happens in the system built for it, never from the draft.",{"type":51,"tag":52,"props":180,"children":181},{},[182,187],{"type":51,"tag":152,"props":183,"children":184},{},[185],{"type":56,"value":186},"Who said what.",{"type":56,"value":188}," In a consultation the clinician, the patient and sometimes a\nrelative all speak; in veterinary practice it is the owner. What the patient\nreports and what the clinician observes have to sit in different sections, or\nthe note ends up attributing to the examination something that was only a\ncomplaint.",{"type":51,"tag":52,"props":190,"children":191},{},[192],{"type":56,"value":193},"The indicator that best shows whether the system is working is not transcription\naccuracy, it is the edit rate: what percentage of the draft the clinician changes\nbefore signing, and in which sections. When one section is always rewritten, the\nproblem lies in the note template, not in the clinician.",{"type":51,"tag":64,"props":195,"children":197},{"id":196},"the-line-between-documentation-and-clinical-decision-support",[198],{"type":56,"value":199},"The line between documentation and clinical decision support",{"type":51,"tag":52,"props":201,"children":202},{},[203],{"type":56,"value":204},"This is the part most often treated lightly, and the one that can cost the most.\nRegulation (EU) 2017/745, the Medical Device Regulation (MDR), applies to\nsoftware whose intended purpose is to support diagnosis, prevention, monitoring\nor treatment. Whether a system is a medical device depends on the purpose it is\ndesigned and presented for, not on the fact that it uses AI.",{"type":51,"tag":206,"props":207,"children":208},"table",{},[209,233],{"type":51,"tag":210,"props":211,"children":212},"thead",{},[213],{"type":51,"tag":214,"props":215,"children":216},"tr",{},[217,223,228],{"type":51,"tag":218,"props":219,"children":220},"th",{},[221],{"type":56,"value":222},"Function",{"type":51,"tag":218,"props":224,"children":225},{},[226],{"type":56,"value":227},"What it does",{"type":51,"tag":218,"props":229,"children":230},{},[231],{"type":56,"value":232},"Tendency",{"type":51,"tag":234,"props":235,"children":236},"tbody",{},[237,256,274,292,310],{"type":51,"tag":214,"props":238,"children":239},{},[240,246,251],{"type":51,"tag":241,"props":242,"children":243},"td",{},[244],{"type":56,"value":245},"Transcription and draft note",{"type":51,"tag":241,"props":247,"children":248},{},[249],{"type":56,"value":250},"Records what was said, for review and sign-off",{"type":51,"tag":241,"props":252,"children":253},{},[254],{"type":56,"value":255},"Closer to documentation, but needs assessing",{"type":51,"tag":214,"props":257,"children":258},{},[259,264,269],{"type":51,"tag":241,"props":260,"children":261},{},[262],{"type":56,"value":263},"Letters, reports, patient summary",{"type":51,"tag":241,"props":265,"children":266},{},[267],{"type":56,"value":268},"Rewrites information already validated by the clinician",{"type":51,"tag":241,"props":270,"children":271},{},[272],{"type":56,"value":273},"Documentation and communication",{"type":51,"tag":214,"props":275,"children":276},{},[277,282,287],{"type":51,"tag":241,"props":278,"children":279},{},[280],{"type":56,"value":281},"History summary before the appointment",{"type":51,"tag":241,"props":283,"children":284},{},[285],{"type":56,"value":286},"Brings together what exists, linked to its sources",{"type":51,"tag":241,"props":288,"children":289},{},[290],{"type":56,"value":291},"Borderline if it starts to prioritise or alert",{"type":51,"tag":214,"props":293,"children":294},{},[295,300,305],{"type":51,"tag":241,"props":296,"children":297},{},[298],{"type":56,"value":299},"Billing code suggestions",{"type":51,"tag":241,"props":301,"children":302},{},[303],{"type":56,"value":304},"Proposes procedure codes, confirmed by a person",{"type":51,"tag":241,"props":306,"children":307},{},[308],{"type":56,"value":309},"Administrative, with mandatory review",{"type":51,"tag":214,"props":311,"children":312},{},[313,318,323],{"type":51,"tag":241,"props":314,"children":315},{},[316],{"type":56,"value":317},"Diagnosis, dose or clinical alert suggestions",{"type":51,"tag":241,"props":319,"children":320},{},[321],{"type":56,"value":322},"Influences the clinician's decision",{"type":51,"tag":241,"props":324,"children":325},{},[326],{"type":56,"value":327},"Likely a medical device",{"type":51,"tag":52,"props":329,"children":330},{},[331],{"type":56,"value":332},"The right-hand column is a tendency, not a classification. Even transcription is\nnot automatically outside the regulation: some European clinical transcription\nvendors have chosen to certify their products as medical devices, precisely\nbecause the note feeds future\ndecisions, and the question is not settled. That is why the\nintended purpose of each function is written down from the start of the project,\nso that it can be assessed by