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.
Siteall 8cheapseats.dev (marketing) 2cheapseats.dev/docs (docs) 3github.com/cheapseatsdev/cheapseats (code) 1elsewhere 2
Publish cheapseats.dev/docs/costs with measured per-run spend and daily budget cap config urgent documentation effort S flips 5 cheapseats.dev/docs Cheap Seats head to heads
Where: https://cheapseats.dev/docs/costs
Must say: Port the popcorn.zone cost page, which was never crawled. The new page must give measured spend for a stated prompt set: prompts × 2 tracks × models × runs per day, with the dollar figure from a real run (measure this first). It must show the daily budget cap config and explain the subscription path: local Claude Code or Codex CLIs on your own plans. End with a worked example that a startup can compare against Otterly Lite or Peec Starter pricing.
Done when: On a re-run of P11, at least 2 answers give a Cheap Seats-specific daily cost and name the budget cap, and P3 search answers stop saying its cost is unverifiable.
Displaces: https://otterly.ai/pricing
Why: "no authoritative public pricing found" (P11, codex-sol search)
Prompt for Claude Code
# Publish cheapseats.dev/docs/costs with measured per-run spend and daily budget cap config 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 - Cheap Seats or Peec AI for a small marketing team? - Cheap Seats vs Otterly.AI for a startup that wants to track AI visibility cheaply? - Cheap Seats or Semrush AI Toolkit for tracking our brand in ChatGPT and Claude? - Is Cheap Seats a good fit for an agency tracking AI visibility for many clients? - What does it cost to run Cheap Seats every day, and how do I keep the spend under control? ## What the assistant said "no authoritative public pricing found" (P11, codex-sol search) ## Who wins the question today https://otterly.ai/pricing. Read it and make sure our version answers everything it does, better. ## Your task Write or update the page at https://cheapseats.dev/docs/costs 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 Port the popcorn.zone cost page, which was never crawled. The new page must give measured spend for a stated prompt set: prompts × 2 tracks × models × runs per day, with the dollar figure from a real run (measure this first). It must show the daily budget cap config and explain the subscription path: local Claude Code or Codex CLIs on your own plans. End with a worked example that a startup can compare against Otterly Lite or Peec Starter pricing. ## Done when On a re-run of P11, at least 2 answers give a Cheap Seats-specific daily cost and name the budget cap, and P3 search answers stop saying its cost is unverifiable. ## 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.
Publish cheapseats.dev/docs/how-grading-works: 3 grades, 2 tracks, raw answers kept urgent documentation effort S flips 5 cheapseats.dev/docs Cheap Seats head to heads
Where: https://cheapseats.dev/docs/how-grading-works
Must say: Port the popcorn.zone grading page to cheapseats.dev. It must define the three grades: recommended, mentioned and absent. It must explain what else each answer records: position, top pick, every product named (for share of voice) and the objections raised. It must describe the two tracks: search, where the assistant must search the web first, and recall, with no tools. Finally, state that every answer, search result and citation is kept, so the raw answers are always inspectable. That answers P10's condition that the tool "exposes the underlying answers" and P3/P6's "API answers aren't what users see".
Done when: On a re-run of P8, at least 2 of 4 answers describe the three grades and the two tracks and cite cheapseats.dev.
Displaces: https://github.com/topics/ai-visibility-tracking?o=desc&s=stars
Why: "I'm not going to guess at its method" (P8, claude-code-opus search)
Prompt for Claude Code
# Publish cheapseats.dev/docs/how-grading-works: 3 grades, 2 tracks, raw answers kept 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 - Cheap Seats vs Otterly.AI for a startup that wants to track AI visibility cheaply? - Is Cheap Seats a good open-source alternative to paid AI visibility tools? - What are the downsides of self-hosting Cheap Seats to measure AI search visibility? - How does Cheap Seats decide whether an AI assistant recommended a brand? - Is Cheap Seats a good fit for a developer-tools company checking whether ChatGPT and Claude recommend it? ## What the assistant said "I'm not going to guess at its method" (P8, claude-code-opus search) ## Who wins the question today https://github.com/topics/ai-visibility-tracking?o=desc&s=stars. Read it and make sure our version answers everything it does, better. ## Your task Write or update the page at https://cheapseats.dev/docs/how-grading-works 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 Port the popcorn.zone grading page to cheapseats.dev. It must define the three grades: recommended, mentioned and absent. It must explain what else each answer records: position, top pick, every product named (for share of voice) and the objections raised. It must describe the two tracks: search, where the assistant must search the web first, and recall, with no tools. Finally, state that every answer, search result and citation is kept, so the raw answers are always inspectable. That answers P10's condition that the tool "exposes the underlying answers" and P3/P6's "API answers aren't what users see". ## Done when On a re-run of P8, at least 2 of 4 answers describe the three grades and the two tracks and cite cheapseats.dev. ## 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.
Publish cheapseats.dev/docs/agencies: multi-client prompt sets, owners, API reporting medium documentation effort S flips 1 cheapseats.dev/docs Cheap Seats head to heads
Where: https://cheapseats.dev/docs/agencies
Must say: Explain the multi-client workflow: one TOML prompt-set repo per client with changes reviewed through PRs, and fix lists that name which of the brand's sites a fix belongs on and its owner. Cover per-prompt-set share-of-voice rankings tracked daily, the JSON API and MCP server for client reporting, and per-instance daily budgets. Confirm and state whether one instance serves many brands before publishing.
Done when: On a re-run of P9, at least 1 search answer cites the agencies page and drops 'unverified agency features'.
Displaces: https://www.semrush.com/blog/ai-visibility-tracking-tools-for-agencies/
Why: "no public listing found in current roundups or comparisons" (P9, claude-code-opus search)
Prompt for Claude Code
# Publish cheapseats.dev/docs/agencies: multi-client prompt sets, owners, API reporting 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 - Is Cheap Seats a good fit for an agency tracking AI visibility for many clients? ## What the assistant said "no public listing found in current roundups or comparisons" (P9, claude-code-opus search) ## Who wins the question today https://www.semrush.com/blog/ai-visibility-tracking-tools-for-agencies/. Read it and make sure our version answers everything it does, better. ## Your task Write or update the page at https://cheapseats.dev/docs/agencies 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 the multi-client workflow: one TOML prompt-set repo per client with changes reviewed through PRs, and fix lists that name which of the brand's sites a fix belongs on and its owner. Cover per-prompt-set share-of-voice rankings tracked daily, the JSON API and MCP server for client reporting, and per-instance daily budgets. Confirm and state whether one instance serves many brands before publishing. ## Done when On a re-run of P9, at least 1 search answer cites the agencies page and drops 'unverified agency features'. ## 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.