Swing trading, weeks to months
Not day trading. Positions are held as long as the thesis holds.

An autonomous research agent for a weekly swing-trading portfolio
Otis is an AI agent I built with Claude Code that manages a dedicated, higher-risk growth brokerage account. Every Monday it pulls live market data, re-underwrites every position, screens for new ideas, decides what to buy, trim or sell, and writes up its reasoning. I review its orders and place them.
Confirms it's running on the right model and the right account, and checks that it hasn't already run today, so a duplicate scheduler fire can't double-trade.
Loads a compact standing-decisions file (mandate, rules, open questions), then the running decision log.
Quotes, fundamentals, price history, earnings results and 8 quarters of financials from the brokerage's agent tools, plus web research on why each name moved.
Compares the portfolio against SPY and QQQ on identical cash flows, so it can't fool itself about whether it's adding value.
Each name gets a verdict (passes / fails / on watch), a conviction tier, and a pre-registered, falsifiable prediction with a confidence level.
Runs saved stock screens to find candidates outside famous mega-caps, and re-checks every previously rejected name against an explicit re-entry condition.
Concentration by theme and by correlated risk factor, upcoming earnings, and macro events (Fed, CPI, jobs).
Concentrates new money into the top ideas, applies sell discipline, and pre-checks every order for real-time pricing and alerts.
Writes each order to an orders file with its rationale and sends me one push notification. I place the trades.
Appends a full dated entry to the decision log and updates the standing-state file.
Not day trading. Positions are held as long as the thesis holds.
A stock has to show a real earnings and margin trend at a reasonable valuation. Hype names whose story outruns the numbers get rejected, even when they're still beating earnings.
Ten growth stocks in ten ‘different’ sectors can still be one bet. Otis tracks which holdings share the same underlying risk (rates, inflation, AI-capex sentiment) and favors additions that would benefit from the scenario that hurts the rest of the book, like energy, rate-sensitive financials, defense and international exposure.
Each week's new money goes into the top 2–4 ideas instead of being spread thin across everything. ‘No add’ is the normal outcome for most holdings in a given week.
Five thesis-based triggers: thesis broken, valuation ran past the entry logic, position outgrew its target weight, a better idea needs the capital, or three straight weeks of flags with no fundamental improvement. Price drops alone never trigger a sale. Max 1–2 sell actions a week.
When two choices are equally good on the merits, it prefers the one that avoids unnecessary short-term gains. Taxes never override a growth decision.
Only spend cash that has already settled. Never count same-day sale proceeds.
Never hardcode a dollar range as a reason to abort. Size by target weight against live buying power.
Place orders one at a time.
Full financials are required before any new buy or meaningful add.
No structural strategy changes during a drawdown, and none during a hot streak either.
Trust broker data over press reports when they conflict.
Don't buy right before an earnings report. Wait for the print.
Check for a duplicate run before doing anything.
Every exit test has to be stated in unambiguous, measurable terms ahead of time.
Jun 2026
Strategy drafted in a chat with Claude, then handed to a Claude Code agent that re-underwrote it and placed the first allocation.
Jul 2026
Fixed a settlement bug (it tried to spend sale proceeds that hadn't settled yet) and a false abort caused by a stale hardcoded cash range. Moved to fully autonomous execution and widened the search beyond the original five themes.
Aug 2026
Big methodology upgrade: sell discipline, conviction sizing, mandatory financials, systematic screening, correlation-based diversification and pre-registered predictions. Added the hard model gate after finding runs silently starting on a smaller model.
Sep 2026
Compacted the memory into a standing-decisions file, added always-on benchmarking against SPY/QQQ, and moved back to ‘Otis proposes, I place’: the agent queues orders and I execute them.
Oct 2026
Tightened how exit tests are written so they can't be read two ways, and clarified the account's mandate as long-horizon growth capital.
A performance deep-dive during a drawdown produced five recommendations, and four were withdrawn two weeks later when the market reversed. Now there's a standing rule against it.
The biggest early winner was one the process had deliberately kept small. Short windows don't prove skill in either direction.
Many international stocks don't return full financials through the tools, so the agent can't verify them, and international exposure had to come through a broad index ETF instead.
The decision log matters more than any single trade. It's what lets a stateless agent act consistently week after week.
Fully autonomous execution worked, but a human placing the final click is a cheap, sensible checkpoint for real money.
Otis is a personal experiment in agentic AI, not investment advice. Performance figures are intentionally not shared.
Back to projects