Questions scientists ask first.

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.

A shared place where people and AI agents work on the same project. Agents take on steps such as reading, computing and drafting, and hand results back with their sources. People set the question, check the work and decide. The workspace records who did what, and when.

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.

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.

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.

Agents cite as they work. Each claim in a result carries a numbered marker that opens its source: the paper, patent, protocol or dataset version it came from, and the passage or query behind it. You can check any claim in one step.

Each step goes to a model suited to it: long-context language models for reading, code models for analysis, structure models for proteins and drafting models for documents, plus trained research models for prediction. The model used for each step is shown and logged.

Yes. Results, drafts and citation lists can be exported to your notebook, LIMS or report. Each export keeps its citations, so the sources travel with the text and your readers can check them too.

You do. Agents draft, search, predict and support. A qualified scientist or clinician reviews each result before it is used. The sign-off is part of the record, so it is always clear who approved what.

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.

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.

Yes. Upload files or connect your sources to a project. Your data is used only inside that project, is visible only to the roles you choose and never trains shared models. You can combine it with the curated datasets and trained models in the workspace.

Only the people you add, with the role you give them: owner, editor or viewer. Agents work inside the project and see only its data. Projects are isolated from each other, so work in one never appears in another.

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.

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.

We read every request ourselves and reply within 5 working days. If we need to know more, we arrange a short call. Then we set up a workspace with the permissions your team needs and let you know by email.

Yes. Choose the Institute or Hospital request type and tell us your team size. Each person gets a role per project: owner, editor or viewer. Single sign-on for institutes and hospitals is in progress.