whoever provides the clinic's legal and regulatory\nadvice.",{"type":51,"tag":52,"props":334,"children":335},{},[336],{"type":56,"value":337},"The AI Act adds another layer. AI systems that are medical devices, or safety\ncomponents of a device, and that are subject to assessment by a notified body\nfall into the high-risk category. Under the amendments in the so-called Digital\nOmnibus on AI, in force since July 2026, the high-risk obligations for products\nalready regulated by sector legislation now apply from 2 August 2028. That buys\ntime, but the substance of the requirements is unchanged, and how they apply to\na specific system should be confirmed with your legal advisers.",{"type":51,"tag":52,"props":339,"children":340},{},[341],{"type":56,"value":342},"Our practical position: we design documentation functions to record and\nrewrite, never to suggest or decide, and we put that intended purpose in writing\nfrom the start. That does not replace the regulatory assessment. If it\nconcludes that the system is a medical device, or if the clinic genuinely wants\nclinical decision support, we are talking about a different kind of project,\nwith a quality management system, clinical evaluation and CE marking, and we say\nso in the very first conversation.",{"type":51,"tag":64,"props":344,"children":346},{"id":345},"health-data-what-has-to-be-decided-before-you-record",[347],{"type":56,"value":348},"Health data: what has to be decided before you record",{"type":51,"tag":52,"props":350,"children":351},{},[352,354,361],{"type":56,"value":353},"Health data is a special category of personal data under Article 9 of the GDPR.\nNone of this stops the project, but it does require a few decisions at the\ndesign stage, where they cost little. The general principles are in our article\non ",{"type":51,"tag":355,"props":356,"children":358},"a",{"href":357},"/en/blog/gdpr-ai-act-before-ai-agents-production",[359],{"type":56,"value":360},"GDPR and the AI Act before putting AI into\nproduction",{"type":56,"value":362},"; in a clinical\nsetting there are some specific points.",{"type":51,"tag":52,"props":364,"children":365},{},[366,371],{"type":51,"tag":152,"props":367,"children":368},{},[369],{"type":56,"value":370},"Permission to record.",{"type":56,"value":372}," The patient has to know the consultation is being\nrecorded and what for, and the design we advocate lets them say no without any\nconsequence. A short\nrequest at reception or at the start of the consultation, logged in the patient\nrecord, and a mode without recording, in which the clinician dictates a summary\nat the end.",{"type":51,"tag":52,"props":374,"children":375},{},[376,381],{"type":51,"tag":152,"props":377,"children":378},{},[379],{"type":56,"value":380},"Where the data lives.",{"type":56,"value":382}," Hosting in the European Union, in accounts the clinic\ncontrols, with contracts that rule out retention of, and training on, the data\nsent. Consumer tools, even paid ones, rarely offer this by default.",{"type":51,"tag":52,"props":384,"children":385},{},[386,391],{"type":51,"tag":152,"props":387,"children":388},{},[389],{"type":56,"value":390},"How long the audio lives.",{"type":56,"value":392}," In most cases, until the note is signed. Keeping\nrecordings for years increases risk without adding clinical value.",{"type":51,"tag":52,"props":394,"children":395},{},[396,401],{"type":51,"tag":152,"props":397,"children":398},{},[399],{"type":56,"value":400},"Who has access and what gets logged.",{"type":56,"value":402}," Role-based profiles, a log of every\naccess, and the draft stored alongside the signed version, so it is always clear\nwhat was generated and what the clinician decided.",{"type":51,"tag":52,"props":404,"children":405},{},[406],{"type":56,"value":407},"The processing will very likely require a data protection impact assessment. We\nprepare the technical documentation the data protection officer needs; we do not\ngive legal advice.",{"type":51,"tag":64,"props":409,"children":411},{"id":410},"what-usually-goes-wrong",[412],{"type":56,"value":413},"What usually goes wrong",{"type":51,"tag":52,"props":415,"children":416},{},[417,422],{"type":51,"tag":152,"props":418,"children":419},{},[420],{"type":56,"value":421},"Leaving each clinician to sort it out alone.",{"type":56,"value":423}," This is already happening in\nmany clinics. The result is a clinical record produced outside the clinic's\nsystems, with no audit trail and no guarantees about the data.",{"type":51,"tag":52,"props":425,"children":426},{},[427,432],{"type":51,"tag":152,"props":428,"children":429},{},[430],{"type":56,"value":431},"Buying the tool without thinking about where the note ends up.",{"type":56,"value":433}," If the draft\nlives in another application and has to be copied field by field into the\nclinical software, part of the time saved is lost in the transfer, and adoption\ndrops off after a few weeks.",{"type":51,"tag":52,"props":435,"children":436},{},[437,442],{"type":51,"tag":152,"props":438,"children":439},{},[440],{"type":56,"value":441},"Letting the system \"complete\" the note.",{"type":56,"value":443}," Suggesting the most likely diagnosis\nor the next test feels like a natural improvement. It is exactly the step that\ncan change the regulatory status of the whole system.",{"type":51,"tag":52,"props":445,"children":446},{},[447,452],{"type":51,"tag":152,"props":448,"children":449},{},[450],{"type":56,"value":451},"One note template for everyone.",{"type":56,"value":453}," The progress note for a physiotherapy\nsession, an orthodontic appointment and a dog's vaccination do not fit the same\nformat. A draft in the wrong structure takes more work to correct than writing\nfrom scratch.",{"type":51,"tag":64,"props":455,"children":457},{"id":456},"from-note-template-to-pilot",[458],{"type":56,"value":459},"From note template to pilot",{"type":51,"tag":461,"props":462,"children":464},"h3",{"id":463},"_1-free-diagnosis",[465],{"type":56,"value":466},"1. Free diagnosis",{"type":51,"tag":52,"props":468,"children":469},{},[470],{"type":56,"value":471},"A conversation about specialties, consultation volume, the clinical software in\nuse and where most time is lost today. No commitment, and by the end it is clear\nwhether there is a use case worth pursuing and where to start.",{"type":51,"tag":461,"props":473,"children":475},{"id":474},"_2-note-templates-built-with-the-people-who-will-use-them",[476],{"type":56,"value":477},"2. Note templates built with the people who will use them",{"type":51,"tag":52,"props":479,"children":480},{},[481],{"type":56,"value":482},"We sit down with two or three clinicians from each specialty and define the\nstructure of the note, what is never filled in automatically and which local\nexpressions the system needs to recognise. This is the phase that most\ninfluences the edit rate.",{"type":51,"tag":461,"props":484,"children":486},{"id":485},"_3-purpose-data-and-consent",[487],{"type":56,"value":488},"3. Purpose, data and consent",{"type":51,"tag":52,"props":490,"children":491},{},[492],{"type":56,"value":493},"We put in writing the intended purpose of each function, the patient permission\nflow, the retention periods and the processors involved. This is the material\nthe data protection officer and legal advisers need to carry out their\nassessment.",{"type":51,"tag":461,"props":495,"children":497},{"id":496},"_4-pilot-with-real-clinicians",[498],{"type":56,"value":499},"4. Pilot with real clinicians",{"type":51,"tag":52,"props":501,"children":502},{},[503],{"type":56,"value":504},"Two to four weeks with a small group, measuring time per note, edit rate per\nsection and errors by type. Whatever needs adjusting is adjusted before rolling\nit out further.",{"type":51,"tag":461,"props":506,"children":508},{"id":507},"_5-integration-and-roll-out",[509],{"type":56,"value":510},"5. Integration and roll-out",{"type":51,"tag":52,"props":512,"children":513},{},[514,516,522],{"type":56,"value":515},"The reviewed note is written into the patient record through an integration with the clinical software, without changing systems, in the same way you ",{"type":51,"tag":355,"props":517,"children":519},{"href":518},"/en/blog/add-ai-to-existing-business-software",[520],{"type":56,"value":521},"add AI to the software a business already uses",{"type":56,"value":523},". Letters, reports and the\nhistory summary are added, and the system is extended to other specialties or\nother clinics in the group.",{"type":51,"tag":64,"props":525,"children":527},{"id":526},"from-first-use-case-to-clinical-platform-the-figures",[528],{"type":56,"value":529},"From first use case to clinical platform: the figures",{"type":51,"tag":52,"props":531,"children":532},{},[533,535,540,542,547,549,555,557,563],{"type":56,"value":534},"A ",{"type":51,"tag":152,"props":536,"children":537},{},[538],{"type":56,"value":539},"first use case in production",{"type":56,"value":541},", one specialty, one note template and the\ndraft delivered alongside the clinical software, typically falls ",{"type":51,"tag":152,"props":543,"children":544},{},[545],{"type":56,"value":546},"between\n€7,500 and €15,000",{"type":56,"value":548},", with six to ten weeks to the pilot. That is the scope of\nour ",{"type":51,"tag":355,"props":550,"children":552},{"href":551},"/en/solucoes/ia-para-empresas",[553],{"type":56,"value":554},"AI for business",{"type":56,"value":556}," offering. What makes that\ntimeline shrink or stretch is explained in ",{"type":51,"tag":355,"props":558,"children":560},{"href":559},"/en/blog/how-long-a-custom-software-project-takes",[561],{"type":56,"value":562},"how long a custom software or AI\nproject takes",{"type":56,"value":564},".",{"type":51,"tag":52,"props":566,"children":567},{},[568,570,575,577,582,584,589,591,597,599,605,607,613,615,620],{"type":56,"value":569},"When