Can an AI agent beat Kalshi's 15-minute silver market?

From a rule to a record

A backtest of a silver rule tells you what it would have done against prices already known. This page wants the other thing: how the reversal idea fares against the KXSILVER15M book as it stands, at :01 and :31 past each hour from 9 AM to 5 PM Eastern, Monday to Friday, filled at the ask, charged Kalshi's fee (about 1.7¢ a contract at 48¢), and settled when Pyth - Silver says so. So the Silver agent runs on Windmill like any user's agent, and each bet it places on KXSILVER15M is written here as it settles, wins and losses alike.

How the agent works

The agent is the rule below in plain English, on Claude Haiku 5.5, scheduled twice an hour from 9 AM to 5 PM Eastern, Monday to Friday. It builds its record in four steps.

1. Read the window that just opened

At :01 and :31 past each hour from 9 AM to 5 PM Eastern, Monday to Friday, it reads the KXSILVER15M window that just opened, with the live bid and ask on each side and the minute candles since it opened. Kalshi lists a new KXSILVER15M window every fifteen minutes, and settled 76.9 a day over the last seven complete days. No silver price feed is among its tools: Kalshi's own book is what it reads, and Pyth - Silver is what settles the window.

2. Filter for the setup

It places nothing unless one of these holds:

• if the window that just settled resolved YES and the ask is 40–55¢: buy 5 NO at the NO ask
• if it resolved NO and the ask is 40–55¢: buy 5 YES at the YES ask

Why this setup: Each window's target is the previous window's settlement, one Pyth candle close, so a stray print at that close moves two windows in opposite directions; the rule bets the new window reverses the last one, and only near even money.

3. Size and place

It buys 5 contracts of the side its branch names, at that side's ask, on paper against the live KXSILVER15M book: a paper order fills only against what the book shows at that price. At about 48¢ a contract, Kalshi's taker fee at KXSILVER15M's settings (fee type "quadratic", multiplier 1) is about 1.7¢. So the five contracts cost about $2.49 all in, and pay $5.00 if they win.

4. Hold to settlement and record it

Every silver position is held until its KXSILVER15M window closes, at most fifteen minutes after the order, and Kalshi settles it on Pyth - Silver; nothing is carried past 5 PM Eastern. The price paid, the fee, the result and the net go into the record below as each bet settles. Most of the 16 runs a day end with no order, and the agent's log keeps those too.

The record: October 30, 2026

The agent started October 28, 2026. Nine bets have settled since, all on October 29, 2026: won 6, lost 3.

The nine settled bets, newest first:

Nine settled bets is a start, not a result; nothing is read into the record before thirty.

It runs this page's starter rule, word for word:

“At :01 and :31 past each hour from 9 AM to 5 PM Eastern, Monday to Friday, on the KXSILVER15M window that just opened: if the window that just settled resolved YES, buy 5 NO at the NO ask when it is 40–55¢; if it resolved NO, buy 5 YES at the YES ask when it is 40–55¢. Otherwise no order. Hold to settlement.”

Run this rule as a Windmill agent

The market the rule is betting into

Over the last 1,000 settled windows, from Oct 14, 2026 to Oct 29, 2026, silver closed at or above its start 473 times and below it 527. The longest run was seven NO windows in a row. The median move from start to close was 0.12% of price. Volume ran at a median of 4.5 million contracts a day; the thinnest hours, by a median window's contracts, close at 5 AM, 6 AM and 7 AM Eastern.

The number that matters most for any rule that buys the favorite is whether the favorite pays for itself. For each of the last 200 windows up to Oct 29, 2026 we read Kalshi's quote 5 minutes before the close and took the favorite, the side priced above 50¢, at its ask; 200 had a quote on both sides, and the favorite won 165 of them. Breakeven is the price plus Kalshi's taker fee, as a share of the $1 a winning contract pays.

