Problem: post-earnings emotion will overrule any plan you didn't write down first. Fix: an AI earnings pre-trade prompt that forces you to commit your trim, add, and hold triggers before the call. Payoff: a numbered playbook you read off the screen at 9.30am instead of improvising into a stock that opened down 7%.
// On this page
I held META into Q1 2026 earnings on 2026-04-30. I did not have a written trim trigger. Revenue came in at $56.3bn consolidated, up 33% year on year — strong. Full-year capex guidance came in at $125–145bn against FactSet consensus around $122.6bn going in. The top of the band was the surprise, not the raise itself. The stock fell roughly 8% in the session. I sat through it and made no decision, which is the same as deciding to hold — but harder on the nerves.
If I had run this AI earnings pre-trade prompt the morning before, I would have written the trim trigger down. The cost of not pre-committing was 8%.
The argument
Going into Q1 2026 I had a thesis on META but no written trim trigger. That gap is the problem this prompt solves. An AI earnings pre-trade prompt is one you run the morning before a company reports. It forces you to commit your trim, add, and hold triggers in writing — before management speaks. The model lists specific conditions back to you from the inputs you give it. You sign off on the list. When the call ends, you act on what you wrote, not on the first move the stock makes.
Three posts on this site already cover what to do with AI after a company reports — the 5 prompts for earnings call analysis, the tool comparison, the questions to ask AI before buying any stock. All useful. All reactive. None of them covers the harder discipline: deciding what would make you change your mind before a company reports — so when management speaks, you act on a written plan, not a gut response.
Most “AI for earnings” content is reactive. You ask the model what to think after the news lands. The prompt worth running the morning before is the one that forces you to commit your trim, add, and hold triggers before you know what management will say.
AI is bad at predicting what management will say. It is good at listing your decision triggers back to you.
This prompt keeps AI in the lane it’s good at.
It follows the same shape as the rest of the Prompt Stack — ROLE, FILTER, RISK, VERDICT. The placeholders in square brackets are yours to fill in.
The pre-trade earnings prompt
ROLE: Act as a sceptical analyst preparing me for [COMPANY NAME]‘s [QUARTER] results, which report [DATE / TIME]. I hold this position and I have not yet decided what would change my mind. Your job is not to predict the announcement. Your job is to make me commit, in writing, to what I will do based on what management says.
FILTER: Here is the position I hold and the thesis underneath it.
- Position: [LONG / SHORT / OPTIONS — be specific], entered [DATE], cost basis [LEVEL], current price [LEVEL].
- Thesis (one sentence): [why I own this; what I think the market is missing or pricing wrong].
- The line item that matters most: [REVENUE / MARGIN / CAPEX / SUBSCRIBER GROWTH / GUIDANCE — pick one].
Here is the consensus picture going into this release:
- Consensus revenue [PERIOD]: [VALUE]
- Consensus margin: [VALUE]%
- Consensus on the key line: [VALUE]
- Consensus guidance midpoint: [VALUE] Source: [BLOOMBERG / VISIBLE ALPHA / FACTSET / IBES] as of [DATE].
Now produce three lists. Be specific. No “depends on context” hedges. Every entry must reference a number, a phrase, or a named topic.
LIST A — TRIM TRIGGERS: what would management have to say, guide to, or fail to address in the prepared remarks for me to trim this position the same day. Aim for three to five specific triggers. Each one must be observable on the call — not a derivative read from outside reporting.
LIST B — ADD TRIGGERS: what would management have to say or guide to for me to add to this position, knowing the stock will probably move in the opposite direction first on a performative-bear release. Three triggers max.
LIST C — HOLD-AND-WAIT TRIGGERS: what would land in a grey zone where I should neither trim nor add, but mark the position for a re-read in two weeks once the analyst day or follow-up filing lands.
RISK: Identify the single trigger across the three lists that is most likely to fire on this release and that I am most likely to talk myself out of acting on. Name the trigger and one sentence on why I will rationalise around it if I don’t pre-commit.
VERDICT: Restate, in one paragraph, the trim / add / hold triggers as a numbered playbook I can read off the screen after the call. End with one sentence on the magnitude — how much would I trim, how much would I add, expressed as a fraction of the current position, not a number of shares.
The FILTER forces you to type cost basis, thesis, and consensus numbers into the prompt. You can’t dodge writing them down — that’s the pre-commit move. The VERDICT closes with size as a fraction of the position. Not “trim some” but “trim a quarter.” Without that, the playbook is conditions, not actions.
The friction is the value. When I drafted the worked example below, the FILTER section took the most time — picking the single line item that matters most, writing the consensus number rather than gesturing at it. If the prompt feels easy to fill in, the inputs are too vague to commit to.
What it would have looked like on META Q1 2026
Here is what the FILTER section would have looked like the morning of 2026-04-30, pasted as I would have written it:
- Position: Long META, held into Q1 2026 results, current price ~$760 going in.
- Thesis: META is investing through an AI capex cycle the market is undervaluing on a free-cash-flow basis; ad revenue growth is durable.