documentation is part of a custom-built clinical platform, the figure\nfollows the scope of that platform: ",{"type":51,"tag":152,"props":571,"children":572},{},[573],{"type":56,"value":574},"between €15,000 and €25,000",{"type":56,"value":576}," for a single\nclinic, ",{"type":51,"tag":152,"props":578,"children":579},{},[580],{"type":56,"value":581},"between €25,000 and €40,000",{"type":56,"value":583}," with integrated billing and ",{"type":51,"tag":152,"props":585,"children":586},{},[587],{"type":56,"value":588},"from\n€40,000",{"type":56,"value":590}," for a network of clinics, on our ",{"type":51,"tag":355,"props":592,"children":594},{"href":593},"/en/solucoes/plataforma-agendamento-clinicas",[595],{"type":56,"value":596},"clinic\nplatform",{"type":56,"value":598},", which can also include\nthe ",{"type":51,"tag":355,"props":600,"children":602},{"href":601},"/en/blog/ai-clinical-scheduling",[603],{"type":56,"value":604},"agent that confirms appointments and cuts no-shows",{"type":56,"value":606},". For veterinary\npractices, ",{"type":51,"tag":355,"props":608,"children":610},{"href":609},"/en/solucoes/software-gestao-clinicas-veterinarias",[611],{"type":56,"value":612},"veterinary clinic\nmanagement",{"type":56,"value":614}," falls ",{"type":51,"tag":152,"props":616,"children":617},{},[618],{"type":56,"value":619},"between\n€18,000 and €30,000",{"type":56,"value":564},{"type":51,"tag":52,"props":622,"children":623},{},[624],{"type":56,"value":625},"What pushes the figure up: several specialties with their own note templates,\nclinical software without a ready-made connection, coding for several insurers and health\nschemes, and groups with different rules in each clinic. What brings it down: one\ndominant specialty, software with documented integration and clinicians\navailable for the pilot. There is also a recurring cost for transcription and\nmodels, which depends on consultation volume and is estimated in the proposal.",{"type":51,"tag":64,"props":627,"children":629},{"id":628},"when-it-is-better-to-use-what-already-exists",[630],{"type":56,"value":631},"When it is better to use what already exists",{"type":51,"tag":52,"props":633,"children":634},{},[635],{"type":56,"value":636},"If the clinic has few clinicians, one specialty and clinical software that\nalready includes a documentation assistant, or if there is a certified tool on\nthe market that writes directly into that software, the sensible choice is to\nuse it. Checking contracts and hosting is a matter of days, not a project.",{"type":51,"tag":52,"props":638,"children":639},{},[640],{"type":56,"value":641},"Building makes sense when there are several specialties with their own formats,\na group with different processes in each clinic, in-house or older clinical\nsoftware, a need to link documentation to coding and billing, or data\nrequirements that off-the-shelf tools do not meet.",{"type":51,"tag":52,"props":643,"children":644},{},[645,647,653],{"type":56,"value":646},"If someone at the clinic has already built a prototype of the note template in\nChatGPT, Claude or Gemini, it is a good starting point and shortens the\ndiscovery work. What is missing (user accounts for each clinician, data in the\nright place, a connection to the clinical software, backups and tests) is\nexactly what ",{"type":51,"tag":355,"props":648,"children":650},{"href":649},"/en/blog/ai-prototype-to-production",[651],{"type":56,"value":652},"separates an AI-built prototype from a system in\nproduction",{"type":56,"value":564},{"type":51,"tag":64,"props":655,"children":657},{"id":656},"questions-to-answer-before-moving-forward",[658],{"type":56,"value":659},"Questions to answer before moving forward",{"type":51,"tag":98,"props":661,"children":662},{},[663,668,673,678,683],{"type":51,"tag":102,"props":664,"children":665},{},[666],{"type":56,"value":667},"How many hours a week do clinicians currently spend on records outside the\nconsultation?",{"type":51,"tag":102,"props":669,"children":670},{},[671],{"type":56,"value":672},"Which specialties account for most of that time?",{"type":51,"tag":102,"props":674,"children":675},{},[676],{"type":56,"value":677},"Does the clinical software have a documented way of receiving data?",{"type":51,"tag":102,"props":679,"children":680},{},[681],{"type":56,"value":682},"Who in the clinic makes decisions about intended purpose and data protection?",{"type":51,"tag":102,"props":684,"children":685},{},[686],{"type":56,"value":687},"Would patients agree to being recorded, or is dictation the more realistic\nstarting point?",{"type":51,"tag":52,"props":689,"children":690},{},[691,693,699],{"type":56,"value":692},"If the lights in your clinic or group of clinics also stay on after the last appointment, you can\n",{"type":51,"tag":355,"props":694,"children":696},{"href":695},"/en/contacto",[697],{"type":56,"value":698},"request