Inbrev logoInbrev
Hack Apertus 2026 · Track 2B · Team Apertool
Run locally, the practice inbox never leaves the practice.
Inbrev sorts the inbox of a Swiss GP practice by handling path and deadline, with Apertus, built to run on a box in the practice. Every field it extracts quotes its source.
▶ Watch the 2-min demo Code on GitHub
solo builder · fictional data only
The problem

Before the first patient, there is the inbox.

Lab reports, refills, insurer forms and faxes in four languages land in one queue. A practice assistant (MPA) reads them one by one.
9.5h / week
of administration for Swiss GPs, up from 8.6 h in 2020
Workforce Study, Praxis 2026 · n = 1,776
54min / day
on requests from authorities and insurers alone
gfs.bern for FMH, 2025 · N = 1,532
Art. 321
Professional secrecy binds doctors and their assistants
Swiss Criminal Code · FADP Art. 5
How it works · Purposeful use of AI

Sorted by who handles it and by when.

01 · READ

Mail, forms, faxes

E-mail, IMAP, web forms, fax via OCR. German, French, Italian, English.

02 · ROUTE

9 handling paths

Plus the administrative deadline and who takes it.

03 · PROVE

Quote or drop

Every field quotes its source. No quote in the original, no field.

Clinical contentPossible symptoms leave automation and go to a person. Not rated, not ranked.
Code checks what code can check: AHV numbers, dates, quotes.
Demo

One fax, sorted. Every value shows where it came from.

Inbrev web app: insurer fax routed to admin with deadline 8 October; route, deadline and extracted values are highlighted as quotes in the original text 1 2
1
Route and deadline

Insurer, admin, by 8 Oct. The date comes from the quote, the deadline from code.

2
Quote or drop

Each highlighted value is verbatim in the fax. No quote, no value.

Running app, stored Apertus 8B result, fictional fax. Possible symptoms would go to a person instead.

Architecture · Sovereign deployability

Pull the cable.
Inbrev keeps sorting.

Inside the practice · no outbound connection
Inbox
›
Parse + OCR
›
Apertus 8B
›
Quote check
›
Sorted inbox
On-premmini PC in the practice
Air-gappedmail gateway hands messages in
Swiss cloudoption for single practices
Docker, no network
egress dns / tcp / https: FAILED
Local Q4, laptop iGPU
71.8 s / message, 16/16 clinical out
Evaluation · Technical rigour

No synthetic clinical message ran by itself.

180 synthetic messages, labels checked by one person on 60.
Setup Routes right Clinical out Runs by itself
Keyword rules + lexical net 0.79 7/16 88 %
Apertus 8B, one answer, no checks 0.87 9/16 95 %
Inbrev with Apertus 70B 0.96 15/16 82 %
Inbrev 8B + symptom pass 0.94 16/16 78 %
Paired on 180: 8B beats the rules 32 to 5 (p = 7·10⁻⁶). Details and all rows: report §5.
16/16
clinical messages out of automation
95 % CI 0.81–1.00 (Wilson)
  • Labels fixed before any text; Apertus never writes or labels test data.
  • Two open models (not people) relabelled 367 messages blind: κ 0.93 route, 0.97–0.98 clinical. One person, blind, 60 messages: κ 0.98 route, 1.00 clinical.
Purposeful use of AI · model choice

Why Apertus, and what it costs.

Measured, same pipeline

  • Qwen3.5-9B, Ministral 8B: 177/180 routes
  • Apertus 8B: 170/180 · 70B: 172/180
  • Fresh hold-out: 5 wrong routes run by themselves (Qwen 0); 70B second opinion: 3

Why Apertus anyway

  • Only openly available training data, opt-outs applied, personal data filtered
  • Published data catalogue and EU training-content summary
  • Local run and quote checks work with any model: no argument
A trade-off, not a free choice. Sources and hold-out details: report §5.
Value, cost & scalability

Swiss francs per 1,000 messages, on hardware the practice owns.

On-prem mini PC
≈ CHF 12
at 60 messages a day; box, power, CPU time before the symptom pass
Swiss cloud VM
CHF 2.39
billed while sorting; same CPU time, other CPU not measured
Swiss token API
CHF 3.13
Apertus 70B list price, tokens measured with the symptom pass
≈ 32 min
MPA time saved a day assumption
60 messages × 78 % automatic × 45 s saved, minus rework of misroutes
Estimates, prices excl. VAT, 4 Oct 2026. Box and value: report §5; VM: scripts/cost_model.py.
Intended purpose · Implementation feasibility

Administrative by default. Clinical mode is research only.

Default mode: Inbrev does

  • Sort by path and deadline
  • Extract fields, each with its quote
  • Say “you decide” when unsure

Default mode: Inbrev never

  • Rank by clinical severity
  • Rate symptom severity or suggest care
  • Send patient data out (local mode)
Clinical research mode: off by default, not validated, not certified (MDCG 2019-11, MepV Art. 15).
Business model & roadmap

A module for the software practices already use.

User
The MPA, first thing in the morning
Buyer
Practice owner or doctors' network
Price
CHF 150–250 / month hypothesis
Channel
Module in HIN mail or practice software
OCT 2026
Evaluation, offline proof, cost
NOV – DEC 2026
5–10 interviews with MPAs and owners
Q1 2027
Pilot in one group practice
Q2 2027
Classification review before first sale
Inbrev logoInbrev
Team Apertool · Niklas Wichter, solo builder
Our ask
Pilot Inbrev in one Swiss group practice.
On its own box, from Q1 2027. Your inbox stays in your practice.Contact: hello@apertool.ch

inbrev.apertool.ch