{
  "fixes": {
    "slug": "vocily",
    "name": "Vocily AI",
    "listing": "https://www.anchorterminal.com/tools/vocily",
    "markdown": "# Fix list: Vocily AI\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/vocily, the October 2026 research run, assessed 8 October 2026. Grade D, 53.8 out of 100.\n\nThis 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.\n\nFor a coding agent working on Vocily AI: 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.\n\n## 1. Reliability, 40 out of 100, up to 12 more on the total\n\nWhy it scored 40: Graded on the public REST API at api.vocily.ai, read as a hosted service. No status page found. status.vocily.ai doesn't resolve and neither the site nor the docs link one (0). No readable incident history (5). The limit is published as 300 requests a minute per key, with ten concurrent calls per organisation reported in response headers (15). A 429 carries `Retry-After` and `X-RateLimit` headers, capacity refusals carry `Retry-After`, and `POST /v1/calls` requires an `Idempotency-Key` and replays the original call on a retry (15). No SLA found. The terms say availability isn't guaranteed, and the Enterprise tier mentions only agreed support response commitments (0). The docs don't label the API beta, but four dated releases between 23 and 30 September 2026 changed the `/v1` contract, three of them with removals or changed codes, the API root reports version 0.1.0, and the terms still allow for beta and pre-launch service (5 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Security \u0026 auth, 46 out of 100, up to 9.5 more on the total\n\nWhy it scored 46: Bearer keys are shown once, revocable in the dashboard and bound to one workspace, and they can't reach billing, members or key management. There are no scopes to set and no rotation route, and webhooks are HMAC-signed with a timestamp and a rotation overlap (22 of 30). No read-only key. Spending and contractual actions stay in the dashboard, a version answers calls only after publish and make-live, and the memory erase previews by default (10 of 20). Transcripts and caller speech are untrusted content, and the API docs have no prompt-injection guidance. The site describes topic fencing and an empty-knowledge-base guard (4 of 15). Each call keeps a record with cost and version, webhooks have a delivery log and every response a request id, but we found no audit log of account or key actions (8 of 15). No security.txt, disclosure policy, bug bounty or certification. The compliance page says Vocily doesn't claim certification, and the privacy policy states encryption in transit and at rest (2 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 3. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 (0 of 40). Per-minute prices for each speech-to-text model, language model and voice, the platform fee, telephony, per-reply chat prices and WhatsApp fees are public without a login in rupees and US dollars (20). A new organisation gets ₹200 or $2 of credit, and the pricing page says no card (20). Access starts with a browser signup and email verification, and API keys can only be created in the dashboard (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 4. Transparency \u0026 trust, 47 out of 100, up to 4.6 more on the total\n\nMade of editorial 34, provenance 59.\n\nWhy it scored 47: A closed service. The terms (10 June 2026) name no legal entity or governing law, still describe a possible beta, and say paid plans may come later while prices are live (10 of 30). The privacy policy (3 September 2026) is written mainly around WhatsApp data and gives no retention period. The pricing and compliance pages say recordings are kept for the life of the account and deleted on request, and audio and transcript storage are per-agent settings. No DPA found (12 of 30). The reference promises additive changes within `/v1`, but removals shipped on 23 and 25 September 2026 with same-day notes and migration tables and no notice period (6 of 20). The privacy policy mentions vetted providers without naming them. Model providers and carriers can be read from the pricing page and docs, and no data location is documented (6 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: vocily.ai, registered 2026-07-12 (under a year) (0 of 15)\n- Terms of service: read, states 4 of the 7 things a reader expects (7.4 of 10)\n- Privacy policy: read, states 4 of the 8 things a reader expects (7 of 10)\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 5. Maintenance \u0026 community, 61 out of 100, up to 3.4 more on the total\n\nWhy it scored 61: The latest dated API change is 30 September 2026 (30). Four dated entries, on 23, 25, 27 and 30 September (20). A public change log, a Discord server and a founder email address are the channels found, and we didn't test whether they answer (8 of 15 for a closed service). No official SDK found, although the marketing site lists Python and TypeScript SDKs (0 of 15). There is no package to assess. The OpenAPI file was last modified on 1 October 