ZENOUZ.ai
Email Kayvan
Projects

Public work selected for clarity and substance.

Each project is here because it says something concrete about how AI should be built, used, or explained.

Featured now

ZenInvest

ZenInvest is an open-source investing system with deterministic risk rules, broker-truth reconciliation, and a full audit trail. Its first design let a multi-vendor committee of Claude, GPT, and Gemini debate every trade. Six months of live paper-trading evidence showed that committee had no entry edge, and the results were published as a working paper. The redesign, ZEN-2, lets a deterministic full-universe ranking choose the shortlist, asks one LLM analyst for a falsifiable thesis memo per name, and measures the agent against an index arm and a rules-only arm. Autonomous buying is paused while ZEN-2 is built.

Most AI investing claims are never tested against a baseline. ZenInvest publishes its own evidence, including the negative results, and treats every claim about LLM value as something to measure rather than assume.

PythonFastAPIReactSQLiteMulti-LLMDockerSlack
Read the ZenInvest briefView ZenInvest on GitHub
Why it belongs here
  • Negative results published, not buried
  • Measured against control arms
  • Deterministic rules keep the veto
  • Research posture over return promises
Portfolio

Working systems with clear boundaries.

Each project states what works, what remains experimental, and where human judgment stays in control.

activeEvidence-grounded job search intelligence

ZenGrowth

A local-first, auditable career operating system spanning role discovery, grounded applications, interviews, offers, and the first 90 days — while keeping personal data on your own machine.

  • Deterministic grounding gates catch selected unsupported figures and names a draft can't trace back to verified evidence, and a human reviews every sentence
  • Structure-preserving CV tailoring realigns the summary and reorders evidence-backed lines instead of rewriting
  • Interview, offer, onboarding, and departure workflows preserve context beyond the application
  • Explainable scoring with a stored rationale, and each material action recorded in an audit trail
  • Python
  • FastAPI
  • SQLModel
  • React 19
  • Claude
  • Tavily
  • SQLite
  • Docker
Read the ZenGrowth briefView ZenGrowth on GitHub
From the lab

6 more projects, documented as R&D briefs.

Earlier-stage work lives in the lab until it earns a full project page. Each brief covers the idea, the engineering, and the pattern worth reusing.

Research & EducationZenArena

Can an agent get better without changing its weights?

ZenArena puts one of agentic AI's favourite claims — that memory makes agents better — under a falsifiable test, using chess and a Stockfish truth signal to measure whether governed memory beats remembering everything.

Research & VisionZenForecast

Forecasting as a loop, not a number on a slide

ZenForecast is an open-source, governance-first Python framework that treats forecasting as a continuous predict → decide → act → learn loop — with interchangeable models, leakage-free backtesting, and an audit trail behind a single API.

Research & EducationZenLab

Measure before you build: a sandbox for de-risking agentic AI

ZenLab is an offline-first research monorepo spanning 21 AI/ML topics across 10 tracks — a place where agentic techniques must earn their way into production designs through experiments instead of hype.

Independent InnovationStitch

Prove it in physics first: a digital twin for a canal-cleaning robot

Stitch is a simulation-first digital twin of an autonomous, wildlife-safe, amphibious litter-collection robot — a six-package ROS 2 / Gazebo system that must pass its full mission in simulated physics before a single part is bought.

Research & Educationmatroid-grid-rl

Can a little graph theory make grid-control AI learn faster? A pre-registered no.

A solver-free connectivity test, grounded in the graphic matroid, can screen power-grid topology actions far more cheaply than simulating each one. I pre-registered a study to see whether that screen also helps a reinforcement-learning agent learn faster. It did not, and the reasons are worth more than a positive result would have been.

Lab projects graduate to full project pages here as they mature. The full collection, including the ZenInvest and ZenGrowth briefs, lives inWriting.