Platform for Risk and Incentives Management in Web3

Driving efficiency and economic security in Web3:

  • Drive participation in Web3 ecosystem

    • Increasing transparency of protocols
    • Monitoring of systemic risk
    • Assurance and auditing aligned with regulatory expectations
  • Independent and Impartial evaluations of protocol design

    • Testing for robustness and resilience
    • Evaluations of economic soundness
    • Analysis of tokenomics models.
  • Inform and Automate Protocol Governance

    • Principled reward & incentive mechanism design
    • Automatic risk management
    • Optimising liquidity growth
    • Continuous monitoring and stress testing against adversarial scenarios


Plug and Play platform that uses battle-tested techniques from the quant finance industry and multi-agent RL simulations:

  • Principled optimisation and design to manage risk and maximise growth
  • Rational validation and verification of protocol design and its economic security
  • Continuous monitoring and stress testing against plausible future scenarios including black swan events


Adapting behaviours to available information


Learning strategies to optimise reward

Environment design

Capturing key interactions and incentives

REWARD "of a system"

Discovering plausible states of a systems


  • Lukasz Szpruch

    Lukasz Szpruch

    Quant Finance & Machine Learning

    • scholar
    • twitter
  • David Siska

    David Siska

    DeFi & Quant Finance

    • scholar
    • twiter
  • Marc Sabate Vidales

    Marc Sabate Vidales

    Engineering & RL

    • twitter
    • github
  • Sam Cohen

    Sam Cohen

    Quant Finance & Data Science

    • scholar


  • Estimating risks of option books using neural-SDE market models

    In this paper, we examine the capacity of an arbitrage-free neural-SDE market model to produce realistic scenarios for the joint dynamics of multip

  • Identifiability in inverse reinforcement learning

    Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions. As al

  • Tail-GAN: Nonparametric Scenario Generation for Tail Risk Estimation

    The estimation of loss distributions for dynamic portfolios requires the simulation of scenarios represent- ing realistic joint dynamics of their c

  • The Case for Variable Fees in Constant Product Markets: An Agent Based Simulation

    We are interested in how the relationship between the fee in a constant product market (CPM) and the volatility of the swapped pair on other liquid

  • Inefficiency of CFMs: hedging perspective and agent-based simulations

    We investigate whether the fee income from trades on the CFM is sufficient for the liquidity providers to hedge away the exposure to market risk. W