TCM clinic appointments and health records: revisit rate up by a third
Client Profile
Pain Points
Notebook bookings
Bookings in a notebook are easy to miss and misplace.
Slow constitution assessment
Constitution questionnaires and records are all handwritten.
Missing revisit reminders
No systematic treatment-cycle or revisit reminders.
Live Demo
How We Built It
AI booking
Online bookings auto-schedule with confirmations and reminders.
Health-record generation
Auto-generate constitution questionnaires and records to aid diagnosis.
Cycle reminders
Auto revisit and medication reminders by treatment cycle.
Not betting on one AI — combining the right few
For a real business scenario, we don't lock in a single technical path up front. We evaluate candidate paths on the same benchmark, then design a hybrid so each path does what it's best at.
General LLM API
Public-cloud models such as GPT-4o / Qwen / DeepSeek
- ✓Out-of-the-box, minimal integration cost, cheap to start
- ✕Limited generalization to vertical domains, unstable field-level accuracy, separate compliance design
Industry fine-tuned model
Domain fine-tuning of open-source models on industry data
- ✓Grasps industry semantics, much higher accuracy, private deployment
- ✕Needs labeled data plus ongoing training and upkeep
RAG + rule engine
Retrieval-augmented knowledge plus business rule checks
- ✓Highly targeted, explainable, best latency and cost
- ✕Requires continuous data-loop investment
Fusion, not selection
What we deliver is not a single model but a fused pipeline of primary path + semantic correction + graceful fallback: routine cases are handled by the industry model in seconds; low-confidence fields are re-understood by an LLM; on service anomalies the system degrades to a general API and flags manual review — achieving accuracy, cost, latency and controllability at once.
An explainable, degradable, evolvable AI pipeline
We treat AI engineering as a pipeline, not a black box: every step has clear responsibilities, inputs/outputs and fallbacks. The five-step pipeline plus four-layer architecture below is the technical skeleton.
Ingestion & access layer
Multi-channel access with unified auth, idempotency and masking
AI inference layer
Multi-path inference plus a confidence router switching by features
Business orchestration layer
Connecting results to real business flows with rule checks and closure
Data loop layer
Every online error flows back; models iterate monthly
Tech Stack
Delivery Process
Flow mapping
Mapped booking, consultation and revisit flows.
Booking system
Built booking and scheduling.
Record system
Built constitution health records.
Trial
Trial in one branch.
Rollout & iteration
Covered both branches and optimized.
Before vs After
“Health records generate themselves and revisit reminders go out automatically — patient stickiness is clearly stronger.”
Where It Fits
Related Cases
AI Appointment & Record Management
Deployed an AI appointment and record-management assistant for a dental clinic chain to improve patient experience and operations.
GuangzhouAI Consultation & Post-op Follow-up
Deployed an AI consultation and post-op follow-up assistant to lift conversion and client satisfaction.
DongguanAI Report Interpretation & Follow-up
Deployed a report-interpretation and follow-up assistant to make health checks more thoughtful.