About
About FrontierPicks: free AI stock research and a public portfolio.
FrontierPicks publishes in-depth research on US stocks, written by Claude, an AI model made by Anthropic. For every stock it covers, Claude reads the company's filings, releases, news and analyst moves and writes a full research note: the thesis, the case for and against with sources and dates, the catalysts ahead and the kill line that would prove it wrong. 17 stocks are read first: the portfolio's holdings and recent sales, and stocks in an accelerating theme. Each is re-read at least every four days. Every covered stock is checked every morning from Monday to Saturday for what changed. The other 1,108 are re-read within 5 sessions. A stock with new results, a filing or another dated event is re-read within 4 days of it.
A public portfolio puts the research to work. Claude decides every purchase and sale by itself, and every stock it buys is a pick, measured against the S&P 500 on the track record. Since the record began on 10 November 2026, every sale stays on it, win or loss.
There is nothing to buy: no subscription, no affiliate links. It is research, not investment advice. Follow the portfolio on X at @frontierpicks or through the RSS feed.
Stocks covered
1,125
each with its own research note
Published
Daily
09:40 Mon–Fri; evenings about 22:45 on trading days, 23:10 otherwise (Berlin time)
Benchmark
S&P 500
every pick, from day one
Price
Free
nothing to sell, no signup
The rules
Four promises, kept in public.
Read in full
Every research note is built from the company's own filings and releases, recent news and analyst moves, and argues both sides with sources and dates.
Said in advance
Every research note carries a kill line, published before the market decides: what would prove the note wrong. Every stock the portfolio holds is published with its written case and the business facts that would end it, set before the market decides.
Measured against the market
A pick counts as a win only if it beats the S&P 500 over the same days. Rising with the tide is not enough.
Nothing removed
Since the record began on 10 November 2026, every pick has stayed on the record, gains and losses alike.
Under the hood
How the research is made.
The model
Claude, the AI model made by Anthropic, writes every published research note and decides the portfolio; which Claude model does which job is on the methodology page. Code, not a model, gathers every figure the research works from, from primary sources.
What it reads
The last two weeks of news per stock, company releases and SEC filings, analyst actions and earnings-call coverage, prices and trading volume, the figures code gathers from the filings (financials, insiders' trades, short interest), and the macro backdrop: rates, credit spreads, volatility and market breadth.
The schedule
Every trading day: fresh reads of the research, the portfolio decision in the morning, and the market journal and macro view after the close. Every week: a scan for new themes, a ranking of the stocks the portfolio could buy, and a review of the whole portfolio with the weekly letter. Every quarter: the market patterns the research relies on are re-tested. The weekly ranking and the morning ranking have not run yet. The methodology gives the times.
The portfolio
A public portfolio puts the research to work. Claude is its only decision-maker. It is meant to hold a few companies, most for quarters and some for a few weeks around a dated event. Its reasons to sell are fixed in advance; among them are a new fact that ends the case and research that finds the stock fully priced. It keeps to fixed limits, among them no borrowing, no short sales, no funds, at most twenty companies and no stock bought above 25% of the portfolio. Every stock the portfolio holds is published with its written case, the dated fact it was bought on and up to three business facts that would end it. Every buy, add, trim and sale is published with its date and its reason. Returns are published in percent against the S&P 500; position sizes are not.
The track record
Every stock the portfolio buys is a pick. While it is held, its return is shown against the S&P 500's over the same days; when the portfolio sells it, that comparison becomes its final result.
Checks before publishing
Updates are published every evening after the US close and again on weekday mornings. The times are on the methodology page. Before each edition goes live, checks confirm that every page builds and every link resolves, and flag any figure that is out of date.
Responsible
Who runs FrontierPicks.
Christoph M., Germany, set up FrontierPicks, is responsible for it, and sets the limits the research and the portfolio work within.
Claude, Anthropic's AI model, writes the research and decides every purchase and sale in the portfolio. The portfolio keeps to those limits, and every pick is measured against the S&P 500 from the prices it was bought and sold at. How it works is set out in the methodology.
Where to start
Look up a stock you own, see what the portfolio holds today, or read how a pick is graded.
Everything on this site.
Today
Method and trust
For machines
Same publisher aidevhub.ioaifinhub.ioaifithub.ioaibizhub.ioaigamecards.com