Features
Everything the platform does, with the status marks left on.
The full capability panorama, cluster by cluster: the gate, the channels, memory and the record, and the full scope of the field-rep role. The status marks are literal — live, preview, in development, or roadmap — because a pharma buyer should be able to audit the ambition. We would rather you read "roadmap" here than discover it in a contract.
The gate
On the gated text channels — web chat and Telegram — a ZenRep's reply is constructed and checked before it reaches the HCP: grounded in your MLR-approved corpus, verified claim by claim, fair-balanced, and written to an inspectable record.
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, pre-send
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 refusal
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 runs live on the production path; the LLM backstop has shipped and is validated offline, with live verification in progress.
Escalation to your team
Edge cases and adverse-event reports route to your team, never to an autonomous decision — human-in-the-loop, stated as policy.
Jurisdiction & class rulesets
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. A product the system cannot classify is refused rather than mis-classed.
EU & UK jurisdictions
Not live today. The regulatory research is complete and provisional rulesets are authored; counsel review and productization remain before any EU or UK tenant goes live. EU is a near-term priority.
The channels
HCPs don't all live in one inbox. A ZenRep meets them where they already are — and each new channel ships behind the same compliance gate that governs the first one. Here is exactly what's live and what's coming.
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. 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
Video detailing by avatar — demoable today, with every word audited after the fact. The fully gated version, checked before it speaks, is the near-term path.
Phone (voice call)
A gate-enforced voice pipeline is in development; it is not available today. Every spoken word will still pass the same gate.
Email & SMS
Email and SMS as detailing channels, behind the same gate as everything above. On the roadmap.
Memory & the record
What a ZenRep remembers, and the record it writes while it works — reconstructable for your compliance team any time.
Conversation persistence
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
Compounding per-HCP memory that carries prior context forward into new conversations is on the roadmap — not present today.
Append-only 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.
Admin console & drill-down
Every interaction lands in your audit trail and admin console, exportable as CSV, with per-conversation drill-down for your compliance team.
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.
Post-call notes & CRM write-back
Structured post-call notes and CRM write-back. The raw material is live today: every conversation is already recorded verbatim, turn by turn.
The full-scope ambition
A field rep's job runs longer than a call list — and we publish where we stand on every line of it. The lines below are ambition, marked as ambition.
Scheduling
Booking with office staff, reminders, and the inevitable reschedules — when a clinician asks to set one up.
Sample requests
Sample requests placed in the conversation where they are asked for — filed at the moment of the ask, not from the car afterward.
See the status marks proven, not promised.
A demo runs against a corpus that looks like yours. Bring your MLR team and your hardest off-label probe.