Mobile-first, on your own phone
Built for an entry-level Android handset held in one hand, not a desktop in a consulting room. No app store download required, and no new hardware for the practice.
Any smartphone
The product
Better context, not more admin.
From the health profile a patient builds on their own phone to the coded brief a clinician reads before the consultation, here is how Doogie works. For the safety controls, evidence and data protection behind it, see Safety & Trust.
The problem
Clinicians meet patients without the story.
Take South Africa as one example among many: a person's health story is spread across a public clinic, a private GP, a pharmacy and a hospital that never shared a record, and most of it was never written down at all. In countries with mature health records it sits inside systems built for episodes rather than prevention. Either way the consultation starts cold, and the family-health and lifestyle context that makes prevention possible is the first thing the clock takes away.
15,5 %
Of South Africans covered by a medical scheme. The rest depend on the public sector, where records rarely follow the patient.
≤5 min
A primary-care visit in countries home to about half the world's population.
10 M
Projected global shortfall of health workers by 2030, concentrated in low- and lower-middle-income countries.
4.5 bn
People worldwide not fully covered by essential health services.
Sources: Statistics South Africa, General Household Survey 2024; WHO (2023); Irving et al., BMJ Open (2017). Figures shown for South Africa as a worked example; the same fragmentation appears in most health systems.
How Doogie works
A health profile the patient owns, a brief the clinician can trust.
Doogie handles the part that eats the clock, and it does the job thoroughly every time, so the clinician arrives already informed and can spend the consultation on judgement and care. Ten stages, start to finish.
01
Patient profile
Set up once, reused every visit
The patient creates a consent-aware profile scoped to a practice: who they are, which practice can see their history, and what they've agreed to share. Nothing is collected before this is in place.
Patient profile
PracticeRiverside Family Practice
ConsentGranted, can be withdrawn
02
Conversation
The patient tells their story
Doogie talks with the patient in plain language on the phone they already own, in their own language, before the appointment. It covers the current concern, medicines, lifestyle and family-health history that usually never reaches a record.
Guided conversation
What brings you in today?
I've had a cough for 3 weeks.
03
Adaptive questioning
Each question depends on the last answer
Doogie is not a fixed form. A reported symptom opens a specific follow-up path; a "no" closes it and moves on. The patient never sees a question that a thorough clinician wouldn't have asked next.
Branching logic
If cough persists 3+ weeksAsks about fever, weight loss, night sweats
If none reportedMoves on to medication history
04
Structured extraction
The conversation becomes structured fields
Symptoms, duration, relevant positives and negatives, medication and family history are pulled out of the free-text conversation into named fields — organised against recognised clinical guidance, never diagnosed.
Extracted fields
SymptomCough, 3 weeks
Relevant negativesNo fever, no weight loss
05
Clinical terminology
Plain words become coded terms
What the patient said in their own words is mapped to SNOMED CT via the terminology services — codes are looked up, never generated by a model — so the record holds clean structured data instead of free text to retype.
Terminology mapping
“cough for 3 weeks”
49727002 · Cough
06
Safety layer
A deterministic guard, not a prompt
Every reply passes through rule-based code before a patient sees it: no medication or dose advice, and a deterministic red-flag screen ahead of any model call. See Safety & Trust for exactly what this does and doesn't cover today.
Deterministic checks
No medication or dose advice
Red-flag screen: checked, clear
07
Clinician brief
A concise, clinician-ready draft
The practice receives what the patient reported, what has changed since last time, and what to look at first — coded in SNOMED CT, with every line traceable back to what the patient actually said.
Consultation brief
M. James, 41Awaiting review
- Presenting complaint
- Cough, 3 weeks
08
Clinician review
The clinician decides, every time
A brief is never final until a clinician accepts it. They can accept as-is, edit any field, or discard it entirely — Doogie does not close the encounter on its own.
Review actions
Accept
Edit
Discard
09
Patient timeline
What's changed since last time
Accepted briefs build a timeline the clinician can see at a glance, so a follow-up starts with what's new rather than re-asking everything from scratch.
Visit history
MarVisit 1
JunVisit 2
TodayCurrent
10
System integration
Lands where the clinician already works
An accepted brief exports as FHIR R4 resources, so it can slot into the practice management and health record systems clinics already run — a clear path, not a promise of every integration on day one.
Structured export
Brief
FHIR R4
Practice system
Built for the market
Designed for how care is actually delivered.
Doogie is built for intermittent connectivity, low-end phones, many languages, and records that never followed the patient — because that is what a consultation actually looks like in most of the markets we serve, not an edge case to handle later.
Low bandwidth by design
Text-first, small payloads, and a conversation that survives a dropped connection and picks up where it stopped. Data cost is treated as a clinical access issue, because it is one.
Works on a weak signalDesigned to meet patients on WhatsApp
Doogie is built toward the channel patients already use every day, so the practice is not asking them to learn something new. Today the guided history runs as a simple web chat on any phone; WhatsApp delivery is in progress.
Web chat today, WhatsApp nextMultilingual by default
A patient explains their health best in their own language. Doogie converses in the patient's language and hands the practice a brief in the language the clinician works in.
Patient's own wordsPublic and private, side by side
Most people move between a public clinic and private care over a lifetime. The health profile follows the patient across both, so context is not lost every time the setting changes.
Mixed systemsTrust and consent led
The patient is told plainly what is collected, who will see it and why, in language they can act on. Consent is granted per practice and can be withdrawn, because here trust is the whole sale.
Consent by designSafety, the spine of everything
Doogie collects and structures. A clinician always decides.
What Doogie can and can't do, the deterministic controls it runs on, the evidence framework, and how patient data is protected — all live in full on one page.