Patient portal inbox triage that stops following clinicians home.
Classify, summarize, route, and draft grounded replies for routine portal messages while escalating symptoms, medication risk, and uncertainty.
Nothing is finalized until a human approves it.
Where the time and money actually go.
Clinicians and staff face growing asynchronous message volume, duplicate threads, incomplete context, and after-hours burden; simple administrative requests compete with clinical risk.
Physicians, nurses, medical assistants, portal support teams
Trigger to act: Inbox turnaround is missing targets, clinicians report message burnout, or a system wants centralized team-based inbox management.
The result you can model before you sign.
Illustrative only: 8,000 messages/month × 1.5 minutes removed × $45 blended loaded hourly cost ÷ 60 = $9,000 monthly capacity. Clinical safety value is measured separately through escalation recall.
The outcome, plainly: Classify, summarize, route, and draft grounded replies for routine portal messages while escalating symptoms, medication risk, and uncertainty.
Inputs in. A cited, review-ready result out. Your expert decides.
A Permission-aware RAG copilot. Every material fact is grounded in an allowed source and returned with its identifier, with no invented data.
Claude Sonnet 4.6 or GPT-5.6 Terra for complex grounded work; select by task-level evaluation; Gemini 2.5 Flash, GPT-5.4 mini or Claude Haiku 4.5 for high-volume routing and drafting. PostgreSQL + pgvector or managed vector store; Policy rules and evaluator service.
- Patient message
- recent encounter context
- medication list
- approved response protocols
- appointment and refill policies
- routing taxonomy
AI-Native, not autonomous. Judgment stays with your people.
The machine does the work; the human’s role narrows to the one thing that matters, judgment. That constraint is what makes it safe to deploy.
A licensed clinician reviews all clinical drafts; urgent symptom patterns route immediately under client-approved protocols; the model never independently diagnoses.
A scorecard, not a demo. We baseline what breaks in production.
Every deployment ships with an evaluation suite. These are the numbers we baseline before launch and monitor after.
The category is crowded. Most of it isn’t built for your workflow.
Fixed-scope, tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in from day one. A price you own, not a subscription you rent.
It plugs into the stack you already run.
No rip-and-replace. Access is scoped to the minimum data necessary, isolated per tenant, and fully logged.
Transparent by design. The build price buys the workflow and the proof.
A fixed implementation fee plus a monthly bill that scales with volume and governance. No hidden seats.
- ✓ One process / scope
- ✓ Live workflow on your data
- ✓ Baseline evaluation suite
- ✓ Measured vs. current process
- ✓ Full scope & integration
- ✓ Human-review UI & audit trail
- ✓ Write-back to your systems
- ✓ Production evals & monitoring
- ✓ Multi-facility rollout
- ✓ Advanced security & compliance
- ✓ Custom control & escalation
- ✓ Dedicated evaluation program
10,000–35,000 grounded questions/month plus indexing and vector search.
Planning assumptions, not vendor quotations. Your EHR portal inbox and other platform licenses are separate and owned by you. Figures confirmed during scoping.
“His vast knowledge of technologies and a natural problem-solving mindset consistently lead us through complex challenges with clarity and confidence.”
Questions serious buyers ask.
Does the AI act on its own?
No. A licensed clinician reviews all clinical drafts; urgent symptom patterns route immediately under client-approved protocols; the model never independently diagnoses. The system drafts and recommends; a human approves every consequential action. Explicitly excluded: No unreviewed clinical response; no emergency diagnosis; no medication changes; no use of context outside user permissions; no training on PHI without contractually approved controls..
How do you stop it inventing facts?
Every material claim is grounded in an allowed source record and returned with its source identifier. The system separates observed facts, model inference, and missing information, and routes to a human whenever confidence is low, evidence conflicts, or an adverse outcome is possible.
What does it cost to run each month?
A usage bill of roughly $500–4,200/month (10,000–35,000 grounded questions/month plus indexing and vector search), plus a $2,800/month managed retainer for evaluation, monitoring and maintenance. Your existing platform licenses are separate and already yours. Exact figures are confirmed during scoping.
Do we need a ChatGPT or Claude subscription?
No consumer ChatGPT or Claude subscription is required for the production workflow. The client needs an approved API/cloud billing account. Workspace seats are optional for internal prototyping and administrator access.
How is this different from Epic in-basket tools?
Tools like Epic in-basket tools, Oracle Health workflows, Memora Health are broad platforms you adapt to. This is a fixed-scope implementation tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in, and a transparent price instead of a seat subscription.
How long until it is live, and how do we prove it works?
This is a specialist opportunity. We baseline “Time-to-first-response” first, then measure against that baseline. You see the scorecard before expanding scope: the evaluation suite ships with the system, not as an afterthought.
Bring your real numbers. Leave with a fixed-scope plan.
A 30-minute engineering-led working session, no slideware. You leave with a sized opportunity estimate, a fixed-scope pilot plan, and the integration & human-review path mapped.
VP of Growth at ViitorCloud · senior delivery owner confirmed before paid work