Lobby

# Fix list: Lobby

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/lobby-os, the October 2026 research run, assessed 21 October 2026. Grade F, 11.1 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Lobby: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 0 out of 100, up to 17.5 more on the total

Why it scored 0: Graded on the interface an outside agent can use. With none for Lobby, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15), whatever the service does for its owner. The security programme line doesn't need an interface and is scored. For the record, the terms say nothing is sent, booked or updated until the owner explicitly approves it, and the privacy policy says Gmail and Calendar connect through Google OAuth 2.0, data is encrypted in transit and at rest, and every access is logged. Those are claims. thelobby.ai/.well-known/security.txt returns 404, and no security contact, disclosure policy, bug bounty, certification or advisories were found, the reading the Tomo and Orbits dossiers took (0 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Reliability, 15 out of 100, up to 17 more on the total

Why it scored 15: Read with the hosted lines. No status page found. status.thelobby.ai doesn't resolve and thelobby.ai/status returns 404 (0). No readable incident history (5). No rate or usage limits published in numbers. The home page says unlimited emails and calendars, which isn't a limit (0). No overload or retry guidance, and no interface for an outside agent (0). No SLA, and the terms say Lobby doesn't guarantee uninterrupted access (0). Sign-ups are open and nothing is labelled beta (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Agent ergonomics, 0 out of 100, up to 16.3 more on the total

Why it scored 0: Graded on the interface an outside agent can use. Lobby has none, so context cost, pagination, errors, retries and defaults have nothing to score (0 on each line). This says nothing about the product for people.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 4. Schema & documentation, 10 out of 100, up to 14.6 more on the total

Why it scored 10: Graded on the interface an outside agent can use, the reading the 12 and 14 October audits took for every listing without one. Lobby has no API, MCP server or A2A endpoint for an agent. /docs returns 404 and the sitemap lists three pages. So the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15). That is a statement about agent access, not about the product for people. thelobby.ai/llms.txt describes the product, connections, approval model and prices in plain text for agents (10). With no agent interface there is nothing to version (0 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 5. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: Read with the hosted rule. No x402, MPP or L402 (0). The home page and llms.txt publish US$50 a month billed monthly or US$42 a month billed annually, with no per-unit price, so plan-only (10). The terms say all plans include a 7-day free trial with no charge until it ends, but don't say whether a card is taken. The HireAlpha dossier gave 10 for a trial with its card question open (10 of 20). A person signs up in a browser at in.thelobby.ai (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Maintenance & community, 2 out of 100, up to 8.6 more on the total

Why it scored 2: Read for a closed service. No dated release, changelog, blog or app-store listing found. /changelog returns 404 and the site links no App Store page for its iOS and macOS apps. The newest dated pages are the terms and privacy policy of 26 March 2026, more than 180 days ago (0). No dated entries in the last 90 days (0). A support address in llms.txt, untested, and no changelog or community channel, the reading the Instinct and HireAlpha dossiers took (2 of 15). No MCP server or SDK (0). No package or CI to judge (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 43 out of 100, up to 5 more on the total

Made of editorial 38, provenance 47.

Why it scored 43: Closed service under Terms of Use dated 26 March 2026 naming Lobby OS, Inc. of San Francisco (15). The terms and the privacy policy of the same date agree that Lobby doesn't sell data, share it with third parties or train AI models on it, keeps data while the account is active and deletes it within 30 days of account deletion, and the privacy policy says a DPA is available. Neither names the model providers that process mail, and the sign-up app at in.thelobby.ai runs on Bubble and loads Hotjar and PostHog, none of which is named beside the no-third-parties statement or the Google Cloud hosting statement. Below HireAlpha's 18 for a consistent policy with a 30-day deletion period (16 of 30). Price changes get 30 days' notice and material term changes an email, with no deprecation policy and nothing on retiring parts of the product, the Instinct and Del reading (3 of 20). Google Cloud is named for hosting with no region, and no other processor is named, the Asaply reading for one named processor (4 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: thelobby.ai, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: whether the 7-day trial takes a card. No account was created.
- unchecked: the iOS and macOS apps. The site names them but links no App Store listing.
- Which model providers process mail, and whether Bubble holds account data, weren't established.
- The domain's registration date wasn't established.

## Weaknesses

- No API, MCP server or A2A endpoint for an outside agent.
- No status page, changelog, release notes or security.txt found on 21 October 2026.
- The privacy policy names no model provider, and the sign-up app's Bubble hosting and Hotjar and PostHog scripts aren't named as processors.
- The home page's 92% prediction accuracy and other figures are the vendor's, with no method published.

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Don't plan to call Lobby from another agent. It works only inside its own app for the signed-in owner.
- Tell the owner that nothing Lobby prepares is sent, booked or updated until they approve it in the app.
- Check whether the 7-day trial takes a card before signing the owner up. The terms don't say.

## What the review panel asked for

- state whether the trial needs a card
- a dated changelog
- a status page
- price the tools add-on
- name the model providers

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.