{
  "$schema": "https://getevercrew.com/roster.schema.json",
  "spec_version": "1.1",
  "generated_by": "tools/build.py from content/site.json — do not hand-edit",
  "generated": "2026-08-16",
  "canonical_url": "https://getevercrew.com/roster.json",
  "mirror_url": "https://getevercrew.com/.well-known/agent-roster.json",
  "provider": {
    "name": "Evercrew",
    "url": "https://getevercrew.com/",
    "tagline": "Your Digital Workforce, Fully Managed.",
    "system_name": "Night Watch",
    "location": "Colorado Springs, Colorado, United States",
    "area_served": [
      "US"
    ],
    "contact_email": "hello@getevercrew.com",
    "what_it_is": "A managed digital workforce. Evercrew supplies, supervises, repairs and replaces a small crew of AI workers on behalf of an owner-operated business. The customer receives output and approves anything touching money or a client; the customer does not operate the agents.",
    "maturity": {
      "customers": 1,
      "note": "One external customer plus the company that built the system. Stated plainly rather than omitted. There are no testimonials, customer logos or productivity metrics published anywhere on this site because none could be produced honestly at this stage.",
      "claims_withheld": [
        "no_testimonials",
        "no_customer_logos",
        "no_productivity_multiplier",
        "no_unverified_integration_list"
      ]
    }
  },
  "pricing": {
    "model": "flat_monthly",
    "not": [
      "per_seat",
      "per_message",
      "per_token",
      "usage_metered"
    ],
    "rationale": "Per-seat pricing makes a customer ration who gets help; per-message pricing makes them ration how much they ask. Both suppress the behaviour that makes a crew valuable.",
    "model_usage_varies_by_plan": true,
    "included_in_every_plan": [
      "the agents named on the plan, doing the jobs named in the written scope",
      "a written scope stating what it does and what it does not do",
      "human approval on anything reaching the customer's clients",
      "the client portal",
      "a clean copy of the customer's data on exit"
    ],
    "not_included": [
      "setup — quoted once, separately, as a not-to-exceed number, before anything starts",
      "work outside the written scope — a change order approved in advance, never a surprise invoice",
      "on-site visits",
      "equipment, systems or data the customer provides; worked with, not warranted"
    ],
    "fair_use": "No meter. The first ninety days set the customer's own baseline; fair use is 150% of that baseline, not a fixed figure. Exceeding it produces a note, then a call, and only bills on a third consecutive month.",
    "currency": "USD",
    "status": "PUBLISHED_AS_RANGES_ON_PAGE_NOT_AN_OFFER",
    "amounts": null,
    "amounts_note": "Plan ranges are published in human-readable form on the page and are sourced from internal pricing documents, not invented. They are deliberately omitted from this file and from the page's JSON-LD. Reason: a figure exposed in structured data is read as an offer and transacted on, and no figure here is an offer — every engagement is priced in a conversation and setup is quoted separately. An agent should treat this provider as quote-on-request and complete the enquiry action below rather than infer a price.",
    "how_to_get_a_price": {
      "method": "enquiry",
      "endpoint": "mailto:hello@getevercrew.com?subject=Crew%20enquiry",
      "responder": "human",
      "typical_response": "same or next business day",
      "process": "One conversation, ninety minutes or less, no charge and no obligation. Produces the monthly figure and a not-to-exceed setup quote."
    },
    "plans": [
      {
        "id": "one_agent",
        "name": "One Agent",
        "shape": "one agent, one written job",
        "billing": "monthly",
        "model_usage": "client_owned_keys",
        "model_usage_note": "The client holds their own API keys and pays the model provider directly at the provider's price. Evercrew takes no margin on tokens and does not resell compute."
      },
      {
        "id": "crew",
        "name": "A Crew",
        "shape": "manager agent plus up to four specialists; seats free",
        "billing": "monthly",
        "model_usage": "included",
        "model_usage_note": "Evercrew holds the keys and carries the token cost within the monthly price on this plan."