a free diagnosis",{"type":56,"value":700},". We look at the specialties, the\nsoftware and the time being lost, with no commitment, and tell you whether there is a case for a pilot.",{"title":702,"searchDepth":703,"depth":703,"links":704},"",3,[705,707,708,709,710,711,712,713,720,721,722],{"id":66,"depth":706,"text":69},2,{"id":77,"depth":706,"text":80},{"id":93,"depth":706,"text":96},{"id":139,"depth":706,"text":142},{"id":196,"depth":706,"text":199},{"id":345,"depth":706,"text":348},{"id":410,"depth":706,"text":413},{"id":456,"depth":706,"text":459,"children":714},[715,716,717,718,719],{"id":463,"depth":703,"text":466},{"id":474,"depth":703,"text":477},{"id":485,"depth":703,"text":488},{"id":496,"depth":703,"text":499},{"id":507,"depth":703,"text":510},{"id":526,"depth":706,"text":529},{"id":628,"depth":706,"text":631},{"id":656,"depth":706,"text":659},"markdown","content:en:blog:ai-clinical-documentation-consultations.md","content","en/blog/ai-clinical-documentation-consultations.md","en/blog/ai-clinical-documentation-consultations","md",[730,738,747,755,763,771,778,785,794,801,808,815,823,830,837,845,851,857,864,871,878,885,891,899,905,912,919,926,934,942,949,956,962,969,976,983,989,997,1004,1011,1018,1025,1032,1040],{"_path":731,"title":732,"description":733,"date":13,"image":734,"tags":735},"/blog/custom-software-quote-what-it-should-include","What a Custom Software Quote Should Include: A Line-by-Line Example","The line items a custom software quote should break down, a line-by-line example, the costs left out and the warning signs to check before signing.","/images/blog/orcamento-software-medida.jpg",[736,737],"Costs & Decision","Custom Software",{"_path":739,"title":740,"description":741,"date":742,"image":743,"tags":744},"/blog/real-estate-crm-software-portugal-how-to-choose","Real Estate CRM Software in Portugal: How to Choose the Right One for Your Agency","Portals, listings, viewings, commissions and IMPIC obligations: what a real estate CRM has to handle in Portugal and when a custom-built one pays off.","2026-11-09","/images/blog/crm-imobiliario-portugal.jpg",[745,746,737],"Real Estate","CRM",{"_path":748,"title":749,"description":750,"date":751,"image":752,"tags":753},"/blog/is-your-company-data-ready-for-ai","Is Your Company Data Ready for AI? How to Tell Before You Invest","What each type of AI project asks of your data, an eight-question self-assessment, and why you do not need a data lake before your first AI project.","2026-10-29","/images/blog/dados-prontos-ia.jpg",[20,754,736,737],"Business Intelligence",{"_path":756,"title":757,"description":758,"date":759,"image":760,"tags":761},"/blog/ai-cash-flow-treasury-forecasting","Cash Flow Forecasting: Stop Running Treasury on Bank Statements and a Friday Spreadsheet","Consolidated multi-bank position, automatic reconciliation and a 13-week cash flow forecast. Where AI genuinely helps and where simple statistics are enough.","2026-10-24","/images/blog/previsao-tesouraria.jpg",[754,20,762,736],"Automation",{"_path":764,"title":765,"description":766,"date":767,"image":768,"tags":769},"/blog/fleet-rent-a-car-management-software-ai","Custom Rent-a-Car Software: Real Fleet Status, AI Inspections and Dynamic Pricing","Real availability, inspection photos compared by AI, fines passed to the renter on time and occupancy-based pricing: what a rent-a-car operation needs.","2026-10-14","/images/blog/frotas-rent-a-car.jpg",[770,737,20],"Logistics",{"_path":772,"title":773,"description":774,"date":775,"image":776,"tags":777},"/blog/ai-recruitment-hr-ai-act-high-risk","AI in Recruitment and HR: What to Automate and What the AI Act Treats as High Risk","What AI can safely do in HR, what the AI Act classifies as high risk in recruitment, and how to design systems that support decisions without making them.","2026-10-08","/images/blog/ia-recrutamento-rh.jpg",[20,21,762,737],{"_path":779,"title":780,"description":781,"date":782,"image":783,"tags":784},"/blog/field-service-management-software-technical-teams","Software for Field Technical Teams: From the Call to the Invoice Without Paper","Work orders, an offline app, parts in the van, contracts with SLAs and an invoice at close-out: what a system for field technicians really has to solve.","2026-10-03","/images/blog/equipas-tecnicas-terreno.jpg",[737,762,20],{"_path":786,"title":787,"description":788,"date":789,"image":790,"tags":791},"/blog/custom-erp-wholesale-distribution","Custom ERP for Wholesalers and Distributors: Where the Margin Goes","Customer pricing, volume rebates, WhatsApp orders and credit limits: where an off-the-shelf ERP fails a wholesaler, where AI helps and what custom costs.","2026-09-26","/images/blog/erp-distribuicao-grossista.jpg",[770,792,737,793],"ERP","B2B Sales",{"_path":795,"title":796,"description":797,"date":798,"image":799,"tags":800},"/blog/ai-document-processing-invoices-orders","Invoices, Purchase