# AX Check: bettermenu.live Checked 2026-09-18. Pricing is public, but agents disagree on what it even is. The $39/month Starter plan with clear limits is posted openly, yet one session found no pricing page and another concluded the product is free. ## End-to-end onboarding not demonstrated ## Coding sessions Three independent sessions checked BetterMenu's pricing. DeepSeek V4 Pro correctly reported the $39/month Starter plan with trial and overage terms. Kimi K3 said no pricing page existed. Qwen 3.8 Max concluded the product was a free open-source library with no license found. ### DeepSeek V4 Pro [View public run](https://agents.withgauge.com/p/runs/c438c53b-54c5-45e7-848c-f852be2073c8) · [Read transcript](https://www.ax-check.com/bettermenu.live/sessions/deepseek.json) Final output gives $39/month Starter plan with named assumptions: 7-day trial, 50 recipes/month included then $0.50/recipe overage, 1000 AI-resolved ingredients then $0.012/ingredient, and flags that live entitlements API price figures are config-driven and restricted (seq 65-66, 101). Session findings unavailable. ### Kimi K3 [View public run](https://agents.withgauge.com/p/runs/d8593128-511a-45f5-8140-29f222752678) · [Read transcript](https://www.ax-check.com/bettermenu.live/sessions/kimi.json) Final output explicitly states 'no pricing page exists to report on' — no cost figure or assumptions are given anywhere in the trace or final message. #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: Agent found no product named BetterMenu anywhere (npm, PyPI, GitHub, or web domains). No credentials were ever sought or obtained, and no authenticated operation against a real hosted product was attempted or demonstrated. Event 19: ```text there is no product called "BetterMenu" that I can find, so there's no developer workflow for me to act on. ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **Product BetterMenu does not exist in any checked registry or domain**: The agent searched npm, PyPI, GitHub, and guessed web domains (bettermenu.com, bettermenu.io, app.bettermenu.com) and found no matching product, SDK, or API. This is not a product defect or agent error — it reflects that the named product could not be located with the information given, likely a seed prompt referencing a nonexistent or misnamed product. Event 10: ```text npm error 404 Not Found - GET https://registry.npmjs.org/bettermenu - Not found ``` Event 17: ```text app.bettermenu.com: 502 pypi: 404 ``` Event 19: ```text bettermenu.com` returns a 502 error, `bettermenu.io` doesn't resolve, `app.bettermenu.com` also 502s ``` #### Suggested Changes None identified in this transcript. ### Qwen 3.8 Max [View public run](https://agents.withgauge.com/p/runs/b3f60d54-a50f-4d9f-a19e-f48e318a268f) · [Read transcript](https://www.ax-check.com/bettermenu.live/sessions/qwen.json) Final output states pricing is 'Free' with the explicit basis that it's an open-source library rather than a commercial/hosted product, and flags the missing-license risk as a caveat to that assumption. #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: BetterMenu turned out to not be a hosted product with an SDK/API at all. The agent searched npm, PyPI, GitHub, and several guessed domains (bettermenu.com/.dev/.io/.ai) and found only an unrelated open-source terminal-menu library (better-menu on PyPI). No credentials exist for this product, no API was called, and no authenticated operation against a hosted backend occurred — the agent only pip-installed and ran a local Python script. Event 68: ```text It is not a hosted product**: no SDK for a cloud service, no API, no accounts, no keys. ``` Event 57: ```text -> Hello from BetterMenu! Selected index: 1 exit: 0 ``` #### Hallucinated URLs - **Guessed BetterMenu SaaS domains that don't exist**: The agent probed several domains it invented by pattern-guessing a possible hosted product name (bettermenu.dev, bettermenu.io, bettermenu.ai), none of which resolved. This wasn't following a documented link — it was speculative guessing to find a nonexistent hosted product, and all attempts failed to resolve or return content. Event 25: ```text for d in bettermenu.com bettermenu.dev bettermenu.io bettermenu.ai; do echo "== $d"; curl -s -m 8 -o /dev/null -w "%{http_code}\n" "https://$d"; done ``` Event 26: ```text == bettermenu.dev 000 == bettermenu.io 000 == bettermenu.ai 000 ``` #### Blockers - **BetterMenu is not a hosted product with a developer workflow**: The requested product 'BetterMenu' does not exist as a hosted SDK/API service. The only real match is an unrelated open-source terminal-UI Python library (better-menu on PyPI) with no accounts, keys, pricing, or network calls. This is a product/naming mismatch discovered via research, not an agent error or missing credential — there was simply no hosted product to onboard into. Event 68: ```text The only "BetterMenu" I can find and act on is **`better-menu` on PyPI** (C-JeanDev/better_menu on GitHub) — a small open-source Python library for rendering interactive terminal menus. ``` Event 21: ```text 200 {"message": "Not Found"} {"error":"Not found"} ``` - **Undeclared runtime dependency breaks fresh install**: Installing the better-menu package via pip succeeded but importing it immediately failed because the package requires 'getch' on Linux/macOS without declaring it as a dependency. This is a product (package) defect, not an agent or environment issue; the agent worked around it by manually installing getch. Event 41: ```text ModuleNotFoundError: No module named 'getch' ``` #### Suggested Changes None identified in this transcript. ### Task given to each agent Help me build a simple example using BetterMenu. