AI covered calls: when NOT to sell another one

A covered call is a trade you can run on a stock you already own: you agree to sell your shares at a set price, and you get paid a small fee, the premium, for the promise. The catch is what happens after one closes. My trade #6 on BMNR closed on 13 May for +$375 in nine days: sold the promise for $2.25, bought it back for $1.00, a clean win. The app pings. I’m holding the shares again. The screen of prices I could sell against is right there.

The instinct is to do it again straight away. The win felt good, and the same trade is sitting there at roughly the same price. Why wouldn’t you?

Because more often than not, it’s the wrong move, and an AI is good at telling you so. Not because it knows something you don’t: it can’t see live prices, and any prompt that pretends otherwise just makes things up. It’s good because it makes you answer five questions, in the same order, before you click. That’s the whole job here. Five checks, six real trades, one lesson that keeps proving itself: selling another call isn’t the default.

Should you sell another covered call straight after closing one? Usually not. Before you open the broker’s list of strikes and prices, the same AI prompt runs five checks: where the stock sits against what you paid, whether a price-moving event is near, why the last trade closed, whether the premium is worth taking now, and whether a clean win is a reason to pause rather than repeat. Any one of them can say wait, even when the trade looks fine.

Why the urge is the problem

The money is the trap. Every win pulls you straight back in: nine days, +$375, do it again. That maths is what makes the strategy work, and what gets people into trouble. The good trades are easy. The bad ones are the trades you take because the last one paid.

The bad trades aren't the ones where the rules say sell and it goes sideways. They're the ones where the rules say wait and you sold anyway, because the alert was loud and the chain was open.

So I run the same AI prompt every time I close a trade. It forces me to answer five questions before I do anything, in the same order, every time. That order is the Prompt Stack: fence it to what you give it and let it flag what it can’t verify, give it the facts, ask it where the risk is, get a one-line verdict. Left to itself, the urge skips straight to the prices. The prompt makes me stop.

Five conditions where the rules say WAIT

Each of these is a reason the prompt comes back with WAIT, even when the trade looks fine on the screen.

1. The stock is below your basis after a fall

“Basis” is just what the shares cost you, on average. My trade #5 closed in April for a thin +$18: the stock had crept up toward the $23 price I’d agreed to sell at, so I closed it early. The problem was where that left me: I’d been buying more on the way down, which pulled my real cost down to $18.99 a share (the headline figure was $22.11). Selling again at that $23 price would have locked the shares in just as the stock was about to climb back. The rule is to wait. When this was written, I was waiting for the stock to recover toward $22.50–$23.00 before even considering the next trade, a level it has since dropped well below, so that specific number now needs re-basing (see the dated note further down). The reason behind it doesn’t.

2. There’s a known event inside 14 days

If something in the next 14 days could jolt the stock (a company announcement, a move to a bigger stock exchange, results from a similar company), you’d be agreeing to a sale price right before the price might run. The fee looks fair when things are quiet and bad once they start moving. BMNR moved up to the main New York Stock Exchange on 9 April this year. Selling into that window was not the trade.

3. The last trade closed because the stock fell, not because it went well

There’s a difference between a trade that ended because it worked and one that ended because the stock dropped. If it’s the second, you’re now looking at a falling stock, and the temptation is to sell again straight away, because the agreed sale price looks “safer” further from the price. It isn’t. You’re selling into a stock that hasn’t shown it’s settled, for a smaller fee. After trade #5’s thin +$18 close, BMNR drifted lower for weeks. Selling again on the way down would have been the textbook version of this mistake. The fee is worth taking on a calm or rising day, not on the wreckage of a fall.

4. The fee is below this stock’s normal level

The size of the fee tracks how big a move the market expects. The jargon is “implied volatility”, but it just means the expected swing. BMNR’s has usually been high, around 75–85%, because the stock moves with the price of Ethereum. When that drops below its own normal range, the fee no longer pays you enough for the chance of having to hand the shares over. The prompt makes you look the number up and compare it, rather than trusting the price on the screen. It’s the check people skip most, because it takes one extra look.

5. You just closed a clean trade: wait for the next fresh setup

Two of my rules close a trade early: one takes the win once the fee has lost half its value (the 50% target), the other gets out once there are 21 days left before the agreed sale date (the time when the odds stop favouring you). The payoff comes from waiting for the next clean setup, not piling back into the same one. When both rules fire together, that’s the signal to step back. Trade #6 closed with 23 days left and both rules met. The right next move was to watch, not to sell again just because the alert was still flashing.

What you do once you’ve decided to wait

Once the prompt says wait, the job becomes watching rather than a one-off decision. I keep a short list of what would flip the answer: the stock recovering to a price I’d be happy to sell at, the fee spiking back up, the right sale date coming into range, and a sale price set a sensible distance above today’s (I aim for roughly the 30-delta strike: the level with about a one-in-three chance of the shares being called away). The exact numbers move with the stock; what stays fixed is that all four have to line up before I sell another call.

Update, 12 June 2026: The specific levels in my re-entry table when this was published (a $22.50–$23.00 price trigger, a July expiry, a roughly $26–$27 strike) were built around BMNR trading in an $18–$23 range. It has since fallen to the mid-$16s on ETH weakness, so those numbers are stale and the watch table needs re-basing before the next call is sold. The five conditions below are unchanged; only the levels they point at have moved.

I re-run the prompt weekly with fresh numbers. The answer flips from wait to sell when the conditions earn it, not when an alert pings. The prompt isn’t doing the thinking. It’s holding me to the order I check things in.

Where these five conditions fall short

The five checks stop you selling another call when you shouldn’t. They don’t find you the next trade. When I ran the prompt after closing trade #6, it said wait, and that was the whole of its value. It stopped me selling again; it didn’t hand me a new trade. It also assumes you’re feeding it honest numbers: the fee figure from your broker or a tool like Barchart, an events calendar you’ve actually checked, a cost figure that includes the fees you paid. Bad numbers in, confident wait out. (And it assumes this is still a stock you want to be doing this on at all: that earlier question is Prompt 1 of the entry-side post.)

The deepest limit is the one every prompt on this site comes back to: the AI can’t see live prices. It isn’t picking the trade, estimating fees, or working out the odds of having to sell. It’s checking that you followed your own rules, and what goes wrong when you ask it to do more is set out in AI for options trading: what it gets wrong. Give it numbers and it gives you a clear answer. Give it a question with no numbers and it gives you something that sounds right and isn’t.

Garbage in, confident WAIT out.

What would change my mind: a run of three or four “wait” calls that turned out to be obvious misses (a safe sale price, a steady fee, no events ahead, and the stock ran anyway). That would mean the rules are too tight for this stock, and I’d loosen them. Six trades in, the calls have held.

The urge after a win is to sell another call. The prompt is what makes that a decision instead of a reflex.

Every trade the prompt has run on (the price, the fee, how many days it ran, the return, and a tag for which version of the rule fired) is at /trades.