Orders and Delivery Notes in PDF: How AI Reads Them and Posts Them to the ERP Without Silent Errors","How AI reads supplier invoices, purchase orders and delivery notes from email, checks them against the ERP and leaves only exceptions to your team.","2026-09-19","/images/blog/ia-processamento-documentos.jpg",[762,20,792,736],{"_path":802,"title":803,"description":804,"date":805,"image":806,"tags":807},"/blog/modernise-legacy-software-without-stopping-operations","The Old System Nobody Wants to Touch: How to Modernise It Without Stopping Operations","Access, Visual Basic, Delphi or a 15-year-old ERP: how to replace old software one module at a time, migrate data in parallel and keep the business running.","2026-09-12","/images/blog/modernizar-software-legado.jpg",[737,792,736],{"_path":809,"title":810,"description":811,"date":812,"image":813,"tags":814},"/blog/ai-prototype-to-production","Your Team Built an AI Prototype. What It Takes to Get to Production","More and more teams build applications with ChatGPT, Codex or Claude Code. What changes when that software has to be secure, reliable and able to scale to production.","2026-09-05","/images/blog/ai-prototype-to-production.jpg",[737,20,21,736],{"_path":816,"title":817,"description":818,"date":819,"image":820,"tags":821},"/blog/integrate-ai-business-processes-digital-brain","How to Integrate AI into Business Processes Without Adding Another Isolated Tool","Learn how a Digital Brain connects documents, ERP, CRM and email to turn AI into real work, with security, control and measurable return.","2026-08-26","/images/blog/cerebro-digital.jpg",[20,822,762,736],"AI Agents",{"_path":824,"title":825,"description":826,"date":827,"image":828,"tags":829},"/blog/how-long-a-custom-software-project-takes","How Long a Custom Software or AI Project Actually Takes","Real timelines by project type, what happens inside each phase, and the four things on the client side that delay projects more than any technical decision.","2026-08-22","/images/blog/prazos-projeto-software-medida.jpg",[736,737,20,762],{"_path":831,"title":832,"description":833,"date":834,"image":835,"tags":836},"/blog/add-ai-to-existing-business-software","Adding AI to the Software Your Company Already Uses, Without Replacing It","How AI connects to the ERP, the CRM and the files you already have, what changes when a system has no ready-made connection, and what each scenario actually costs.","2026-08-16","/images/blog/integrar-ia-software-existente.jpg",[20,737,792,736],{"_path":838,"title":839,"description":840,"date":841,"image":842,"tags":843},"/blog/how-to-choose-an-ai-agent-partner","How to Choose Who Builds Your Company AI Agents","Seven criteria to separate those who deliver from those who give a good demo: code ownership, fixed scope, what happens when the AI is wrong, and where the data lives.","2026-08-09","/images/blog/agentes-ia-empresariais-suporte-b2b.jpg",[822,736,844],"B2B Portals",{"_path":846,"title":847,"description":848,"date":849,"image":842,"tags":850},"/blog/gdpr-ai-act-before-ai-agents-production","GDPR and the AI Act: What to Check Before Putting an AI Agent in Production","What the GDPR and the AI Act actually require from a company using AI agents, the five points that cover most cases, and the mistake that costs the most.","2026-08-02",[21,822],{"_path":852,"title":853,"description":854,"date":855,"image":820,"tags":856},"/blog/how-much-ai-costs-company-portugal","How Much Does It Cost to Implement AI in a Company in Portugal in 2026","Real price ranges for AI agents, internal platforms and custom software in Portugal, what drives the figure up, and the running cost that never appears in proposals.","2026-07-26",[736,20,822],{"_path":858,"title":859,"description":860,"date":861,"image":862,"tags":863},"/blog/custom-erp-crm-vs-primavera-phc-sap","Custom ERP and CRM or Primavera, PHC, ARTSOFT and SAP: How to Decide","Primavera, PHC, ARTSOFT and SAP fit most companies. The three signs the product stopped fitting, and why replacing everything rarely pays off.","2026-07-19","/images/blog/agribusiness-erp.jpg",[792,746,736],{"_path":865,"title":866,"description":867,"date":868,"image":869,"tags":870},"/blog/custom-ai-agents-vs-generic-tools","Custom AI Agents or Generic Tools: When Building Is Worth It","ChatGPT and Copilot solve individual productivity. When the process needs company data and has to act in your systems, the maths changes. Criteria for deciding.","2026-07-12","/images/blog/automacao-vendas-ia.jpg",[822,20,736],{"_path":872,"title":873,"description":874,"date":875,"image":876,"tags":877},"/blog/custom-real-estate-crm-high-ticket-deals","Custom Real Estate CRM: The Key to Closing High-Ticket Deals","Discover why generic CRMs fail in the luxury market and how a custom-built real estate CRM with AI integration accelerates