Platform
How a zenrep stays on-label — end to end.
Every message takes the same path: an HCP writes in on web or Telegram, a reply is drafted, and before a single word is sent it passes the compliance gate — checked in scope, grounded in your approved corpus, fair-balanced, and verified claim by claim. Only then does the HCP see the reply — and every turn is written to the audit trail for your compliance team. This page walks that path and states, honestly, what is live today and what is on the roadmap.
The path every message takes
On web and Telegram, live today, every reply passes the compliance gate before a single word reaches the clinician. Below: one question, one answer, and the record the gate writes while it works. The video avatar is a preview today — a managed-LLM demo audited after the fact, with the fully gated version on the near-term path.
It can only speak approved material.
Every claim is checked before it's delivered.
It refuses rather than guesses.
Every turn is audit-traceable.
The four guarantees the gate rests on
It can only speak approved material.
There's no general medical model improvising underneath. A zenrep cannot assert anything that isn't in your medically and legally approved source material — that corpus is the ceiling on what it can say.
Every claim is checked before it's delivered.
Each turn passes the pipeline: in scope, fair-balanced, grounded in an approved passage, and citable. Then, and only then, is it spoken.
It refuses rather than guesses.
When a claim can't be grounded in approved material, the gate is fail-closed: the zenrep declines, redirects, or routes the question to a human. Refusing correctly is treated as a success, not a failure.
Every turn is audit-traceable.
Each exchange records what was asked, what was answered, what the gate decided, and the exact approved passage it was anchored to — reconstructable for your compliance team any time, and exportable as CSV.
What the gate enforces, control by control
Corpus-grounding
A zenrep answers only from the MLR-approved materials you load — product monograph, ISI, approved claims. There is no general-model answer underneath.
Per-claim verification
Every factual claim in a drafted reply is checked against your approved corpus. If any claim can't be supported, the whole reply is refused rather than sent — there is no partially-approved answer.
Fail-closed
When a question can't be answered from the corpus, a zenrep refuses and routes to a human rather than guessing. Silence over speculation, by design.
Off-label refusal, fail-closed
Structural refusals (pediatric-on-adult, cross-tenant) fire before any model runs. Off-label and out-of-indication claims are refused at the fail-closed pre-send verifier, with deterministic per-class refusal templates — a reply that cannot be grounded on-label is never improvised.
Fair balance & ISI
Efficacy statements are automatically paired with the required safety information; a reply cannot send benefit without the balancing risk.
Adverse-event detection & PV routing
A two-layer detector — a deterministic pattern floor plus an LLM backstop — flags adverse-event reports, records the regulated intake, and pages pharmacovigilance. The deterministic layer is live-verified; the LLM backstop has shipped and is validated offline, with live verification in progress.
Immutable audit trail
Every turn is written to an append-only record with database-level tamper protection; reconstruct any conversation and export CSV for an inspector.
MLR-approval corpus workflow
Your MLR team reviews and approves the corpus at onboarding — nothing a zenrep can say has not already been cleared, and we walk your reviewers through the refusal templates the gate uses. Onboarding is "here is our approved corpus," not a code project.
Memory — live persistence, roadmap compounding
Per-HCP continuity: a zenrep persists each clinician's thread so the record stays continuous and your team can pick it back up.
Compounding per-HCP memory that carries prior context forward into new conversations is on the roadmap — not present today.
Jurisdiction & class adaptation
The gate adapts its rules to the market and the product class: Canada (PAAB / Health Canada) and the United States (FDA OPDP) today, for both drug and device. Additional jurisdictions are on the roadmap.
Every channel, held to the same gate
HCPs don't all live in one inbox. A zenrep meets them where they already are. Web and Telegram route through the same pre-send compliance gate today — same corpus, same audit trail; here's exactly what's live and what's coming, stated honestly with nothing oversold.
Web chat
Chat with a zenrep right now in the browser. The public demo runs the live compliance gate on every turn — try to push it off-label and watch it decline.
Telegram
Live today with our design partner. HCPs message the zenrep on Telegram, and every reply passes the gate before it's sent — gated, grounded, and logged like every other channel.
Live video-avatar call
A real-time, face-to-face avatar conversation — a face, a voice, a genuine back-and-forth, not a form or a chatbot script. You can demo it today; a generally available, fully gated video channel is on the near-term path.
Phone (voice call)
A gate-enforced voice pipeline is in build — every spoken word still passes the same gate. Coming as we complete the provider agreements; not available today.
SMS (text)
Text the zenrep, get the same gated, on-label answers. On the roadmap and coming alongside phone voice; not yet available.
See the whole path on your own corpus.
A demo runs against a corpus that looks like yours — bring the off-label probe and read the receipt end to end.