{"@context":"https://schema.org","@type":"FAQPage","id":"agentcheck-qa","mainEntity":[{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"A visitor-side review for AI chatbots and agents. AgentCheck chats with your bot through its public chat window the way a regular customer does, and checks what it actually tells people: promises it was never given, prices and policies that do not match your website, private details it should not repeat, and what it does when it does not know the answer. It delivers a written report in plain English, with every finding marked Critical / Warning / Passed and a step-by-step fix plan. No calls, no passwords, no code access."},"name":"What is AgentCheck?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Fixed prices, known before you order. The AgentCheck Audit is $149 one-time (a full visitor-side review of one chatbot). The Full Audit is $299 one-time (all five checks in depth, a setup review, and a free re-check within 30 days). