Published Work — Papers, Playbooks, Code

The Enterprise Agentic Platform

Architecture, Patterns, and the AI Operating System. A Technical Reference for Building Governed, Scalable Agentic Systems in the Enterprise.

Every company will build an agentic platform. Gartner predicts 40% will be cancelled by 2027, not because the technology fails, but because the governance layer was never built. This is the blueprint for the other 60%. Twelve chapters on the full ecosystem (protocols, frameworks, LLMs, guardrails, observability), the six implementation paths with honest trade-offs (Microsoft, Salesforce, AWS, Google Cloud, Databricks, DIY), the four-layer AI Operating System architecture, and a week-by-week 90-day plan.

From Autonomous Agents To Accountable Systems

The Enterprise Playbook for High-Trust, High-ROI AI

The "AI agent" hype is a strategic trap. Enterprises don't need more autonomy — they need accountability. This playbook argues that the durable asset isn't the agent, it's the Enterprise AI Operating System: the architectural blueprint that turns ungoverned experiments into a governed, auditable, reusable capability. Includes a 3-step, 90-day roadmap for leaders who want to stop chasing features and start owning the platform.

TrustGate

Black-box reliability certification for AI agents via self-consistency sampling and conformal calibration. The production implementation of the TMLR paper. Exact, finite-sample, distribution-free guarantees — no retraining, no white-box access.

Guardrails

Declarative YAML-based policy engine for AI agent guardrails. Define what an agent can and can't do in a config file — not in prompt engineering. Auditable, reviewable, diff-able.

Context-Router

Intelligent context routing for agentic systems. Decides what context to load, for which step, at what cost — instead of jamming everything into every call. Built for systems where token economics matter.

Agent-Monitor

Governance-first observability for AI agents. Built around the questions auditors actually ask, not the metrics dashboards love. Traces, decisions, interventions — logged in a form a compliance team can read.

Agent-Auth

Identity and access management for AI agents. Agents aren't users. Your security model was built for users. This is the missing layer.

Mapping The Exploitation Surface: A 10,000-trial taxonomy of what makes LLM agents exploit vulnerabilities.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. Nine of twelve attack dimensions produce zero exploitation. One, goal reframing ("you are solving a puzzle"), breaks every model tested despite explicit rule instructions. A narrower, testable threat model for defenders.

Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training

How load balance evolves during Mixture-of-Experts training, modeled as a congestion game with a single effective parameter. Three phases emerge — surge, stabilization, relaxation — invisible to analysis of converged models. Validated on OLMoE and OpenMoE checkpoints.

Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration

Self-consistency sampling plus conformal calibration yields a single reliability number per system-task pair, with exact, finite-sample, distribution-free guarantees. Validated across five benchmarks, five models, three families. Cuts API cost by ~50% via sequential stopping.

A Mean Field Game of Portfolio Trading and Its Consequences On Perceived Correlations

With Charles-Albert Lehalle

This paper extends the optimal-trading MFG to portfolios of correlated instruments. Shows how trading flows distort naive estimates of intraday volatility and correlations. Validated on 176 US stocks over one year.

On quasi-stationary Mean Field Games models

Mean field games with myopic players — agents who optimize expected future cost by treating their environment as frozen. Existence, uniqueness, and exponential convergence to equilibrium under quadratic Hamiltonians.

On mean field games models for exhaustible commodities trade

With P. Jameson Graber

Mean field game model for firms producing exhaustible resources and leaving the market as capacities deplete. Well-posedness and epsilon-Nash equilibrium results for the corresponding N-player Cournot game.

Variational mean field games for market competition

With P. Jameson Graber

Bertrand and Cournot mean field games with reflection boundary conditions. Shows the system can be written as the optimality condition of a convex minimization problem.

A short proof of the large time energy growth for the Boussinesq system

A short proof that L^p norms of global solutions grow for 1 < p < 3 and decay for 3 < p ≤ infinity. Kinetic energy blows up as t^(1/2) — contrasting the Navier-Stokes case.