S Shamar Bryant
Projects Skills Certifications About Resume Contact
Email LinkedIn
Home/Projects/THE BRAIN
AI-Assisted EngineeringPythonReactData PipelineQuant Systems

THE BRAIN

A quantitative system that tracks live sports-betting markets in real time, spots mispriced odds, and acts on them automatically. It has a Python backend, a React control room, a large data pipeline, and an automated test suite that gates every change. I designed and built it end to end, using Claude Code and ChatGPT to move faster.

What it isAn automated, real-time market-analysis and decision system that runs on my own machine
StackPython (~40 modules) · React / JSX control room · local market database · Kalshi API · Discord
Scale~50,600 lines of Python · ~9,500-line React app · 335 automated tests
My roleDesigned, built, tested, and iterated the whole system
Built withClaude Code and ChatGPT as coding collaborators
StatusRunning locally  actively developed
NoteA personal research project. Not investment advice. Most performance figures come from backtests and are labeled as such.
THE BRAIN operations floor — the live control-room interface showing every game the system is watching, its calculated fair prices next to the market, the current streak, and a live signal log.
The live control room: every game the system is watching, its own fair price next to what the sportsbooks say, and a running signal log.
50,600
Lines of Python
9,500
Lines of React (the control room)
335
Automated tests, green before every deploy

Overview

The idea is simple. A betting market is made of many sportsbooks, and they don’t all update at the same speed. When the fast, professional books move and the rest of the market hasn’t caught up yet, there’s a brief, measurable gap between the current price and the “true” price.

THE BRAIN watches for that gap across about 30 books, decides whether it’s real, and places a bet with no human in the loop. Then it grades the result and retrains overnight. It’s a closed loop: collect data, decide, record, learn, repeat.

What makes it a real engineering project rather than a script is everything built around that loop to keep it honest — a full automated test suite, a permanent record that can’t be quietly edited, and a validation step that has to approve any change before it’s allowed to risk money.

How AI fits in: I designed the system and made every real decision about how it works. AI coding tools helped me implement it faster. The architecture, the testing, and the judgment calls are mine.

How it works

Data flows one direction, from raw prices to a placed bet. Every step only uses information that existed at decision time, and if data is missing or stale the system stops instead of guessing.

COLLECT · live odds from ~30 books + the exchange, scores, weather

PRICE · strip the bookmaker margin, blend books into one fair price

ANALYZE · read who’s moving the market + run an independent game model

DECIDE · bet only when several signals agree (see below)

EXECUTE · place the bet on the Kalshi exchange, fees included

RECORD · write every decision to a permanent log

LEARN · overnight: grade results, retrain, repeat
When it bets

The system stays out of the market by default. It only bets when the fast books are leading, the wider market agrees on a price, and at least four of these six checks line up:

sharp books leading the game model agrees the close-price forecast agrees the line moved toward the side no late money against it it agrees across both markets

I didn’t hand-pick that rule. I found it by testing thousands of candidate rules, then confirmed it held up on data it had never seen and beat a “shuffled-data” test designed to show what pure luck could look like.

THE BRAIN market-intelligence screen showing how fair value is built, close-forecast coverage, the fee model, and how ready each sport is.
The market view — how the system builds its fair value, its accuracy tracking, and how much data each sport has to work with.

Engineering highlights

Most of the work is infrastructure. These are the parts that took real engineering, and the skills they map to:

  • Real-time data pipeline. Collects and stores millions of price updates from ~30 sources, keeping only actual changes so the full history stays compact and can be replayed exactly.
  • Statistical validation. Every proposed change is tested on data it wasn’t built on, and against a luck baseline, before it’s allowed to affect real money. This has repeatedly killed my own ideas that only looked good in hindsight.
  • Automated testing. 335 checks run before any deploy. They confirm the system behaves correctly and that removed features stay removed, so nothing quietly creeps back.
  • Safe execution. Bets are placed with exact fee accounting and reconciled against the account every night. Any unexplained gap halts trading automatically until I review it.
  • Fail-safe by default. Missing, stale, or inconsistent data blocks a decision rather than triggering a guess.
7.8M
Market price updates stored
1.7 GB
Replayable market database
115
Versions shipped

The control room

The React control room is the cockpit. It shows every game the system is watching, a live market feed, a performance page, and the safety switches that decide whether it can place real bets. There’s also a chat panel where I can ask the system, in plain English, why it did or didn’t bet a game and get the real reasoning back — which turned out to be the fastest way to audit a decision.

THE BRAIN settings screen with the safety switches: the live-bet toggle, bet size, per-sport coverage, and system status.
Settings — the safety switches. None of them can override a test or let the system bet without a clear all-clear.
THE BRAIN chat panel — a plain-English console for asking about a game, the board, or the system's reasoning.
Chat — ask about any game or the day’s picks in plain English, or tell it to re-check a game.

Built with AI tools

This project is where my interest in AI reliability became a real tool instead of a study. I worked as the architect: I decided what to build, defined how it should behave, and wrote the tests. Claude Code did most of the implementation inside the codebase and ran the test suite. ChatGPT was a thinking partner for the design and the math.

What stayed with me is the judgment — the overall design, every decision about risking money, and the discipline to throw out my own ideas when the data proved them wrong.

An AI can write a betting script in an afternoon. What it won’t do on its own is tell you your results are overstated, build the test to prove it, and then delete the flattering number. Directing that loop — decide, build, test, and stay honest — is the real work. The AI made it possible to build at this scale as one person; it didn’t decide what was worth building or whether it was true.

How it evolved

I built THE BRAIN across 115 versions. Each one was an experiment that either survived contact with reality or got cut. The through-line is a steady move from “trust my model” to “trust the measured market, and prove everything.”

The foundation

A basic model-vs-market bet with a permanent decision log and strict “stop if the data is bad” rules.

Market-as-truth

The market became the anchor instead of my model, after I proved the model lost money on its own.

The validation harness

A proper testing and validation layer that any new rule has to pass before it can risk money.

The current system (live)

One clear, validated betting rule, plus a deeper market-reading engine that feeds the next one.

Honest about results

The engineering I’m confident in. The profits I’m careful about, on purpose.

The record looks strong, but most of it comes from replaying the strategy on past data, which is not a promise about the future. The real-money sample is small, the stake is tiny by design, and one sport (baseball) does most of the work right now. The control room shows these limits plainly — real bets and backtested ones are always labeled separately — because a system that flatters its own record is worse than useless.

THE BRAIN performance view showing the record split into real bets and backtested bets, an equity curve, and a per-market breakdown.
The performance view — the record is broken out into real and backtested bets, never blended, alongside the equity curve.

The point of the project was never the betting. It’s the engineering around it: a real-time data system, careful statistical testing, honest record-keeping, and a workflow that gets the most out of AI coding tools.

Stack & skills

PythonReact / JSXSystem ArchitectureReal-Time Data Pipelines Data ModelingStatistical ValidationBacktestingAutomated Testing REST API IntegrationSQLiteTime-Series DataMonte-Carlo Simulation Fail-Safe DesignData IntegrityAI-Assisted DevelopmentClaude Code Prompt EngineeringTechnical Writing