closing high-ticket deals.","2026-06-08","/images/blog/crm-real-estate.jpg",[746,745,20],{"_path":879,"title":880,"description":881,"date":882,"image":883,"tags":884},"/blog/legal-erp-integrated-crm-lead-capture","From Followers to Clients: How a Legal ERP with Integrated CRM Transforms Lead Capture","What changes when client acquisition and case management live in the same system, and why most of the enquiries generated on social channels are lost before they ever reach a fee proposal.","2026-05-21","/images/blog/erp-juridico-crm.jpg",[737,746,762],{"_path":886,"title":887,"description":888,"date":889,"image":869,"tags":890},"/blog/ai-sales-automation","How AI Automation Shortens Sales Cycles and Boosts Conversion Rates","Discover how AI sales automation eliminates manual administrative work, accelerates high-value B2B deals, and transforms your CRM.","2026-05-14",[20,762,793],{"_path":892,"title":893,"description":894,"date":895,"image":896,"tags":897},"/blog/e-commerce-checkout-optimization","Why Your Online Store is Losing Sales at Checkout (and How to Fix It)","Discover why an outdated e-commerce platform turns customers away at checkout and how modern payment integrations immediately increase your conversion rate.","2026-05-12","/images/blog/otimizacao-checkout-e-commerce.jpg",[898,737],"Retail & E-commerce",{"_path":900,"title":901,"description":902,"date":903,"image":820,"tags":904},"/blog/digital-brain-institutional-memory-smes","What if Your Company Had a Digital Brain? The Revolution of Institutional Memory in SMEs","Discover how a Digital Brain powered by Private AI can centralize company knowledge, eliminate the Bus Factor, and scale your operations securely.","2026-05-08",[20,762],{"_path":906,"title":907,"description":908,"date":909,"image":910,"tags":911},"/blog/ai-chatbot-qualifies-leads-24h","Multiply Your Sales: How an AI Chatbot Qualifies Leads 24 Hours a Day","Discover how a custom Artificial Intelligence chatbot can interact, qualify high-value potential clients, and schedule meetings while your team sleeps.","2026-05-02","/images/blog/chatbot-ia-qualifica-leads.jpg",[20,793,762],{"_path":913,"title":914,"description":915,"date":916,"image":917,"tags":918},"/blog/custom-wms-ai-inventory-management","Zero-Touch Inventory Management: How Custom WMS & AI Reduce Stockouts","Discover how a custom Warehouse Management System (WMS) powered by AI reduces stockouts and automates replenishments in retail and distribution operations.","2026-04-24","/images/blog/wms-medida-ia-gestao-inventario.jpg",[898,20,770],{"_path":920,"title":921,"description":922,"date":923,"image":924,"tags":925},"/blog/custom-erp-consulting-firms-project-management","Ending Consultancy Chaos: 10 SaaS Tools vs 1 Custom ERP","Discover why dozens of SaaS tools destroy consultancy profit margins and how a custom ERP safely restores holistic financial control.","2026-04-20","/images/blog/finance-automation.jpg",[737,792],{"_path":927,"title":928,"description":929,"date":930,"image":931,"tags":932},"/blog/custom-eqms-manufacturing-quality-control","Paperless Quality Control: The Value of Custom e-QMS in Manufacturing","Discover how a custom e-QMS replaces manual factory floor processes and accelerates audits in manufacturing.","2026-04-17","/images/blog/eqms-sistema-controlo-qualidade-industria.jpg",[933,737,20],"Manufacturing",{"_path":935,"title":936,"description":937,"date":938,"image":939,"tags":940},"/blog/law-firm-management-software-ai","Law Firm Management Software: How AI Solves the Problem of Slow Contract Analysis","Discover how a custom ERP and management software for law firms integrates AI to analyze contracts and scale billable hours.","2026-04-15","/images/blog/software-gestao-advogados-ia.jpg",[20,737,941],"Legal Sector",{"_path":943,"title":944,"description":945,"date":946,"image":947,"tags":948},"/blog/custom-crm-vs-salesforce","What Is a Custom CRM and Why Salesforce Might Be Holding Your Business Back","The signs a generic CRM is no longer enough, what changes with a custom system, and how licence costs compare against ownership over a three to five year horizon.","2026-04-10","/images/blog/crm-medida-vs-salesforce.jpg",[746,793,737,736],{"_path":950,"title":951,"description":952,"date":953,"image":954,"tags":955},"/blog/custom-vendor-portals-procurement","Custom Vendor Portals: The Secret Strategy for a Resilient Supply Chain","Discover how bespoke Vendor Portals guarantee efficiency, rock-solid compliance, and total management control across complex procurement operations.","2026-04-09","/images/blog/portais-fornecedores-medida-procurement.jpg",[844,770],{"_path":957,"title":958,"description":959,"date":960,"image":842,"tags":961},"/blog/enterprise-ai-agents-b2b-support","Enterprise AI Agents: Reimagining Complex B2B Customer Support","How AI Agents integrated into your ERP transform B2B support, resolving complex