- The line item that matters most: Capex guidance for the full year. Revenue is well-modelled; margin is well-modelled; capex is the variable that determines whether the FCF trajectory holds.
- Consensus picture going in: Revenue Q1 ~$55.5bn (FactSet), FY26 capex ~$122.6bn (FactSet).
If I had run the prompt with those inputs, the three lists the model would have produced look like this. None of these triggers are clever. That’s the point. The pre-commit move only works if the triggers are obvious enough that I can’t pretend later I didn’t mean them.
LIST A — TRIM TRIGGERS. (1) Capex guidance above $130bn for FY26 with no payback timeline mentioned. (2) Capex revision pinned on “component cost inflation” with no commentary on procurement or supplier diversification. (3) AI return language framed as “ongoing investment” rather than “expected to contribute by [period].” (4) Cost-discipline language (“Year of Efficiency”, “operational discipline”) absent from the prepared remarks.
LIST B — ADD TRIGGERS. (1) Capex guidance held at or below $125bn AND ad revenue +30% YoY or better. (2) Specific commitment to a payback period on the AI infrastructure spend. (3) Reels or Threads monetisation metric disclosed for the first time, with a number.
LIST C — HOLD-AND-WAIT TRIGGERS. (1) Capex guidance band wide (top end above $135bn, bottom end below $128bn) — wait for the analyst day to narrow. (2) Margin commentary defers to “investment phase” language without a specific year for normalisation.
What happened on the call: capex band $125–145bn for the full year, top end well above the trim trigger, payback timeline absent, AI return language framed as “investment in AI capability” (per the prepared remarks), “Year of Efficiency” register absent. All four Trim Triggers fired. The stock fell roughly 8% in the session.
With the prompt, the trim was a written commitment honoured or not. Without it, the trim was an emotional call at 9.30am with a stock already moving against me.
I did not trim. The triggers had not been written down, so the call became “is this bad enough to act on yet” rather than “the triggers fired, do what you said you would.” Those are different conversations.
The first one your future self loses every time.
Where the prompt falls short
This is one prompt, not a system. Five caveats worth naming up front.
Consensus numbers go stale fast. If you paste a FactSet snapshot from a week before and the consensus has moved since — analyst revisions, a competitor’s report, a macro data point — your triggers are calibrated to the wrong baseline. Re-pull on the morning. If the consensus you paste is wrong, the triggers fire on noise.
The model will assume position size when you don’t give it one. Be explicit that you’re not pasting share count or P&L. The size in the VERDICT is a fraction of the current position, never an absolute number. If you let the model assume “you hold 300 shares” because you didn’t tell it otherwise, you’ll get an answer calibrated to a portfolio that isn’t yours.
AI invents details when it doesn’t have them. If you don’t supply the consensus picture, the model will reach for something like “consensus expects revenue around $50bn” and the number may be roughly right or roughly wrong. The whole prompt is calibrated to the inputs you paste — paste real numbers or don’t run it. I keep a running lessons log of the specific things AI tools have invented on me. The pattern is always the same: confident output where the inputs were thin. Thin inputs mean the model fills the gap with something that sounds right.
It doesn’t help with non-standard reporting cadences. Companies that don’t report quarterly need the same discipline applied to the closest equivalent — an interim filing, a board update, a CEO’s public commentary. I sell covered calls on BMNR, an ETH treasury company that updates the market via interim filings and Tom Lee’s public commentary. I run the same pre-commit move informally on what Lee says. The prompt structure transfers; the “earnings call” framing doesn’t.
It is not a forecast. A model that says “this trigger is most likely to fire” is pattern-matching against your inputs. It isn’t predicting what management will say. The RISK output flags the trigger you’re most likely to talk yourself out of — not a prediction of what’s coming. It reads as a checklist item for after the call, not a hint at what’s coming.
What I run on results morning
The pre-trade prompt is half the sequence. The other half runs once the company has reported. The 5 prompts for earnings call analysis cover the language read — I use the same trim-trigger framing on Apple, where the services language has drifted from absolute growth numbers to softer quality phrasing over the last four quarters. A pre-committed services trigger catches that kind of drift. The tools comparison sorts which model handles which step. Full sequence: pre-commit the morning before → read the language after → trade against the written triggers.
What worked
Writing the trim trigger down before the call meant I had a rule to follow on the day, not a feeling to talk myself out of.
What didn't
AI can't tell you what management will say. It turns your inputs into a checklist, nothing more. If it picks "this one is most likely to fire," that's a flag, not a forecast.
Bottom line
Useful. Run the morning before earnings on a position you hold. Stops working when you can't get clean consensus numbers.
The prompt is the discipline; the model is the second pair of eyes. Pre-committing the triggers is the move that matters — running them through an AI is what makes you type them out. The Field Guide is the underlying methodology in one PDF. The lessons log is the running record of where I’ve watched AI tools invent the answer.
Ben documents AI experiments against his own investment portfolio — real money, human analysis, sceptical use. About Ben →