Where scientists and AI agents do research together.

From question to cited answer in three steps.

  1. 01

    Ask

    Write the question in plain language. Attach your data or connect your sources.

  2. 02

    Agents work

    Each step is routed to the model that does it best: reading, coding, prediction, drafting. Every action is recorded.

  3. 03

    You decide

    Review results with their sources. Export to your notebook, LIMS or report.

You → Reader, Analyst, Writer → a cited result → your decision

Seven workflows. One evidence trail.

One query over papers, patents and protocols · three become citations

Literature & evidence

Papers, patents, protocols and registries in one query. Every claim points to its source.

PubMedpatentsprotocols
Open literature & evidence

A ligand docks into the pocket · candidates ranked

In-silico studies

Screen, simulate and compare before the bench: docking, ADMET, pathway and PK models.

dockingADMETsimulation
Open in-silico studies

Sequence → predicted fold → candidate with validation

Protein studies & design

Structure prediction, binding analysis and sequence design, with validation reports.

structurebindingdesign
Open protein studies & design

Guide finds the site · cut · repaired · off-targets reviewed

CRISPR & genome editing

Guide design, off-target review and screen analysis, documented for the lab.

guide RNAoff-targetscreens
Open crispr & genome editing

Plan → Start → Run → Close · the cohort fills in

Clinical trials, full cycle

Protocol drafts, site feasibility, cohort criteria, CRFs, statistical analysis plans, monitoring summaries and CSR drafts.

protocolCRFSAPCSR
Open clinical trials, full cycle

IND modules checked one by one · a reviewer question answered

Regulatory documentation

IND/CTA modules, IVDR technical files and SOPs, structured for reviewer questions.

INDCTAIVDRSOP
Open regulatory documentation

Claim tree · prior art on a timeline · novelty argued

Patent & IP documentation

Prior-art search, invention disclosures and claim-drafting support from your own results.

prior artclaimsdisclosure
Open patent & ip documentation

Follow a single question through the workspace.

You ask · two datasets attach to the question

The Reader agent reads 40 papers · three become citations

The Analyst docks the ligand · candidates ranked · G12C flagged

Guides designed · cut and repair · off-targets checked

The Writer assembles the protocol · cohort defined · SAP drafted

IND modules and claim draft from the same sources · a scientist signs off

  1. 01

    A question arrives

    The team asks why a cell line resists an inhibitor. They attach assay results and a variant list.

  2. 02

    Evidence is gathered

    The Reader agent reviews 40 papers and two cohort datasets and cites the three that explain the mutation.

  3. 03

    Models test the idea

    In-silico docking and a variant-effect model rank the mutation and suggest a binding-site change.

  4. 04

    An edit is designed

    Guide RNAs are designed and checked for off-targets. A validation protocol is drafted for the bench.

  5. 05

    A study is planned

    A cohort definition, protocol draft and statistical plan are prepared for the clinical team to review.

  6. 06

    The record is written

    Regulatory and patent drafts are built from the same cited results. A scientist signs off at each checkpoint.

Not another chat window.

General AI chatPoint toolsCytogent
  • Cites every claim to a source you can openRarelySometimesAlways
  • Routes each step to the best modelNoNoYes, logged
  • Curated life-science datasets and trained modelsNoPer toolBuilt in
  • Works across literature, in-silico, protein, CRISPR, trials, documentsNoOne area eachOne workspace
  • Your data never trains shared modelsVariesVariesNever
  • Role-based access per project and datasetNoVariesYes
  • Human sign-off at every checkpointNoNoYes

Built on data you can trace.

Datasets

Public and licensed collections, cleaned, versioned and documented. Each one lists its source, version and licence inside the workspace.

Trained models

Domain models for prediction and screening — variant effect, binding affinity, assay QC — each with its validation reported on its own card.

Protocols

Protocols you can search, adapt and cite, with every step attributed to where it came from.

See data and models

Datasets with source, version and licence · models with validation · the curation path

Your data stays yours.

  • Project isolation

    Each project has its own storage scope. Agents see only its data.

    Done
  • No training on your data

    Your data never trains shared models.

    Done
  • Encryption in transit and at rest

    TLS 1.2 or higher. Managed keys, rotated on a schedule.

    Done
  • Role-based access

    Owner, editor and viewer roles per project and dataset.

    Done
  • EU data residency

    Storage and processing inside the EU.

    In progress
  • SOC 2 Type II

    Independent audit of controls.

    Planned

Cytogent is a research tool. It is not a medical device and makes no clinical decisions.

Read the full security page

Three isolated projects · a crossing refused · roles · the audit log

Questions scientists ask first.

What is Cytogent?

Cytogent is an agentic workspace for life science research. Scientists and AI agents work together on literature and evidence, in-silico studies, protein studies and design, CRISPR and genome editing, clinical trials from planning to report, and regulatory and patent documentation — every result with cited, auditable evidence. Cytogent is operated by WelloWork AB in Sweden.

Who is Cytogent for?

Four groups. Pharma and biotech R&D teams who need evidence behind every decision. CROs and clinical teams who draft protocols, CRFs and reports. Hospitals and academic labs doing cohort work under strict ethics and data rules. Regulatory and IP teams who build submissions and patent filings from scattered results.

What can the agents do?

Seven workflows. Search literature, patents and protocols with citations. Run in-silico screens and simulations. Predict protein structure and design sequences. Design CRISPR guides and analyse screens. Support clinical trials from protocol to clinical study report. Draft regulatory documents. Support patent prior-art search and claim drafting.

Is my data used to train models?

No. Data you bring to Cytogent stays inside your project and never trains shared models. Projects are isolated from each other, access is granted per role, and every agent action against your data is recorded in an audit trail you can read. WelloWork AB acts as processor under a data processing agreement.

Where is data hosted?

Cytogent is built and operated from Sweden by WelloWork AB. EU data residency — storage and processing inside the EU — is in progress rather than finished, and the security page shows the current status of every control with a plain label: Done, In progress or Planned. Sub-processors are listed publicly.

How is Cytogent different from a general AI assistant?

A general assistant gives you an answer. Cytogent gives you evidence. Every claim links to a source you can open, each step is routed to the model that does it best and logged, curated datasets and trained models are built in, access follows your data rules, and a scientist signs off at every checkpoint.

How do I get access?

By request. There is no self sign-up, no password and no free trial. Choose one of three request types — Individual, Institute or Hospital — and tell us your field and what you want to do. We read every request, arrange a short call if needed, then set up a workspace with your permissions.

Is Cytogent a medical device?

No. Cytogent is a research tool. It makes no clinical decisions, gives no diagnosis and is not certified as a medical device under the MDR or IVDR. Agents draft, search, predict and support. A qualified scientist or clinician reviews and decides, and that review is part of the record.

Bring your next question.

Tell us your field and what you want to do. We set up the workspace around it.

Request access