An embeddable AI assistant for life-sciences teams. It answers patient and caregiver questions about conditions, treatment, access and affordability, and every answer is composed from graded sources and cited.

Is it for medical information or patient support?

Both, on one platform. For medical information, it gives consistent, cited answers to unbranded disease-education questions at any hour. For patient support programs, it answers access and affordability questions between calls, and defers case questions — a prior-authorization status, a shipment — to the channel that can help.

How does it avoid making things up?

Retrieval comes first: an answer is built from passages retrieved from the corpus, and it cites its sources. The guardrails are written into how every answer is generated, and every answer is then checked for citations, directive and diagnostic language and promotional superlatives, with the result recorded. Where retrieval finds nothing usable, the assistant says so rather than filling the gap.

Can we use our own approved content?

Yes. A deployment can be scoped to a defined portfolio or to its own private content, and that scope is enforced during retrieval rather than filtered afterwards.

With one script tag on an existing page, or inside an iframe where a strict content-security policy requires it. Each deployment gets its own public key, bound to the origins you nominate.

Source-grounded AI for life sciences

Answers your medical and patient teams can stand behind.

OpenSupport is an AI assistant for medical information and patient support programs. Every answer is built from graded sources — including your own approved content — and cited, inside guardrails no deployment's configuration can switch off, with adverse-event capture and the audit trail a regulated team needs.

Request a demo Try it live

Health information, not medical advice. No diagnosis. No prescribing. Not for emergencies.

16,500+: sources indexed
28,000+: retrievable passages
20+: therapeutic areas
24/7: patient access

OpenSupport Source-grounded patient support

My treatment was prescribed, but I am worried about the cost. What can I do?

Here are the next places to look

Depending on the medicine and your insurance, support may include manufacturer assistance, co-pay programs, or independent foundations.¹

If coverage was denied, you can also request a formal appeal — plans must offer an internal review and an independent external one.²

Sources

1 Patient assistance & co-pay programs
2 Appealing a health plan decision

Illustrative example. Try the live assistant →

Designed around what medical information and patient-services teams need

Citationsbehind every answer
AE capturefor review workflows
Multi-tenantenterprise isolation
Analyticsquestions, gaps, outcomes

Two solutions, one platform

Where teams put it to work.

Medical information

Consistent, cited answers at any hour

Unbranded disease-education questions from patients and caregivers, answered from graded sources and your own approved content — with possible adverse events and product complaints flagged for review.

Medical information → Patient support programs

Support on your own properties, between calls

Condition, treatment, access and affordability questions answered on your brand sites and hub portals — with case questions deferred to the channels that hold that information.

Patient support programs →

Why OpenSupport

Patient support shouldn't stop when the call centre closes.

Patients don't experience treatment as separate channels. Their questions move from symptoms to therapy, insurance, cost, appointments and next steps. OpenSupport creates one around-the-clock, source-grounded support layer across that journey.

Understand

Make complex health information easier to act on

Explain conditions, treatment concepts, administration, side effects, and the questions worth raising with a healthcare professional — in plain language.

Access

Move from “what is this?” to “how do I get it?”

Help people navigate coverage, affordability, manufacturer assistance, independent foundations, denials, appeals, and access pathways.

Learn

See where the patient journey is breaking

Surface unanswered questions, low-confidence retrievals, content gaps, recurring access barriers, and emerging support needs by therapeutic area.

Where patient support runs out, and what fills the gap

One experience across the patient journey

From first question to next best action.

Understand the condition

Plain-language explanations of disease, progression, terminology, and what to ask next.
Understand treatment

How therapies work, how they are given, what to monitor, and where the source information lives.
Navigate access & cost

Coverage, co-pay support, patient assistance, foundations, denials, and appeals.
Prepare for action

Questions for appointments, specialist resources, trial discovery, and appropriate next steps.

Built for regulated enterprise deployment

The AI experience patients want. The controls your teams require.

