How to find tight price ranges with ChatGPT or Claude

A starting list for research. It does not recommend any trade.

Only NIQ matched at the Nov 5 close, and 90 stocks had less than a year of history to check. This strict test often finds just a few stocks; the variations below loosen it and returned 15 and 3 matches.

US stocks, ETFs and futures. The free plan runs 20 queries a day on daily bars; Pro adds intraday.

Paste these into the same chat, after the first answer, so your AI knows which results you mean.

• Chart these over the past six months with the 10-day high and low marked.

  Copy

• Any news or 8-K filings on these in the past month?

  Copy

• Any insider buying or selling in these over the past three months?

  Copy

• How did revenue change in their latest quarterly filings?

  Copy

A tight range forms when a stock's highs and lows stay close together for two weeks or more. This scan compares each stock's 10-session range with its own ranges over 60 sessions, so a normally jumpy stock and a normally calm one are judged fairly.

The rule Monk.trade uses: common stocks averaging at least $20M traded a day, checked on the last completed session. The 10-session range, from highest high to lowest low, must be at least 3.5% wide and the narrowest in 60 sessions, and the close must be within 5% of the 252-session high.

• 10-session range of 3.5% to 6% above a rising 50-day average

  “Using Monk.trade, check the last completed session for common stocks averaging at least $20M traded a day with a 10-session high-to-low range between 3.5% and 6%. Require the close to be above a 50-day SMA that is higher than 10 sessions earlier.”

  Open in ChatGPT ↗Open in Claude ↗

  MonkQL

  from stocks
  let rng = 100 * (highest(high, 10) / lowest(low, 10) - 1)
  include type == "common" and sma(close * volume, 20)[2] >= 20000000
  where rng[1] >= 3.5 and rng[1] <= 6 and close[1] > sma(close, 50)[1] and sma(close, 50)[1] > sma(close, 50)[11]
  show close[1] as prior_close, rng[1] as range_10d, sma(close, 50)[1] as sma_50
  sort rng[1] asc
  take 5
  

• 20-session range under 8% in $50M+ liquid stocks

  “Using Monk.trade, check the last completed session for common stocks averaging at least $50M traded a day with a 20-session range between 3.5% and 8%. Require the close to be within 5% of the 52-week high.”

  Open in ChatGPT ↗Open in Claude ↗

  MonkQL

  from stocks
  let rng = 100 * (highest(high, 20) / lowest(low, 20) - 1)
  include type == "common" and sma(close * volume, 20)[2] >= 50000000
  where rng[1] >= 3.5 and rng[1] <= 8 and close[1] >= 0.95 * highest(high, 252)[1]
  show close[1] as prior_close, rng[1] as range_20d, 100 * (close[1] / highest(high, 252)[1] - 1) as from_high
  sort rng[1] asc
  take 5
  

• Nothing on this page is a signal to buy or sell. Prices can keep moving against you, and you can lose money.
• The query reads the bar before the newest, which is the last completed session while the market is open. Before the open or after the close the newest bar is already complete, so the query reads the session before it. This example ran during the Nov 6 session and read Nov 5. Ask your AI to check the newest session instead.
• A cash buyout or tender offer can hold a stock just below the deal price near its 52-week high. Deals still awaiting approval can leave ranges above 3.5%. Check recent Form 8-K Item 1.01 and Schedule TO-T filings.
• A narrow range only says the stock has been calm. The price can break out in either direction.
• Stocks with fewer than 252 trading sessions lack a full 52-week comparison and are reported as undecided.
• Ranges can narrow before earnings or regulatory decisions, then jump past nearby prices when the news arrives.