Skip to content
Forticia
Research
Quantitative FinanceEquities, FX, futures. Factors and backtests, every run replayable.Computational BiologySequence, folding, simulation. Versioned, reproducible labs.Cultural IntelligencePhilosophy, governance, ethics. How institutions decide and answer for it.AI InstrumentationPrivate models. Multi-agent orchestration. Guardrails on write.View all research
Quantitative Finance
  • Equities, FX, futures
  • Factors and backtests
  • Every run logged and replayable
InfrastructurePapersPolarisLink™About
Sign inRequest access
Request access

Research

Quantitative FinanceEquities, FX, futures. Factors and backtests, every run replayable.Computational BiologySequence, folding, simulation. Versioned, reproducible labs.Cultural IntelligencePhilosophy, governance, ethics. How institutions decide and answer for it.AI InstrumentationPrivate models. Multi-agent orchestration. Guardrails on write.

Platform

InfrastructurePapersPolarisLink™About
Request accessSign in
Forticia

A private institute for computational research. It publishes original research and runs a governed environment where every run is logged and replayable.

Sign inSystem status

Research

Quantitative FinanceComputational BiologyCultural IntelligenceAI Instrumentation

Platform

InfrastructurePapersPolarisLink™StatusSign in

Institute

AboutRequest accessContactGitHubPolarisLink repository

Forticia publishes research and simulations. Nothing on this site is investment advice.

© 2026 ForticiaPrivacyTerms
  1. Home
  2. About

Forticia Research Institute

A private institute for computational research.

Forticia Research Institute is a private institute for computational research across quantitative finance, computational biology, philosophy and governance, and AI instrumentation. It publishes original research and runs a governed environment where researchers and agents work together, with every run logged and replayable.

Disciplines
Four, listed below
Access
Invitation or application
Oversight
Committee review, lead approval
Record
Full audit trail
Open source
PolarisLink, Apache-2.0
  1. How it works
  2. Disciplines
  3. Founders
  4. Protocol and papers
  5. Commitments
  6. Contact

How the institute works

Access, review and oversight are part of the design, not an afterthought. This is the path every collaborator takes.

  1. Admission

    Apply

    By invitation or application. Seven short steps, and nothing is stored until you submit.

  2. Admission

    Committee review

    Compliance and fit are assessed before any credentials are issued.

  3. Admission

    A scoped workspace

    Each project gets its own isolated perimeter, role-gated, with capabilities attached on demand.

  4. Operation

    Governed AI

    Models draft by default. A research lead approves any write before it lands.

  5. Operation

    An audit trail

    Every action is kept on the record from the first session, complete enough that nobody has to be asked.

  6. Design

    The full architecture

    Research infrastructureGoverned AI

Four disciplines

One institute, four fields, each with its own page, methods and papers.

  • Quantitative FinanceEquities, FX, futures. Factors and backtests, every run replayable.
  • Computational BiologySequence, folding, simulation. Versioned, reproducible labs.
  • Cultural IntelligencePhilosophy, governance, ethics. How institutions decide and answer for it.
  • AI InstrumentationPrivate models. Multi-agent orchestration. Guardrails on write.

Founders

Cayden Richards

Co-Founder and Managing Partner

He started Forticia in 2023 as a quantitative research lab, now four disciplines.

He is also Co-Founder and Managing Partner of Qlumina Inc., founded in 2026.

caydenrichards.com

Dr Yash Kulkarni

Co-Founder

Yash is a medical doctor, qualified MBBS, and a co-founder of Forticia.

An open protocol, and the papers

Two ways the institute puts its work where others can read and check it.

PolarisLink

An open, domain-agnostic protocol for governed multi-agent coordination, telemetry and provenance. The specification and the C++20 and Python clients are published under Apache-2.0.

About the protocolSource on GitHub

Papers

Original research is published here as papers. Each states a question, the method, the results with their uncertainty and the attempts to break them. None is presented as peer reviewed.

Read the papers

Working commitments

Five commitments, each named for the failure it exists to prevent. The full text, with the ideas it borrows, is on the cultural intelligence page.

  • We try to be wrong early and cheaply.Failure preventedA result nobody tried to break.
  • We name the mechanism before we trust the pattern.Failure preventedA regularity mistaken for knowledge.
  • We hide the future from ourselves on purpose.Failure preventedChoosing the test after seeing the answer.
  • We keep our failures on the record.Failure preventedBeing fooled the same way twice.
  • Every decision has an owner, a trail, and a way to be reopened.Failure preventedA decision nobody answers for.
Read the commitments

How to reach us

The research office answers by email. Access requests are reviewed by the committee.

General enquiriesinfo@forticia.ukResearch and accessresearch@forticia.uk
Request accessContact page

This site publishes no trading signals or performance figures and gives no investment advice.