Frequently asked questions

Micromeet — AI for governed healthcare — is a healthcare AI company backed by Microware Group (HKEX: 1985), building AI infrastructure for clinics, hospitals and screening providers across Indonesia, Singapore and Hong Kong. The platform covers MCU CoPilot (medical check-up report automation), AI Scribe / Voice-to-EMR (multilingual clinical documentation), AI Front Desk (instant patient first response), Care Loop (post-visit follow-up), Claim Readiness (coding and claims) and AI Care Command Center (the governed institution runtime that ties them together).

Governed healthcare AI is AI that operates inside an institution's clinical governance instead of around it: every output is drafted by AI, reviewed and approved by a clinician, and recorded with an audit trail of who reviewed what and when. It is the difference between an AI demo and an AI system an institution can actually be accountable for. Micromeet builds its entire platform on this principle.

It means AI drafts the work — reports, clinical notes, follow-up messages, coding suggestions — and a licensed clinician reviews, edits and approves anything that carries medical responsibility before it is released. Micromeet's AI never diagnoses autonomously and never issues a final report; the reviewing doctor retains full clinical and legal responsibility, supported by a complete audit trail.

Micromeet is backed by Microware Group, a Hong Kong-listed technology group (HKEX stock code: 1985). Micromeet operates across Hong Kong, Singapore and Indonesia, with clinical and product teams working directly with practising doctors in each market.

Micromeet's primary markets are Indonesia, Singapore and Hong Kong, expanding across Southeast Asia and East Asia. The platform is built multilingual and multi-standard from day one — local clinical terminology, local coding standards and local data-residency requirements are treated as core product features, not afterthoughts.

MCU CoPilot is an AI agent that automates medical check-up (MCU) report drafting. It reads the structured examination data an institution already produces — laboratory results, vitals, physical exam findings, specialist conclusions — and generates a structured draft report with conclusions, recommendations and fitness-for-work wording for a doctor to review, edit and sign. It works standalone (upload files in a browser, no IT project required) or integrated with an existing HIS, LIS or EMR via API.

AI Scribe, also called Voice-to-EMR or V2N, turns the doctor–patient conversation into structured clinical documentation. It supports 50+ languages including Indonesian, English, Cantonese, Mandarin, Malay, Thai and Vietnamese, and produces structured notes ready for the EMR. On Cantonese medical speech it reaches 95%+ accuracy on our internal medical dataset. The doctor reviews and confirms every note before it enters the record.

AI Front Desk answers patient inquiries the moment they arrive — bookings, questions, follow-ups — across channels and languages, 24 hours a day. It gathers the basics, checks availability and moves the patient toward a booking or the right next step, while anything that carries medical or operational weight is confirmed by staff. Fast first response is one of the strongest conversion levers in healthcare operations, and AI Front Desk makes it systematic instead of dependent on who happens to be free.

Care Loop keeps the patient relationship alive after the visit or screening: report explanation, abnormal-finding follow-up, recheck reminders and longitudinal health engagement. It carries the same patient context forward from screening or consultation, so follow-up is specific rather than generic — and every clinically meaningful message is doctor-supervised.

Claim Readiness helps institutions get claims right at the source. It supports ICD-10 and ICD-11 coding from clinical documentation and works across multi-country claim environments, including Indonesia's BPJS / INA-CBGs workflow. Cleaner coding at the encounter means better-supported files before submission and clearer exception handling downstream.

AI Care Command Center is the governed runtime underneath Micromeet's products: it turns AI and human work into visible, accountable institution queues — every task has an owner, a status, an SLA and an audit trail, with writeback to institutional systems. It is what makes the difference between AI features bolted onto a clinic and an AI layer the institution can measure, manage and trust.

Yes. Micromeet publishes the Indonesia MCU Healthcare AI Agent Readiness Benchmark — an openly documented evaluation method with published pass gates, a 24-criterion weighted rubric and staged test lanes, so clinical, quality and procurement teams can inspect how readiness is measured instead of trusting a demo. The full report is at micromeet.ai/benchmark/index.html.

It is a method-first benchmark that tests 12 foundation models under one fixed MCU agent workflow on 30 anonymized real Indonesian medical check-up cases, measuring whether output is structured, complete, stable and traceable enough to enter a doctor-supervised review workflow. Clinical review is led by Dr. dr. Alfian Wika Cahyono, M.Biomed. It deliberately publishes its limits as well as its results — a machine-side pass is not a clinical-correctness verdict.

Yes — that is the point. The benchmark includes an eight-point readiness checklist (structured-output proof, repeat stability, evidence traceability, safety boundaries, localization fit, review burden, independent review, change control) that an institution can apply to any AI documentation vendor, including Micromeet. If a vendor can only show a polished demo, the checklist tells you what evidence to ask for before committing to a pilot.

Yes. Micromeet is independently certified to ISO/IEC 27001:2022 (scope: AI application platform development). Data is encrypted in transit (TLS 1.3 where supported) and at rest, processed only to deliver the service under a Data Processing Agreement (DPA). Micromeet never sells your data and does not use identifiable data to train AI models — product improvement uses de-identified data only, where the required consent and agreements are in place.

Micromeet's controls are aligned with Indonesia's UU PDP, Singapore's PDPA, Hong Kong's PDPO and HIPAA security standards. Full detail — data ownership, residency, retention, clinical governance, the security model and subprocessors — is published at trust.micromeet.ai.

No. Micromeet's agents are documentation and workflow systems, not Clinical Decision Support Systems (CDSS) and not diagnostic engines. They do not interpret raw clinical media such as ECG waveforms or radiological images — specialist findings are used as reported by the responsible clinician. Every output requires doctor review, editing and authorisation before release.

Data is stored in Singapore by default, with in-country storage supported for Indonesia and Hong Kong. Retention and deletion are governed by your agreement: data is deleted on request and at contract end.

Standalone mode can start immediately: MCU CoPilot's standalone deployment needs only a browser and an internet connection — staff upload examination files and doctors review the drafts, with no HIS/LIS integration project. Integrated mode connects to your existing HIS, LIS or EMR via API or data connector and follows your IT change process. Institutions can start standalone and migrate to integrated mode without retraining staff, because the doctor review workflow is identical in both.

Yes. Micromeet works with the systems an institution already runs — HIS, LIS and EMR — via API or structured data connectors, with results written back so the institution's system of record stays authoritative. Where no integration is possible yet, standalone mode covers the same clinical workflow through file upload.

Micromeet supports 50+ languages across its voice and patient-facing products, including Indonesian, English, Cantonese, Mandarin, Malay, Thai, Vietnamese, Filipino, Tamil, Hindi, Japanese and Korean. Clinical output follows the institution's working language — for example, Bahasa Indonesia MCU reports with local clinical terminology preserved.

Start with a conversation: email enquiry@micromeet.ai or use the contact form at micromeet.ai, and tell us your institution type and the workflow you want to improve first. Pricing depends on deployment mode, volume and integration scope, so we scope it with you — typically beginning with a doctor-supervised pilot on your own cases rather than a long contract.