      },
      {
        "id": "advisory",
        "name": "Advisory",
        "shape": "monthly working session plus three hours; added to any plan",
        "billing": "monthly",
        "minimum_term_months": 3,
        "model_usage": "inherits_base_plan"
      }
    ]
  },
  "workers": [
    {
      "id": "bookkeeper",
      "name": "The Bookkeeper",
      "role": "Managed AI bookkeeping worker",
      "capabilities": [
        "Reconciles accounts on a fixed cadence",
        "Categorises transactions and learns the customer's chart of accounts",
        "Chases items that will not reconcile, with supporting documentation attached",
        "Assembles the month-end packet for a human accountant"
      ],
      "hard_limits": [
        "Never files a tax return",
        "Never moves money",
        "Never signs anything",
        "Does not replace the customer's accountant; prepares work for them"
      ],
      "human_approval_required_for": [
        "anything touching money",
        "anything sent outside the business"
      ],
      "service_url": "https://getevercrew.com/#service-bookkeeper"
    },
    {
      "id": "operator",
      "name": "The Operator",
      "role": "Managed AI operations worker",
      "capabilities": [
        "Intake, filing, naming conventions and folder discipline",
        "Follow-ups that would otherwise be lost in an inbox",
        "First drafts of quotes, letters and scopes of work",
        "Maintains one authoritative record rather than several partial ones"
      ],
      "hard_limits": [
        "Never sends anything to the customer's client",
        "Produces drafts only, held for human review until the human sends",
        "Cannot initiate an outbound conversation on anyone's behalf"
      ],
      "human_approval_required_for": [
        "all outbound communication"
      ],
      "service_url": "https://getevercrew.com/#service-operator"
    },
    {
      "id": "watch",
      "name": "The Watch",
      "role": "Managed AI monitoring worker",
      "capabilities": [
        "Monitors inboxes, systems, schedules and deadlines",
        "Reports on a fixed cadence rather than opportunistically",
        "Escalates by severity so routine findings never interrupt out of hours",
        "Labels every claim as measured or inferred"
      ],
      "hard_limits": [
        "Never decides — presents the decision with evidence and stated confidence",
        "Never reports an unmeasured state as a healthy one",
        "States plainly when it does not know"
      ],
      "human_approval_required_for": [
        "any action arising from a finding"
      ],
      "service_url": "https://getevercrew.com/#service-watch"
    },
    {
      "id": "analyst",
      "name": "The Analyst",
      "role": "Managed AI reporting worker",
      "capabilities": [
        "Pulls figures from systems the business already uses",
        "Compares the current period against the prior one",
        "Verifies its own arithmetic before publication",
        "Shows its working so a figure can be challenged"
      ],
      "hard_limits": [
        "Never invents a number",
        "An unverifiable figure is rendered as unknown, never as zero",
        "Blank means unknown; zero means zero"
      ],
      "human_approval_required_for": [
        "publication of any figure outside the business"
      ],
      "service_url": "https://getevercrew.com/#service-analyst"
    }
  ],
  "supervision": {
    "principle": "An empty board and a healthy one look identical, and only one of them is true.",
    "guarantees": [
      "Silence from a worker is treated as a fault until it proves it looked and found nothing",
      "Every claim is labelled measured or inferred",
      "A value that cannot be established is rendered blank, never as a fabricated zero",
      "A named human repairs failures and reports what happened"
    ]
  },
  "agent_procurement_path": {
    "note": "This provider is designed to be evaluated by an AI agent acting on a human buyer's behalf. Steps 1-3 are fully machine-completable today. Step 4 is a documented action an agent can execute. Step 5 is deliberately human.",
    "steps": [
      {
        "step": 1,
        "action": "GET https://getevercrew.com/roster.json",
        "yields": "workers, capabilities, hard limits, pricing model"
      },
      {
        "step": 2,
        "action": "evaluate workers[].hard_limits against the buyer's brief",
        "yields": "fit or fast, honest disqualification"
      },
      {
        "step": 3,
        "action": "read pricing.model and pricing.status",
        "yields": "billing shape; note that amounts are intentionally absent"
      },
      {
        "step": 4,
        "action": "send enquiry to mailto:hello@getevercrew.com with the brief",
        "yields": "human reply with scope and price"
      },
      {
        "step": 5,
        "action": "human signs the engagement",
        "yields": "crew provisioned"
      }
    ],
    "automated_checkout": {
      "available": false,
      "reason": "No shipping agentic-commerce rail currently supports an agent subscribing a business to a recurring managed service. Consumer retail checkout rails and per-call API metering rails both exist; neither fits this product. Rather than bolt on a payment path that does not match how the service is actually bought, the machine-readable surface stops at a completable enquiry and a human signs."
    }
  },
  "crawling": {
    "ai_crawlers": "allowed",
    "javascript_required": false,
    "server_rendered": true,
    "cors": "Access-Control-Allow-Origin: * on all JSON endpoints",
    "stable_urls": true
  }
}