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. Let me know if you get blocked. If this product has no developer workflow you can act on, say so plainly and stop. Stay light: use the hosted product through its SDK or API. Do not start local service stacks or wait for long-running commands; if the quickstart requires either, say so plainly and stop. No product credentials were supplied and no purchases were authorized. ## Score: B · 77/100 (provisional) Grades come from completed site checks. Coding sessions and skipped checks do not affect the score. ### Clarity - **Failed** — Homepage answers Markdown requests ```text Homepage returned text/html even when text/markdown was requested; no Markdown representation served. ``` - **Failed** — Install and next-step links resolve ```text Start Here links POST /studio/recipes/{recipe_id}/ingredient-resolutions, but that docs page returns 404. ``` - **Pass** — llms.txt provides an actionable documentation index ```text llms.txt links Guide, API Reference, free tools, changelog and llms-full.txt with organized sections. ``` - **Pass** — llms.txt provides navigation guidance ```text llms.txt groups content under Free Tools, Site, Documentation and Full text with descriptive links. ``` - **Pass** — llms.txt mentions offered API, MCP, and skills ```text llms.txt mentions API Reference, MCP agent access and ChatGPT app; docs cover API. ``` - **Pass** — A compact guide representation exists ```text llms.txt and docs pages are published; API quick start is a compact guide representation. ``` - **Pass** — A focused guide is directly retrievable ```text API Start Here quick start is directly retrievable with auth, create recipe, compute, label steps. ``` - **Pass** — Equivalent instructions fit a token budget ```text Start Here guide is 1327 tokens, well under the 8000-token budget. ``` - **Skipped** — Product-docs links survive format changes ```text Homepage Markdown unsupported, so link preservation across formats cannot be measured. ``` - **Pass** — The compact guide is independently actionable ```text API Start Here gives concrete steps: authenticate with Bearer key, create recipe, resolve ingredients, compute nutrition, generate label. ``` ### Onboarding - **Skipped** — Docs lead to a relevant quickstart ```text llms.txt links a Guide and API Reference, but no quickstart page was fetched. ``` - **Skipped** — Installation commands are extractable ```text No installation or CLI guide page was fetched; llms.txt lists no install commands. ``` - **Skipped** — Code examples are available without interaction ```text No docs page with code examples was fetched; only llms.txt index content available. ``` - **Skipped** — Prerequisites and auth boundaries are explicit ```text No docs or API page fetched to show prerequisites or API key boundaries. ``` ### Pricing - **Failed** — Agents identify pricing and its assumptions ```text 3 of 3 sessions were judged on pricing; 1 fell short. DeepSeek V4 Pro: Final output gives $39/month Starter plan with named assumptions: 7-day trial, 50 recipes/month included then $0.50/recipe overage, 1000 AI-resolved ingredients then $0.012/ingredient, and flags that live entitlements API price figures are config-driven and restricted (seq 65-66, 101). Kimi K3: Final output explicitly states 'no pricing page exists to report on' — no cost figure or assumptions are given anywhere in the trace or final message. Qwen 3.8 Max: Final output states pricing is 'Free' with the explicit basis that it's an open-source library rather than a commercial/hosted product, and flags the missing-license risk as a caveat to that assumption. This behavioural item does not affect the fast grade. ``` - **Pass** — Pricing is readable without interaction ```text Pricing page renders full plan details, limits and FAQ as static text without interaction. ``` - **Pass** — Prices are stated, not gated ```text Starter plan price $39/month stated publicly; overage rates $0.50/recipe and $0.012/ingredient listed. ``` - **Pass** — Pricing units and limits are explicit ```text Units explicit: 50 recipes/month, 1,000 AI ingredients/month, 1 user, overage rates and spend ceiling. ``` ### Activation - **Pass** — An API reference or OpenAPI spec is reachable ```text API reference with endpoints, auth, and request/response schemas is reachable at docs.bettermenu.live. ``` - **Skipped** — An MCP server is documented and well-formed ```text No MCP server documentation was fetched; llms.txt only mentions MCP agent access in passing. ``` - **Skipped** — A CLI install path is documented ```text No CLI install path is documented in the fetched pages. ``` - **Skipped** — SDK packages resolve on their registries ```text No SDK package or registry lookup result was supplied for BetterMenu. ``` - **Skipped** — Agent skills are published ```text No agent skills are published in the fetched evidence. ``` [Full report data](https://www.ax-check.com/bettermenu.live/report.json)