The mathematics ofagentic systems.
We bring academic frameworks to bear on the complexity and security of specific agentic systems. Our live testbed is Intellcycle, an agentic marketplace for recycled metals.
Agentic systems are growing in capability faster than the tools we have to measure whether they are tractable, safe, or correct.
We study the structural properties of agent behaviour — branching, information flow, capability boundaries, adversarial pressure — and translate them into measures operators can act on. The work is exercised on real workflows, not benchmarks.
What we study
Complexity metrics
Measures of branching, depth, and decision density in agent execution graphs — turning intuition about 'how complex' into numbers operators can compare.
Capability boundaries
Formal models of what a deployed agent can and cannot reach, so capability creep stops being a surprise discovered after an incident.
Information flow
Tracking what an agent sees, retains, and emits — the surface where leakage, contamination, and prompt injection live.
Adversarial pressure
Quantifying robustness under real counterparties pushing back. Benchmarks lie; live markets don't.
Tractability bounds
Knowing in advance which workflows are even decidable — and which are stochastic surfaces dressed as deterministic systems.
Operational safety
Translating structural measures into thresholds, alerts, and rollbacks that an oncall team can actually act on at 3am.
Live work
Intellcycle
An agentic marketplace for recycled metals. Real counterparties, real settlement, real adversarial pressure — the surface where our measurements stop being theoretical.
Morphika
An agentic solution for email — autonomous handling of inbox workflows that usually need a human in the loop. Where information-flow and capability-boundary measures get tested daily.
Team
A small group of science people working on interesting problems in business.
Hussien Ballouk
Physics, strategy, and software engineering — with a math backbone.
- B.Sc. & M.Sc., Southern Federal University (Russia)
- Ph.D. Physics, University of Victoria — in progress
- Background in nanotechnology
Amir Ahmadian
Materials-science rigor with startup-tested execution — anchoring the lab's theory in real systems.
- Ph.D. Materials Science
- Background in materials-science startups
Matthew
Adds math formalism to the equation.
- M.Sc. Mathematics, UVic 2024
- Combined Honours, CS & Mathematics, 2020
Working on something agentic?
Tell us the shape of the workflow. We'll come back with what's measurable and what isn't yet — no decks, no boilerplate.