Create
Evidence intelligence and knowledge creation
Discover, verify, extract, structure, and synthesize evidence into work that the next function can inspect and use.
Kesis & Sisters
Medicine runs on knowledge.
We’re building the factory.
Kesis & Sisters is building Nyx, where specialized agent teams create, interpret, govern, and maintain computable medical knowledge. Applications are built from that knowledge.
CompanyKesis & Sisters
Flagship in active developmentNyx
CreateInterpretGovern
Governed, computable medical knowledgeexpressed through applications
The problem
Evidence does not arrive as usable clinical knowledge.
Medical evidence is fragmented, context-dependent, and always changing. The hard work is turning it into structured knowledge that can be reviewed, maintained, and used safely across software applications.
- 01Fragmented
Relevant evidence sits across publications, guidelines, standards, and data sources.
- 02Context-dependent
A result gains meaning only when population, setting, applicability, and uncertainty are understood.
- 03Difficult to maintain
Applications need traceable, versioned knowledge that can change without losing its history.
Meet Nyx
A factory built around the work medical knowledge requires.
Nyx is an agent-native medical-knowledge factory. It is being developed around defined functions, responsibilities, handoffs, review, and lifecycle management.
In active developmentNyxAgent-native medical-knowledge factory
CreateEvidence intelligence and knowledge creation
InterpretClinical interpretation and composition
GovernKnowledge governance and publication
From evidence to knowledge
Applications begin with a shared knowledge foundation.
Nyx is being built to turn medical evidence into governed, computable medical knowledge. Applications express that knowledge for different users and decisions.
01Medical evidencePublished sources and standards
02NyxSpecialized functions and governed handoffs
03Governed, computable clinical knowledgeTraceable, reviewable, versioned
04ApplicationsDifferent expressions for different users
The Sisters framework
Three connected functions inside Nyx.
The Sisters provide a memorable structure for creating, interpreting, and governing knowledge. They are a brand framework for the work, not a claim that standalone agent leaders or executive identities are deployed.
Interpret
Clinical interpretation and composition
Contextualize evidence, assess applicability, model outcomes, and compose candidate medical knowledge for review.
Govern
Knowledge governance and publication
Coordinate validation, review, publication control, versioning, supersession, and retirement.
What we are testing
Three applications. One developing knowledge foundation.
Kesis applications are being used to test how governed clinical knowledge developed through Nyx can support different users, clinical contexts, and decisions.
Kesis Clinical — Kidney Cancer
A clinician-facing application currently being used to test how governed clinical knowledge developed through Nyx can support complex kidney cancer decisions.
Kesis Clinical — GIST
A clinician-facing application in clinical testing for gastrointestinal stromal tumour decision support.
Kesis Companion — Breast Cancer
A patient-facing application in testing, designed to express governed clinical knowledge in a form appropriate for patients.
Testing status does not imply commercial availability, regulatory validation, routine clinical deployment, or demonstrated clinical benefit.
See the applications
The company behind Nyx
Built from clinical practice, evidence, policy, and engineering.
Kesis & Sisters is the company building Nyx. Founder Dr. Henry Conter is a practising medical oncologist whose work spans oncology, health technology assessment, quantitative analysis, pharmaceutical strategy, and software.
That combination shapes the company’s central question: how can complex evidence become knowledge that remains clear enough to inspect, govern, and use in real decisions?
About Kesis & SistersInsights
Clinical decisions, evidence, and where technology belongs.
Writing from the perspective of a working oncologist building systems for the decisions that remain difficult.
When I Look at Medical AI, I Start With the Patients
I approach medical AI with the same questions I bring to a clinical trial: who was studied, how dependable is the answer, and will it help the person in front of me?
Read insightI Gave Codex a Chalk Talk
On a walk, I taught Codex how to make a presentation and learned from the exchange. A study of developers asks what stays with us after AI helps finish the work.
Read insightHow Much Benefit Would Make This Worth It?
At a case conference, chemotherapy seemed obvious to many colleagues. I thought the patient had a meaningful choice. What was inside that disagreement?
Read insightCollaborate
Build the next layer with us.
We are interested in clinical testing, research, application development, and strategic collaboration around agent-native clinical knowledge systems.