Motive Agents

# Fix list: Motive Agents

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/motive-agents, the October 2026 research run, assessed 20 October 2026. Grade F, 24.3 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 Motive Agents: 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. Agent ergonomics, 5 out of 100, up to 15.4 more on the total

Why it scored 5: These lines measure an interface an agent calls, and Agents have none. The hub lists each Agent's last modifier, last run and runs in the last 30 days, with drafts and deactivation, which helps the person who runs it (5). Nothing else applies. Total 5.

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.

## 2. Schema & documentation, 7 out of 100, up to 15.1 more on the total

Why it scored 7: No API, OpenAPI file, webhook event or MCP tool for Agents (0). No llms.txt on gomotive.com or the developer portal, whose /llms.txt returns the portal page (0). The help centre's Automations article explains for a person what triggers, conditions and actions exist and when to use templates (5 of 20). No typed inputs an agent could call (0). Step-by-step examples for people, with no error responses (2 of 15). No changelog for Agents, and the developer portal's changelog has no entries (0). Total 7.

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.

## 3. Payments & pricing, 0 out of 100, up to 12.5 more on the total

Why it scored 0: No x402, MPP or L402 (0 of 40). No published price for Agents or the platform, and gomotive.com/pricing redirects to a contact form (0 of 20). No free tier or trial for Agents found (0). Access comes with a Motive contract and a person in the Fleet Dashboard (0). Total 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.

## 4. Security & auth, 35 out of 100, up to 11.4 more on the total

Why it scored 35: No credential an outside agent could hold for Agents (0). Agents need the Automations permission, held by Admin users by default and granted to other roles explicitly, and every Agent goes through a review step before it's published. Actions include calling drivers and marking vehicles out of service, with no separate approval step documented (8 of 20). Agents act on vehicle and driver telemetry rather than free text, with no guidance on injection through Atlas calls (5 of 15). The hub records the last modifier and run counts, and the trust centre lists audit logging, with no per-run log documented for Agents (6 of 15). The trust centre lists SOC 2 Type II, SOC 1 Type II, ISO/IEC 27001:2022, ISO/IEC 27701, PCI DSS and a penetration test, and an invitation-only bug bounty with reports to security@gomotive.com. No security.txt (16 of 20). Total 35.

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.

## 5. Reliability, 50 out of 100, up to 10 more on the total

Why it scored 50: Read with the hosted lines, for a feature only people operate in the Fleet Dashboard. status.gomotive.com (Hund.io) has component history, with Fleet Dashboard and API components and none for Agents (20). In the 90 days to 20 October, Fleet Events and Locations were delayed for about three hours on 29 July (API affected), driver safety scores for about six hours on 3 August, safety events for about 17 hours on 6 and 7 October, and the Driver App had a 12-hour connectivity issue on 8 October. These are delays of the data Agents trigger on rather than an outage, scored as one major (10). No rate limits apply, since there is no API for Agents (0). No retry guidance (0). The SLA promises 99.99 per cent monthly uptime for Fleet Dashboard login, with service credits, for paying customers (10). The launch says Agents are available now to Motive customers, scored 10 as for mandl-cooper, though plain-language and goal-based Agents are listed for early 2027. Total 50.

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.

## 6. Maintenance & community, 35 out of 100, up to 5.7 more on the total

Why it scored 35: Read for a closed service. Launched as Agents on 19 October 2026, within 30 days (30). Fewer than three dated product changes to Agents in 90 days were found (the Automations article was updated on 9 September and the launch on 19 October) (0). Help centre and 24/7 phone support, with no public changelog for Agents (5 of 15). No SDK or registry entry for Agents (0). No package (0). Total 35.

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, 59 out of 100, up to 3.6 more on the total

Made of editorial 38, provenance 80.

Why it scored 59: Closed service with clear terms. The Terms of Service are effective 7 July 2025 with a dated list of changes, governed by California law (15 of 30). Data handling is set by the terms and an incorporated Data Protection Addendum. The terms give Motive a perpetual right to use Customer Data to improve its services and develop new products and to share it with partners under confidentiality. The privacy policy (reviewed 15 June 2026) covers only the website, and no statement was found on which AI models process the data Agents act on (12 of 30). The terms promise notice before material changes, with no deprecation policy (3 of 20). The trust centre lists sub-processors and AWS as the host, without naming the AI providers behind Atlas (8 of 20). Total 38.

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):

- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-10-18, -2. Motive's blog post "Motive launches AI-powered Agents" (dated 27 May 2026, last modified 18 October 2026) says "Agents can be set up using guided workflows, pre-built templates, or natural language", while the 19 October launch blog and press release list describing an Agent in plain language as "Coming early 2027". A current page presents a feature as available that the vendor's own launch says isn't, so the deduction is the minimum (https://gomotive.com/blog/ai-fleet-agents/, https://gomotive.com/blog/motive-launches-ai-agents/)

## 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 Motive MCP exposes any tool for Agents. The help article lists none, and the server answers 401 without an OAuth token, so its tool list wasn't read.
- unchecked: whether Agents cost extra or come with existing Motive subscriptions. No price was found and pricing is through sales.
- unchecked: whether Atlas voice calls to drivers through AI Dashcam Plus work today. The press release describes them as current, while the launch blog says voice agent outreach on AI Dashcam Plus comes "later this year".
- unchecked: the availability of Agents outside the United States. The April help centre note says the rollout began with US customers.
- unchecked: the Wayback Machine copy of the August blog post, to see whether it named Agents in August. archive.org answered 429 to our request.
- Vendor claims not checked: decisions "up to 10 times faster" with Agents, $46 billion lost to preventable issues, and the 2026 ROI Report figure of 42 per cent.

## Weaknesses

- No API, webhook or MCP tool an outside agent can use to create, run or read Agents
- Pricing is through sales, with no published price or trial for Agents
- A Motive page edited on 18 October says Agents can be set up in natural language, while the launch post lists that for early 2027
- Plain-language and goal-based Agents and the Motive-built library aren't available yet
- Safety events were delayed for about 17 hours on 6 and 7 October 2026, and Agents trigger on those events

## 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 Motive Agents. They're built and run by people in the Motive Fleet Dashboard
- For Motive fleet data, use Motive's Public API or its MCP server instead, with the customer's admin authorisation
- Ask the fleet's Motive admin to set up or change an Agent, and describe the trigger, condition and action you need
- Expect Agents to place real calls to drivers and mark vehicles out of service, so confirm with the fleet manager before suggesting one

## What the review panel asked for

- API for creating Agents
- publish a price
- a dated changelog for Agents
- a deprecation policy with notice periods
- an Agents component on the status page
- documented failure behaviour for Agents
- approval step for driver calls
- per-run audit log

## 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.