The QA layer
SENAITY
Catch bad lab results before they leave your lab. ML-based anomaly QA for SENAITE LIMS — one Docker stack next to your SENAITE, no cloud, no data out.
A single result that should have been caught and goes out the door can cost a customer relationship, an accreditation, or trigger a recall.
SENAITY watches every analysis as it flows through your lab and flags the values that do not fit your historical pattern, so your verifier sees the outlier before signing it off.
SENAITY uses Isolation Forest models trained per analysis keyword and per client. Anything that does not fit gets flagged before it can be verified and published. No manual thresholds, no rule maintenance.
Sensitivity is adjustable per analysis: Strict, Normal, or Sensitive. The model retrains on your verified results, so it stays calibrated to how your lab actually works.
- Kanban board. Due, Received, To be Verified, Verified, Published — auto-refreshing as your SENAITE state changes.
- Analysis drawer. Click any sample card to drill into pending tests without leaving the board.
- Search & filter. Full-text search and dynamic filters on any SENAITE catalog field.
- Scientific rendering. Results in proper scientific notation, with uncertainty and units carried through.
- Pick any two or more samples. SENAITY lines them up next to each other.
- %RSD with thresholds. Adjustable per analysis, flagged in line.
- Z-score charts & distribution plots. See where one sample drifts from its peers.
- XLSX export. The full comparison, ready for documentation and audit trails.
SENAITY ships as a Docker stack you run on your own infrastructure, alongside your existing SENAITE. Your lab data never leaves your network. No DPA negotiation, no GDPR Article 28 paperwork, no ISO 27001 audit questions on call one. The same procurement path your team already uses for SENAITE itself.
- On-premise install. Three small containers behind your existing reverse proxy. Memory footprint under 500 MB.
- Bootstrapped on your data. We train the initial anomaly model on your last 90 days of verified results during install.
- Uses your SENAITE credentials. No new accounts, no extra passwords.
- No data lock-in. Every value lives in SENAITE. SENAITY only reads and overlays.
06 / Plans
Pick what matches your lab
- Full feature set, including anomaly detection
- Open-source license, self-host
- You run it, you maintain it
- Community support on GitHub
- Standalone Docker license, single lab, on-premise
- White-glove install & anomaly model bootstrap
- 30-minute training call
- 14-day follow-up call
- Annual EUR 4,900 — saves 16%
- Multi-site, 3 sites included
- EUR 290/month per extra site
- Single invoice for lab networks
- Annual EUR 14,900
- Validated environments: medical, pharma, GxP
- IQ/OQ documentation
- Signed SLA
- Source-code escrow on request
Try the free demo at senaity.com with your own SENAITE URL (or ours).
- What is the difference between the hosted demo and the Standalone product?
- The free demo at senaity.com is for clicking around and evaluating the product. It can connect to your SENAITE if your SENAITE is reachable from the internet. The paid Standalone product runs entirely inside your own network. Your lab data never reaches our servers. For any production lab, Standalone is the right answer.
- Where does my lab data live?
- In SENAITE, where it already lives. SENAITY is read-mostly: it pulls results from SENAITE through the JSON API, runs them past the anomaly model locally, and overlays the flags. Cancel SENAITY at any time and everything is still in your SENAITE.
- Do you support validated environments (GxP, IVDR)?
- Yes, through the Enterprise tier. We provide IQ/OQ documentation, a signed SLA, on-premise deployment with frozen versions, and source-code escrow on request. Talk to us about your specific compliance regime.
- What does the install actually look like?
- One 90-minute screen share. We deploy the three SENAITY containers next to your SENAITE, point them at it, and bootstrap the anomaly model on your last 90 days of verified results. Then a 30-minute training call with your lab manager and one analyst. A 14-day follow-up call confirms it is doing what you need.
- Can we self-host without paying?
- Yes. The Community tier is the full product, free, under an open-source license. You run it, you maintain it, you train your own anomaly model. Most labs eventually move to the Lab plan to get the install, the training, and the support, but you do not have to.
Related
Around the platform
Bring SENAITY into your lab
Built by RIDING BYTES, the core developers behind SENAITE. We built it because we kept watching labs verify results they should not have, and we wanted to give the verifier a second pair of eyes that never tires.