2026 (3 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 6. Agent ergonomics, 84 out of 100, up to 2.6 more on the total\n\nWhy it scored 84: List calls take `limit` from 1 to 100, default 20, and return the transcript only with `include=transcript` (20 of 25). Every growing list uses the same cursor envelope, and calls filter by agent, status, direction, origin and date. The bounded lists return bare arrays (18 of 20). Errors carry a machine-readable `detail.code`, a field path on validation failures and an `X-Request-ID` (20). `Idempotency-Key` is required on call creation, agent edits accept `If-Match` on a document revision, and the bulk memory erase previews unless `dry_run` is false. Other writes have no idempotency key (18 of 20). A call needs only `agent_id` and `to_number` and an agent only `name`. No SDK was found in the docs, on npm or on PyPI (8 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 7. Schema \u0026 documentation, 90 out of 100, up to 1.6 more on the total\n\nWhy it scored 90: A public OpenAPI 3.1 file with 54 operations at docs.vocily.ai/developers/openapi.json (25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Pages say what each route is for and what to use instead, such as webhooks over polling and dashboard batches over a loop of calls, though some operation titles are generated names such as Create Kb (16 of 20). Bodies refuse unknown fields and carry ranges and enums, but list filters such as `status` are plain strings and `variables` and `metadata` are free-form (12 of 15). 196 examples in the spec, a reason-code table by status and a 422 that lists every invalid field (15). The `/v1` prefix and a dated API changes page, which starts on 23 September 2026 and records removals made under `/v1` against the reference's own rule that fields are never removed within a version (12 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-09-23 and 2026-09-25, -3. Two releases removed fields and routes under `/v1` with no notice period, including `tools` on the agent body, `call_type`, `?skip=` and `?offset=`, and the `/widgets` collection routes. The 23 September note says there is no window in which both shapes work. The API reference says fields are never removed or renamed within a version. Documented the same day with migration tables, so the deduction is reduced (https://docs.vocily.ai/developers/changes.md)\n- 2026-10-08, -2. The developer page on the marketing site lists Fern-generated Python and TypeScript SDKs, an MCP server, API key routes with rotation, webhook endpoint routes, `POST /v1/agents/{id}/chat` and events such as `transcript.ready`. The docs and the OpenAPI file have none of these, keys and webhook endpoints are dashboard-only, and no package was found on npm or PyPI (https://vocily.ai/platform/api-tools and https://docs.vocily.ai/developers/api-reference.md)\n\n## What we couldn't check\n\nWhat 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.\n\n- We made no authenticated call, so rate-limit headers, idempotent replay and error bodies are as documented, not as observed. An unauthenticated request returned 401 with an `x-request-id` header.\n- Whether the Python and TypeScript SDKs and the MCP server listed on vocily.ai/platform/api-tools exist anywhere. They aren't in the docs, and npm and PyPI have no package named vocily.\n- What the `agents:publish` permission in the error table refers to, given that the reference says keys have nothing to configure.\n- Where call recordings and transcripts are stored. The compliance page says the region is chosen by the customer, and the docs and privacy policy name no location.\n- The sub-processor list and any DPA. Neither was found on the site.\n- Whether support on Discord or by email answers. We didn't test it.\n- The legal entity is taken from the registrant field of the vocily.ai domain record. No page on the site names it, and we didn't check a company registry.\n- The scout's note described a REST API for batches and a realtime API for conversation events. Batch campaigns are dashboard-only per the API reference, and the docs have webhooks, not a realtime API. The app now lives at app.vocily.ai, with app.vocily.com redirecting to it.\n\n## Weaknesses\n\n- No status page, incident history or SLA was found\n- Fields and routes were removed under `/v1` on 23 and 25 September 2026 on the day of the announcement\n- The marketing site lists SDKs, an MCP server and key management endpoints that the docs don't have\n- No security.txt, disclosure policy, bug bounty or certification was found\n- The terms and privacy policy name no legal entity, sub-processor or retention period\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send a fresh UUID in `Idempotency-Key` on every `POST /v1/calls`. The API refuses the request without it\n- Pass a `from_number` the workspace holds. The shared Test Number returns 403 from the API\n- Publish a version and make it live before placing a call, or the call returns 409 `agent_not_published`\n- Branch on `detail.code`, falling back to the top-level `code`. A 429 body is flat, so read `Retry-After`\n- Read `currency` on every call and chat record. Costs are in rupees or dollars depending on the organisation\n\n## When it's done\n\nSend 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.\n",