OpenSupport is designed as an engagement layer, not an unconstrained chatbot. Retrieval, sourcing, deferral, monitoring and tenant controls are built into the operating model.

Source-grounded responses

Answers are tied to retrievable evidence rather than unsupported free-form generation.

Adverse-event capture

Potential AE mentions are flagged and routed into pharmacovigilance review workflows.

Deferral, not approximation

Questions it cannot answer are deferred, not approximated — and, where enabled, captured as redacted topics in a human-response queue for source-grounded follow-up.

Training-gap detection

No-result and low-rated questions reveal where content or retrieval needs improvement.

Conversation analytics

Understand what patients ask, where they struggle, and which support topics recur.

Multi-tenant isolation

Separate environments, API keys, webhooks, and feature flags per deployment.

Auditability

Operational logs support review of system activity, usage, and deployment behaviour.

Modular deployment

Ship as a patient experience, a branded support layer, a portal capability, or an integrated service.

Evidence before eloquence

A curated knowledge base built to answer with receipts.

91% of retrievable passages come from authoritative, peer-reviewed and institutional sources. Manufacturer-published material is labelled as commercial wherever it is cited.

16,500+

sources indexed across 20+ therapeutic areas

28,000+ passages are retrievable today. The corpus is refreshed continuously, and stale content is archived rather than served.

Source mix, measured

Authoritative 35.2%
Peer-reviewed 31.6%
Institutional 24.6%
Government 7.0%
Commercial 1.3%
Community 0.4%

Share of 28,000+ retrievable passages as of October 2026. 598 stale, archived or unindexed passages are excluded — they cannot be retrieved, so they are not counted.

Designed with boundaries

Trust is not a disclaimer. It is a product requirement.

Every answer shows its sources

People see the evidence behind an answer instead of being asked to trust an opaque response.

No diagnosis, no prescribing

OpenSupport provides health information and directs clinical decisions back to healthcare professionals.

Privacy-minimizing by design

The public patient experience does not require a stored medical history to answer a general information question.

Neutral information architecture

Retrieval and ranking prioritise source quality and relevance, not who funds a deployment. Identical logic runs for every tenant.

How governance, AE capture and deferral work

For pharma & life sciences

The intelligence layer behind patient engagement.

Where it fits

Brand and disease-education websites
Patient support and hub experiences
Market access and affordability journeys
Patient portals and digital companions
Contact-centre deflection and after-hours support
Enterprise patient-services platforms

What your teams learn

Top patient questions by therapeutic area
Where users fail to find an answer
Coverage and affordability themes
Content and training gaps
Support channels offered and used, and questions left unresolved
Engagement trends without a medical-history profile

Questions we get asked

Straight answers.

What is OpenSupport?: An embeddable AI assistant for life-sciences teams. It answers patient and caregiver questions about conditions, treatment, access and affordability, and every answer is composed from graded sources and cited.
Is it for medical information or patient support?: Both, on one platform. For medical information, it gives consistent, cited answers to unbranded disease-education questions at any hour. For patient support programs, it answers access and affordability questions between calls, and defers case questions — a prior-authorization status, a shipment — to the channel that can help.
How does it avoid making things up?: Retrieval comes first: an answer is built from passages retrieved from the corpus, and it cites its sources. The guardrails are written into how every answer is generated, and every answer is then checked for citations, directive and diagnostic language and promotional superlatives, with the result recorded. Where retrieval finds nothing usable, the assistant says so rather than filling the gap.
Can we use our own approved content?: Yes. A deployment can be scoped to a defined portfolio or to its own private content, and that scope is enforced during retrieval rather than filtered afterwards.
How is it deployed?: With one script tag on an existing page, or inside an iframe where a strict content-security policy requires it. Each deployment gets its own public key, bound to the origins you nominate.

Give patients a better answer before they give up searching.

See how OpenSupport supports disease education, patient services, market access and enterprise patient engagement.