queries without human intervention and scaling operations.","2026-04-08",[20,762],{"_path":963,"title":964,"description":965,"date":966,"image":967,"tags":968},"/blog/custom-erp-enterprise-groups-holdings","Multi-Company Management Without Chaos: The Strategic Advantage of a Custom ERP","Discover how Enterprise Groups and Holdings are abandoning rigid ERPs in favor of custom software to centralize management and scale profitably.","2026-04-06","/images/blog/erp-medida-grupos-empresariais-holdings.jpg",[737,792],{"_path":970,"title":971,"description":972,"date":973,"image":974,"tags":975},"/blog/traditional-mes-ai-smart-system","How to Transform Your Traditional MES into an AI-Driven Smart System","Passive MES systems bottleneck factory efficiency. Learn how to integrate Artificial Intelligence for predictive maintenance and near zero downtime.","2026-04-01","/images/blog/tradicional-mes-ai-smart-system.jpg",[933,20,737],{"_path":977,"title":978,"description":979,"date":980,"image":981,"tags":982},"/blog/custom-erp-vs-saas-logistics","Custom ERP vs SaaS: What Works Best for Logistics Operations?","Generic SaaS logistics platforms create bottlenecks. Learn why a custom ERP transforms distribution scalability and lowers long-term operational costs.","2026-03-23","/images/blog/erp-logistics.jpg",[770,792,737,736],{"_path":984,"title":985,"description":986,"date":987,"image":924,"tags":988},"/blog/backoffice-financial-automation","Backoffice Automation in Financial Services: Security and Efficiency","Manual approvals and document handling slow responses and create compliance risks. Discover how financial backoffice automation transforms operations.","2026-03-16",[762,21],{"_path":990,"title":991,"description":992,"date":993,"image":994,"tags":995},"/blog/end-of-excel-construction","The End of Excel in Construction: Centralizing Project Management","Budgets and planning scattered across spreadsheets cause massive financial overruns. Learn how a custom ERP safely centralizes construction management.","2026-03-09","/images/blog/excel-construction.jpg",[996,792,737],"Construction",{"_path":998,"title":999,"description":1000,"date":1001,"image":1002,"tags":1003},"/blog/predictive-maintenance-manufacturing","Predictive Maintenance in Manufacturing: Using AI to Prevent Downtime","Unexpected assembly line failures destroy margins. Discover how predictive maintenance software uses AI to prevent breakdowns before they occur.","2026-03-02","/images/blog/predictive-maintenance.jpg",[933,20],{"_path":1005,"title":1006,"description":1007,"date":1008,"image":1009,"tags":1010},"/blog/ai-crm-real-estate","How AI is Transforming Lead Qualification in Real Estate CRMs","Real estate teams waste hours on unqualified leads. Discover how a custom CRM with AI agents eliminates manual prospecting and boosts conversion.","2026-02-23","/images/blog/ai-real-estate.jpg",[745,746,20,762],{"_path":1012,"title":1013,"description":1014,"date":1015,"image":1016,"tags":1017},"/blog/b2b-custom-extranet-portals","B2B Extranets: Retaining Enterprise Clients with Custom Portals","PDF and email ordering generate B2B friction. Discover how bespoke Extranet Portals streamline corporate sales and secure long-term client relationships.","2026-02-16","/images/blog/b2b-extranet.jpg",[844,933,762],{"_path":1019,"title":1020,"description":1021,"date":1022,"image":1023,"tags":1024},"/blog/custom-bi-dashboards-retail","Custom Business Intelligence Dashboards for Multi-Store Retail","Data silos between e-commerce, retail, and warehouses destroy margins. Learn how custom BI Dashboards centralize operations and drive decisions.","2026-02-09","/images/blog/retail-dashboard.jpg",[898,754,737],{"_path":1026,"title":1027,"description":1028,"date":1029,"image":862,"tags":1030},"/blog/agribusiness-custom-erp","Scaling Agribusiness: Why You Should Avoid Generic Management Software","Agricultural seasonality and traceability collide with traditional ERPs. Discover how custom software fully digitalizes agribusiness operations.","2026-02-02",[1031,792,737,933],"Agribusiness",{"_path":1033,"title":1034,"description":1035,"date":1036,"image":1037,"tags":1038},"/blog/staff-management-hospitality","Staff Management in Hospitality: Ending Roster Disorganization","Rosters in Excel and WhatsApp groups cost you shift coverage, maintenance traceability and GDPR compliance. What changes with a custom internal portal.","2026-01-26","/images/blog/hospitality-staff.jpg",[1039,844,762],"Hospitality",{"_path":1041,"title":1042,"description":1043,"date":1044,"image":1045,"tags":1046},"/blog/ai-clinical-scheduling","Clinical Scheduling Automation: Reducing No-Shows with AI Agents","Uncommunicated patient no-shows destroy daily clinic profitability. Learn how custom clinic scheduling software powered by AI actively eliminates friction.","2026-01-19","/images/blog/ai-clinic.jpg",[19,20,762],1794655861309]