How to Ask AI to Explain a Losing Trade
This prompt splits one losing trade into a thesis, slippage, a gap, fees and a rule you broke, and it ends with a single cheaper fix. No AI can predict markets. One loss does not prove the idea was wrong, and it does not prove you were unlucky.
How to use this prompt
- Fill in the prompt Replace every [BRACKET] in the loss review prompt with your own numbers. Leave a bracket blank only if you truly do not have that input.
- Run it in your AI Paste the plain prompt into any chat assistant. For the Moby version, use a supported host that is already connected with your Moby agent key.
- Check the answer against the checklist The parts have to add up to the total loss. The last line is one fix, and it has to be cheaper than hoping the next trade is different.
The prompt (any AI chat)
Paste planned prices and fill prices. If you paste the plan prices only, the slippage and the gap will come out as zero, which hides the loss.
Explain why this trade lost money. Split the loss into parts and show the math.
Planned entry: [PRICE] Actual fill: [PRICE]
Planned stop: [PRICE] Actual exit: [PRICE]
Size: $[SIZE] Fees: [RULE or AMOUNTS]
My reason for the trade: [THESIS]
Parts to check: wrong thesis, entry slippage, exit gap, fees, size larger than my rule, a rule I broke.
End with the single cheapest fix for next time. Do not tell me the market was rigged or that I was unlucky unless the numbers show it.
The same prompt through the Moby MCP
Your agent can list your live orders, and with a status filter, your filled and cancelled order history. The prompt uses a status filter so the fill prices come back with the order prices. It does not place a trade.
Supported hosts: Codex, Claude Code (CLI), Gemini CLI (with a paid Gemini API key or enterprise access) and Grok CLI.
ChatGPT: works on Business, Enterprise and Edu workspaces that allow custom MCP servers (web).
Use get_my_orders with a status filter for my last [TOKEN] trade. Show the order prices I set and the fill prices.
Then split the loss into: entry slippage, exit gap past my stop, fees, and price move to my stop.
Run get_token_trade_brief for the token now and tell me if anything in it was a warning I could have seen before buying. Do not trade.
Worked example
Example, not a recommendation. Illustrative output, not real market data. Why a planned $10 loss became $12.12.
Plan: buy $40 at $0.0100, stop at $0.0075, which is 25% lower, so the planned loss is $10.00 if you hold the full $40 down to the stop and pay no fee. Actual: the buy filled at $0.0103, which is 3% slippage, and paid a $0.90 buy fee because 0.75% of $40 is $0.30 and the minimum applies. Tokens are ($40 minus $0.90) divided by $0.0103, about 3,796.12 tokens. The stop triggered and filled at $0.0074. Gross proceeds are about $28.09. The sell is a stop-loss fill, so the fee is 0.75% of that gross, about $0.21, not the $0.90 minimum. Net proceeds are about $27.88. The loss is $40 minus $27.88, which is $12.12.
| Part | Dollars | What it is |
|---|---|---|
| Planned move to the stop | $10.00 | 25% of $40, if filled at $0.0075 with no fee and no slippage |
| Entry slippage | $0.87 | Filled at $0.0103 instead of $0.0100, valued at the planned stop |
| Entry fee, fewer tokens | $0.66 | The $0.90 buy fee means fewer tokens, valued at the planned stop |
| Exit gap | $0.38 | Filled at $0.0074 instead of $0.0075, on the tokens you actually hold |
| Exit fee | $0.21 | 0.75% of about $28.09, because a stop-loss fill is 0.75% |
| Total | $12.12 | The parts add up. About 32% of the $40 |
The cheapest fix: use a limit order for the entry on a thin token, and size the trade so the realistic loss, including slippage, a one-tick gap and fees, fits your rule. The planned $10 was the wrong number to compare with the rule. The $12.12 is the number that has to fit. A 0.75% swap fee (minimum $0.90 per swap), plus onchain fees. Limit, take-profit, stop-loss and DCA fills are 0.75%. Fees are computed with the published fee line. Check your own receipts.
If the thesis was wrong, the table will not show it. A wrong idea can lose money at the planned stop with almost no slippage. That loss would sit almost entirely in the first row. Split the loss before you blame the market.
A longer note on being the buyer who lets someone else exit is exit liquidity. Public warning checks are on rug check. Recompute the fees in the trading fee calculator.
How to get a better answer
- Give fill prices, not only the prices you intended.
- Include fees, or the unexplained gap will look like slippage.
- Write the thesis down before the trade so the review can test it.
- Ask for the single cheapest fix, and ignore a list of ten resolutions.
What this prompt cannot do
- It cannot tell a wrong thesis from an early thesis using one trade.
- It cannot recover funds.
- It cannot explain a rug beyond what onchain data shows.
FAQ
Why did I lose more than my stop loss?
Three common additions sit on top of the planned move: you paid more to get in, the exit filled past the stop, and fees came off both sides. The worked example splits a $10 planned loss into those parts and lands at $12.12.
What is slippage?
Slippage is the gap between the price you clicked and the price you got. In the example the plan was $0.0100 and the fill was $0.0103, which is 3%. That gap is entry slippage, and it has a dollar cost.
What is a price gap?
A gap is a jump from one trade to the next that skips the prices in between. A stop at $0.0075 can fill at $0.0074 if that is the next trade. The difference is the exit gap, and it is not the same thing as the fee.
How do fees affect a losing trade?
They add to the loss, and the buy fee also means you hold fewer tokens, so the exit price pays you less. A 0.75% swap fee (minimum $0.90 per swap), plus onchain fees. The example's buy is a market swap, so the $0.90 minimum applies. Limit, take-profit, stop-loss and DCA fills are 0.75%. The exit is a stop-loss fill, so its fee is 0.75% of the fill, about $0.21, not another $0.90.
Can AI tell me if a token was a rug pull?
It can point at public facts that were visible before the buy, such as a mint authority that could still create tokens, if those facts are in the data it has. It cannot recover funds, and it cannot prove intent from one trade.
Related prompts
- Prompt library
- Review a trade
- Risk review
- Research a token
- Exit liquidity
- Rug check
- Trading fee calculator
- Agentic trading
- Set up agentic trading
- AI trading bot
Try it with a Moby Agent
One agent per user, with its own wallet. Agents trade on Solana today. You set your agent's per-trade and daily spending limits and market-cap range; Moby blocks red-rated tokens. Limits are only as tight as you set them. Sells and exits skip the market-cap and safety checks, and tokens with no safety rating are not blocked. Turn on Ask before every trade and your AI asks you first. Moby does not hold or approve trades. AI Trading and copy trading currently need an access pass in the app. Download Moby.
In the Moby app, open the Agent tab and set up your Moby Agent. On the Connect your AI step, pick your platform and tap Create my key, then copy it. The key is shown once; if you lose it, rotate it in Agent settings. Say "Moby agent key" when you talk about it. Keep it out of the chat.
A 0.75% swap fee (minimum $0.90 per swap), plus onchain fees. Limit, take-profit, stop-loss and DCA fills are 0.75%.
The longer setup is how to set up agentic trading. How the loop works is on agentic trading. The map of bot types is the AI trading bot guide.