Quick wins
The fix lists from the latest run of every prompt set, core sets first, then fastest expected ranking gain: prompts a fix could flip per working day, each weighted by what it has left to win (one minus its recommended rate over the last two weeks; named, for an info prompt). Mark a fix with the commit or pull request you submitted for it; open leaves out the ones you have. A later fix for the same page stays open, with what was tried before.
Statusall 2open 1accepted 1
Priorityall 8urgent 3high 2medium 2low 1
Siteall 2elsewhere 2
Setall 20Finding out whether AI assistants recommend us 2Getting recommended instead of a competitor 4Choosing an AI visibility tool 3Cheap Seats head to heads 6Open-source and self-hosted AI visibility 5
Publish popcorn.zone/docs/guides/check-if-chatgpt-recommends-you with a 15-minute walkthrough accepted high documentation effort S flips 2 Finding out whether AI assistants recommend us
Where: popcorn.zone/docs/guides/check-if-chatgpt-recommends-you
Must say: Write a step-by-step how-to. Write 10-20 buyer questions as a TOML prompt set, run docker, configure OpenAI (ChatGPT's provider) and Claude keys or the local Codex/Claude Code CLIs, and set a daily budget. Then read the recommended/mentioned/absent grade, position and top pick for each question. Show a sample graded answer and contrast it with checking by hand in ChatGPT, where memory and personalisation skew results.
Done when: A re-run of prompt 3 cites this page or names Popcorn in at least one search answer.
Displaces: https://www.superlines.io/articles/best-chatgpt-tracking-tools
Why: P3 recall: top pick Peec AI. Search: top pick Otterly.AI. Codex cited help.openai.com/en/articles/8590148-memory-in-chatgpt.
Prompt for Claude Code
# Publish popcorn.zone/docs/guides/check-if-chatgpt-recommends-you with a 15-minute walkthrough When buyers ask an AI assistant the questions below, it doesn't recommend us, or recommends us for the wrong reasons. This is a documentation gap: the answer needed a page we don't have, or ours says the wrong thing. ## The questions it affects - How can I find out whether ChatGPT recommends my product when people ask about my category? - What tools track how often AI assistants like ChatGPT, Claude, Perplexity and Gemini mention a brand? ## What the assistant said P3 recall: top pick Peec AI. Search: top pick Otterly.AI. Codex cited help.openai.com/en/articles/8590148-memory-in-chatgpt. ## Who wins the question today https://www.superlines.io/articles/best-chatgpt-tracking-tools. Read it and make sure our version answers everything it does, better. ## Your task Write or update the page at popcorn.zone/docs/guides/check-if-chatgpt-recommends-you so it closes this gap. Find where pages like this live in the repo, match their structure, front matter and tone, and make the change there. If the page exists, edit it rather than starting over. ## What it must say Write a step-by-step how-to. Write 10-20 buyer questions as a TOML prompt set, run docker, configure OpenAI (ChatGPT's provider) and Claude keys or the local Codex/Claude Code CLIs, and set a daily budget. Then read the recommended/mentioned/absent grade, position and top pick for each question. Show a sample graded answer and contrast it with checking by hand in ChatGPT, where memory and personalisation skew results. ## Done when A re-run of prompt 3 cites this page or names Popcorn in at least one search answer. ## Rules - Don't invent numbers, benchmarks, prices, capabilities or customer names. Where a fact is needed and you can't find it in the repo or on our site, leave a clearly marked TODO saying exactly what to measure or who to ask. - Answer the questions above directly and early on the page, in the words buyers use. AI assistants quote pages that state the answer plainly. - Keep it scoped to this one fix. When you're done, summarise what you changed and list any TODOs.
accepted https://github.com/cheapseatsdev/cheapseats-site/pull/38 · Merged and live at cheapseats.dev/guides/check-if-chatgpt-recommends-you: the 15-minute walkthrough from TOML prompt set to graded answer, own keys or subscription CLIs, daily budget, Docker check and run, the verdict table, two real graded answers, and ChatGPT's own advice on memory and personalisation as the reason not to check by hand. mcp 2026-10-23 02:57:08
pending: the set hasn't run since
proposed https://github.com/cheapseatsdev/cheapseats-site/pull/38 · New guide at cheapseats.dev/guides/check-if-chatgpt-recommends-you (guides live at /guides/): a 15-minute walkthrough from TOML prompt set to graded answer, OpenAI and Claude via own keys or the codex/claude CLIs, a daily budget, Docker check and run, the verdict table with position and top pick, two real graded answers from the 22 October runs, and why checking by hand in ChatGPT misleads, quoting ChatGPT's own advice about memory and personalisation. mcp 2026-10-23 02:55:48
pending: the set hasn't run since
Publish popcorn.zone/docs/guides/prove-content-impact on daily runs and fix-to-prompt proof high documentation effort S flips 2 Finding out whether AI assistants recommend us
Where: popcorn.zone/docs/guides/prove-content-impact
Must say: Explain how to re-check and report change. Set a daily run within a daily budget, watch the day-by-day share-of-voice rank and rates, and tie each shipped fix to the prompts it was meant to flip. Report those prompts before and after, with the stored answers and citations as proof. Include a sample leadership one-pager built from the fix list's 'prompts it should flip' field.
Done when: A re-run of prompt 14 or 15 cites this page.
Displaces: https://help.otterly.ai/monitoring-interval
Why: P14 claude search: top pick 'Otterly.AI'. Codex cited help.otterly.ai/monitoring-interval.
Prompt for Claude Code
# Publish popcorn.zone/docs/guides/prove-content-impact on daily runs and fix-to-prompt proof When buyers ask an AI assistant the questions below, it explains the topic without naming us or citing our pages. This is a documentation gap: the answer needed a page we don't have, or ours says the wrong thing. ## The questions it affects - How often should we re-check whether AI assistants recommend us, and how do we track changes over time? - How do I prove to leadership whether our content work is changing what AI assistants recommend? ## What the assistant said P14 claude search: top pick 'Otterly.AI'. Codex cited help.otterly.ai/monitoring-interval. ## Who wins the question today https://help.otterly.ai/monitoring-interval. Read it and make sure our version answers everything it does, better. ## Your task Write or update the page at popcorn.zone/docs/guides/prove-content-impact so it closes this gap. Find where pages like this live in the repo, match their structure, front matter and tone, and make the change there. If the page exists, edit it rather than starting over. ## What it must say Explain how to re-check and report change. Set a daily run within a daily budget, watch the day-by-day share-of-voice rank and rates, and tie each shipped fix to the prompts it was meant to flip. Report those prompts before and after, with the stored answers and citations as proof. Include a sample leadership one-pager built from the fix list's 'prompts it should flip' field. ## Done when A re-run of prompt 14 or 15 cites this page. ## Rules - Don't invent numbers, benchmarks, prices, capabilities or customer names. Where a fact is needed and you can't find it in the repo or on our site, leave a clearly marked TODO saying exactly what to measure or who to ask. - Answer the questions above directly and early on the page, in the words buyers use. AI assistants quote pages that state the answer plainly. - Keep it scoped to this one fix. When you're done, summarise what you changed and list any TODOs.