# Personal Quant Agent

Source: https://dinand.com/experiments/personal-quant-agent/
Author: Dinand Tinholt

> A research system that scans public market data, tests a small strategy library, applies explicit risk controls and records simulated decisions in a paper portfolio.

The question behind the system

> A useful trading experiment should make weak evidence, regime dependence, costs and failure conditions more visible—not hide them behind an autonomous agent.

What it is designed to do

- Backtest signals net of modeled fees and slippage
- Challenge strategies with walk-forward and Monte Carlo checks
- Apply paper-portfolio sizing, stops and circuit breakers

Execution: Paper only

Validation: Three complementary checks

Live orders: Not implemented

The public boundary

## What this page does—and does not—open.

This is a personal research prototype, not investment advice or a claim of expected performance. It has no live order routing, and the public site exposes no portfolio state or trading controls.

Separate application

No public deployment is linked yet. The introduction remains available without exposing a private service or local data.

[Try the decision brief builder ](https://dinand.com/experiments/decision-brief-builder/)

Continue the thread

## A next room to enter.

[Choose another path ](https://dinand.com/)

[System profile · Working research product

### Pakhuis

A seventeenth-century Amsterdam canal warehouse, built in simulation, where two robots count stock and a reviewer decides what reaches the record.

](https://dinand.com/experiments/pakhuis/)[Experiments · Interactive tool

### Monitoring cost explorer

Explore how portfolio size changes modeled oversight cost.

](https://dinand.com/experiments/monitoring-cost-explorer/)[Experiments · Interactive tool

### Decision brief builder

Turn a question, evidence and constraints into a structured brief.

](https://dinand.com/experiments/decision-brief-builder/)

[All experiments ](https://dinand.com/experiments/)[Back home ](https://dinand.com/)

---
Site guide for AI agents: https://dinand.com/llms.txt