0:35Transcript
Copy My Exact AI Trading Setup (Just a Laptop and Internet)
The exact AI trading setup behind my $26K Robinhood account: NexusTrade MCP + an agentic coding tool + my Public Portfolio Challenge repo. Just a laptop and internet.
NEXUSTRADE / VIDEOS
AI trading videos
Shorts I filmed while building NexusTrade.
Every video has a transcript.
152 shorts · every one transcribed
Algorithmic trading videos
Start watching ↗0:35Transcript
0:14Transcript
AI Data Cleaning: From SEC Filings to Checked Trading Data
See how an LLM, SEC filing retrieval and repair code work together to clean trading data, check results and retry in an agentic workflow before backtesting.
1:04Transcript
Claude Trading Strategies: I Tested SPY Timing Against Buy-and-Hold
Connect Claude to NexusTrade with MCP and compare an SPY 200-day moving-average backtest with buy-and-hold, including returns, drawdown and strategy rules.
1:51Transcript
NexusTrade: Claude Code for Financial Markets
Austin explains the language-model and tool-harness pattern behind an AI agent, then describes the research, stock-screening, backtesting, watchlist and de
2:17Transcript
AI High-Frequency Trading? This 100ms Claim Doesn’t Hold Up
Austin Starks fact-checks Ray Fu’s Jev AI trading pitch, challenging its 100ms HFT claim and asking for out-of-sample tests and evidence of better results.
1:25Transcript
Create a Trading Strategy with Cursor. Then Deploy It to Alpaca.
Create a trading strategy in Cursor and deploy it to Alpaca through the NexusTrade MCP. The $13,805 book on screen is his existing Alpaca account.
1:17Transcript
Congressional Trading Disclosures. Two Free Repos to Research Them.
Download public congressional trading disclosures and test ideas with a free Python SDK. Filings are delayed, so use the public disclosure date.
1:39Transcript
How My AI Trading Bot Decides What to Buy and Sell
The three steps an AI trading agent takes to pick trades: writing a deterministic rule, walk-forward testing it over four folds, and deploying it to paper or live.
1:22Transcript
Claude Code Trading Strategy: 1,100% in 11 Years, and a 59% Drawdown
One command connected Claude Code to my backtest data. The rule it kept turned $10,000 into $119,942 over 11 years, with a 59% worst drawdown.
1:41Transcript
I fact-checked a day trading strategy with 423,000 views. It loses to doing nothing.
A day trading strategy with 423,900 views, coded by an AI agent and backtested on a year of minute data. Tuned and charged zero fees, it still lost 2.40% out of sample while the index gained 1.02%.
1:26Transcript
Why Is My Backtest So Slow? GPT-6 Astra Cut Mine to 51 Seconds.
My backtests took ten minutes. GPT-6 Astra profiled the Rust engine, cited a 2014 paper, and got the run down to 51 seconds on hardware I already owned.
1:24Transcript
Every Rule My AI Trading Bot Follows Is Public. So Is the 12% Crash.
Every rule, backtest, crash and bug behind my $25,000 AI trading account is public. Here is what the live book actually did.
0:28Transcript
An AI Evaluation of NexusTrade
An AI evaluation of the NexusTrade landing page and its engineering. This is what the model said when it looked at the app.
0:28Transcript
What AI Thinks of NexusTrade in an Incognito Tab
I open an incognito tab and ask AI about NexusTrade to see how it describes the app. Here is one of those evaluations.
0:29Transcript
Aurora: AI Over a Trading Research Toolchain
Aurora uses an LLM as an interface over a trading research toolchain: research, strategy generation, backtesting, optimization and deployment. This article explains the architecture behind my public trading experiment.
0:56Transcript
Codex Does the Heavy Lifting With NexusTrade
Codex does the heavy lifting with NexusTrade: research, strategy rules, backtests, and paper trading. Give it a goal and inspect the results. nexustrade.io
0:57Transcript
Claude Does the Heavy Lifting With NexusTrade
Claude does the heavy lifting with NexusTrade: research, strategy rules, backtests, and paper trading. Give it a goal and inspect the results. nexustrade.io
0:43Transcript
10 GitHub Repos for Your Quant Toolkit
10 GitHub repos to build your quant toolkit: indicators, market data, backtesting, machine learning, and derivatives.
0:28Transcript
My $25,000 Public AI Trading Experiment
I put $25,000 into a public AI trading experiment. Real fills, real portfolio history, and every trade you can inspect.
2:57Transcript
Why Trading Strategies Fail: You Shipped Version One
Learn why trading strategies fail after a great backtest, and how strategy variants, market regimes, and unseen-data validation improve your research process.
3:55Transcript
Trading System Design: APIs, Queues, and Workers
Part 2 separates a trading application into stateless APIs, queues, and workers. Austin explains why backtests and live trading need different resources,…
4:54Transcript
Trading System Design: Scaling Backtests and Live Trading
Part 3 covers scaling heterogeneous backtest workloads and live trading. Austin discusses worker pools, shared market data in object storage, user…
2:48Transcript
Trading System Design: Junior Engineer Architecture
Part 1 of Austin’s trading system design series starts with a single-process application. It covers persistent order intent, stable order IDs, an…
0:45Transcript
Claude Haiku 5.5 Cost Me 13x More Than Muse Spark
A real-world cost test of Claude Haiku 5.5 against Meta's Muse Spark on an AI trading agent's long prompts: 13x the cost, much faster, one win.