Three notes on that table. The 60–69¢ band has the widest gap between win rate and breakeven, 71% against 65.8%, and at 28 windows its interval runs from 53% to 85%, which includes breakeven. Two of the five bands fell short of breakeven, the 80–89¢ band by the most: 79% against 85.7%. And every band's interval includes breakeven, which is why the last column reads the same five times. In our read of Kalshi's prices, the silver favorite 5 minutes before the close is priced about right. Nothing on this page says a buyer of the favorite has an edge.

The rule under test pays 40–55¢ a contract, which puts it in the 50–59¢ row: there the favorite won 9 of 18 windows, against a breakeven of 56.3%. The rule's own conditions are what the record above tests; these rows are only the market's baseline at its price.

Kalshi's rules, in Kalshi's words

This is the rule of the market that was open (KXSILVER15M-26OCT292345-45) when we read Kalshi's API on October 30, 2026, quoted from Kalshi; the series and its full rules are on Kalshi's site. The times and the target change with every market:

“If the close price of the 1-minute candlestick for Silver on Oct 29, 2026 at 11:45 PM EDT is at least 51.523 USD/|| Unit ||, then the market resolves to Yes.”

The series names Pyth - Silver as its settlement source. Kalshi lists the series with the fee type "quadratic" at a multiplier of 1: a taker pays 1.8¢ a contract at 50¢ before rounding, less toward either end, and a resting order that fills later pays nothing. The fee calculator works out the fee and the breakeven for any price.

A silver window's rules state its target as a number, for example "at least 54.207 USD" for the window that closed at 11:30 PM EDT on October 27, 2026, and settle on the close of Pyth's 1-minute silver candle at the window's end, rounded to 3 decimal places. (Kalshi's API, the series' settled markets, checked October 28, 2026.)

What success looks like

A positive net per contract after Kalshi's fees over thirty settled bets, with the confidence interval clear of zero, would be a result.

A rule that only matches its price is not one. A contract bought near 48¢ that wins as often as that price says, 48 times in a hundred, loses about 1.7¢ a contract to the fee alone, so the line to beat on KXSILVER15M is a win rate of about 49.7%, not 48%. Each win at that price nets about 50.3¢ a contract after the fee and each loss costs 49.7¢, so one win covers 1.0 losses.

At most 16 KXSILVER15M runs a day, Monday to Friday, means thirty settled bets take at least two days, and longer when the setup is rare. If the record climbs, the reversal idea holds at these prices. If it falls, the idea goes, and the record stays on this page.

Follow along

• This page refreshes every hour from Kalshi's settled data and the agent's own log.
• Copy the Silver agent: the button below opens the builder with this KXSILVER15M rule, to run as written on paper under your own account, or with your own numbers in place of 40–55¢.
• The fee calculator shows the fee and the breakeven at any price on KXSILVER15M.
• The 90-strategy test is the longer version of this exercise: about 90 rules and 4,200 paper bets across ten days.
• The Kalshi markets hub lists the other 15-minute markets and every other market page.

Run this rule as a Windmill agent

Questions

What does Kalshi's 15-minute silver market settle on?

On Pyth - Silver: the rules quoted on this page, read on October 30, 2026, compare the price at the end of the window with the price at its start, and a tie resolves Yes.

What is the fee at 50¢?

A taker pays 1.8¢ a contract before rounding at 50¢ on this series (fee type "quadratic", multiplier 1), less toward either end. The fee calculator gives the fee and breakeven at any price.

Is a bot here profitable?

Nothing on this page says so. The favorite 5 minutes before the close won 165 of 200 windows in our read of Kalshi's prices, and the table shows each price band against its breakeven: 5 of its 5 bands are inside noise. Run your own rule on paper to see what it does, before you risk money.

Paper or live?

Agents trade on paper unless you build them live. Paper orders fill against Kalshi's live order book with Kalshi's fees and settle when the real market settles. To trade real money, connect your own Kalshi API key and build a live agent; your money stays on your Kalshi account.