    "grade": "D",
    "score": 53.8,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 40,
        "maxGain": 12,
        "reason": "Graded on the public REST API at api.vocily.ai, read as a hosted service. No status page found. status.vocily.ai doesn't resolve and neither the site nor the docs link one (0). No readable incident history (5). The limit is published as 300 requests a minute per key, with ten concurrent calls per organisation reported in response headers (15). A 429 carries `Retry-After` and `X-RateLimit` headers, capacity refusals carry `Retry-After`, and `POST /v1/calls` requires an `Idempotency-Key` and replays the original call on a retry (15). No SLA found. The terms say availability isn't guaranteed, and the Enterprise tier mentions only agreed support response commitments (0). The docs don't label the API beta, but four dated releases between 23 and 30 September 2026 changed the `/v1` contract, three of them with removals or changed codes, the API root reports version 0.1.0, and the terms still allow for beta and pre-launch service (5 of 10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 46,
        "maxGain": 9.5,
        "reason": "Bearer keys are shown once, revocable in the dashboard and bound to one workspace, and they can't reach billing, members or key management. There are no scopes to set and no rotation route, and webhooks are HMAC-signed with a timestamp and a rotation overlap (22 of 30). No read-only key. Spending and contractual actions stay in the dashboard, a version answers calls only after publish and make-live, and the memory erase previews by default (10 of 20). Transcripts and caller speech are untrusted content, and the API docs have no prompt-injection guidance. The site describes topic fencing and an empty-knowledge-base guard (4 of 15). Each call keeps a record with cost and version, webhooks have a delivery log and every response a request id, but we found no audit log of account or key actions (8 of 15). No security.txt, disclosure policy, bug bounty or certification. The compliance page says Vocily doesn't claim certification, and the privacy policy states encryption in transit and at rest (2 of 20).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0 of 40). Per-minute prices for each speech-to-text model, language model and voice, the platform fee, telephony, per-reply chat prices and WhatsApp fees are public without a login in rupees and US dollars (20). A new organisation gets ₹200 or $2 of credit, and the pricing page says no card (20). Access starts with a browser signup and email verification, and API keys can only be created in the dashboard (0).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 47,
        "maxGain": 4.6,
        "reason": "A closed service. The terms (10 June 2026) name no legal entity or governing law, still describe a possible beta, and say paid plans may come later while prices are live (10 of 30). The privacy policy (3 September 2026) is written mainly around WhatsApp data and gives no retention period. The pricing and compliance pages say recordings are kept for the life of the account and deleted on request, and audio and transcript storage are per-agent settings. No DPA found (12 of 30). The reference promises additive changes within `/v1`, but removals shipped on 23 and 25 September 2026 with same-day notes and migration tables and no notice period (6 of 20). The privacy policy mentions vetted providers without naming them. Model providers and carriers can be read from the pricing page and docs, and no data location is documented (6 of 20).",
        "blend": "editorial 34, provenance 59",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 61,
        "maxGain": 3.4,
        "reason": "The latest dated API change is 30 September 2026 (30). Four dated entries, on 23, 25, 27 and 30 September (20). A public change log, a Discord server and a founder email address are the channels found, and we didn't test whether they answer (8 of 15 for a closed service). No official SDK found, although the marketing site lists Python and TypeScript SDKs (0 of 15). There is no package to assess. The OpenAPI file was last modified on 1 October 2026 (3 of 10).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 84,
        "maxGain": 2.6,
        "reason": "List calls take `limit` from 1 to 100, default 20, and return the transcript only with `include=transcript` (20 of 25). Every growing list uses the same cursor envelope, and calls filter by agent, status, direction, origin and date. The bounded lists return bare arrays (18 of 20). Errors carry a machine-readable `detail.code`, a field path on validation failures and an `X-Request-ID` (20). `Idempotency-Key` is required on call creation, agent edits accept `If-Match` on a document revision, and the bulk memory erase previews unless `dry_run` is false. Other writes have no idempotency key (18 of 20). A call needs only `agent_id` and `to_number` and an agent only `name`. No SDK was found in the docs, on npm or on PyPI (8 of 15).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 90,
        "maxGain": 1.6,
        "reason": "A public OpenAPI 3.1 file with 54 operations at docs.vocily.ai/developers/openapi.json (25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Pages say what each route is for and what to use instead, such as webhooks over polling and dashboard batches over a loop of calls, though some operation titles are generated names such as Create Kb (16 of 20). Bodies refuse unknown fields and carry ranges and enums, but list filters such as `status` are plain strings and `variables` and `metadata` are free-form (12 of 15). 196 examples in the spec, a reason-code table by status and a 422 that lists every invalid field (15). The `/v1` prefix and a dated API changes page, which starts on 23 September 2026 and records removals made under `/v1` against the reference's own rule that fields are never removed within a version (12 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "vocily.ai, registered 2026-07-12 (under a year)",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 4 of the 7 things a reader expects",
        "points": 7.4,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 4 of the 8 things a reader expects",
        "points": 7,
        "max": 10
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "2026-09-23 and 2026-09-25, -3. Two releases removed fields and routes under `/v1` with no notice period, including `tools` on the agent body, `call_type`, `?skip=` and `?offset=`, and the `/widgets` collection routes. The 23 September note says there is no window in which both shapes work. The API reference says fields are never removed or renamed within a version. Documented the same day with migration tables, so the deduction is reduced (https://docs.vocily.ai/developers/changes.md)",
      "2026-10-08, -2. The developer page on the marketing site lists Fern-generated Python and TypeScript SDKs, an MCP server, API key routes with rotation, webhook endpoint routes, `POST /v1/agents/{id}/chat` and events such as `transcript.ready`. The docs and the OpenAPI file have none of these, keys and webhook endpoints are dashboard-only, and no package was found on npm or PyPI (https://vocily.ai/platform/api-tools and https://docs.vocily.ai/developers/api-reference.md)"
    ],
    "unchecked": [
      "We made no authenticated call, so rate-limit headers, idempotent replay and error bodies are as documented, not as observed. An unauthenticated request returned 401 with an `x-request-id` header.",
      "Whether the Python and TypeScript SDKs and the MCP server listed on vocily.ai/platform/api-tools exist anywhere. They aren't in the docs, and npm and PyPI have no package named vocily.",
      "What the `agents:publish` permission in the error table refers to, given that the reference says keys have nothing to configure.",
      "Where call recordings and transcripts are stored. The compliance page says the region is chosen by the customer, and the docs and privacy policy name no location.",
      "The sub-processor list and any DPA. Neither was found on the site.",
      "Whether support on Discord or by email answers. We didn't test it.",
      "The legal entity is taken from the registrant field of the vocily.ai domain record. No page on the site names it, and we didn't check a company registry.",
      "The scout's note described a REST API for batches and a realtime API for conversation events. Batch campaigns are dashboard-only per the API reference, and the docs have webhooks, not a realtime API. The app now lives at app.vocily.ai, with app.vocily.com redirecting to it."
    ],
    "weaknesses": [
      "No status page, incident history or SLA was found",
      "Fields and routes were removed under `/v1` on 23 and 25 September 2026 on the day of the announcement",
      "The marketing site lists SDKs, an MCP server and key management endpoints that the docs don't have",
      "No security.txt, disclosure policy, bug bounty or certification was found",
      "The terms and privacy policy name no legal entity, sub-processor or retention period"
    ],
    "agentNotes": [
      "Send a fresh UUID in `Idempotency-Key` on every `POST /v1/calls`. The API refuses the request without it",
      "Pass a `from_number` the workspace holds. The shared Test Number returns 403 from the API",
      "Publish a version and make it live before placing a call, or the call returns 409 `agent_not_published`",
      "Branch on `detail.code`, falling back to the top-level `code`. A 429 body is flat, so read `Retry-After`",
      "Read `currency` on every call and chat record. Costs are in rupees or dollars depending on the organisation"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}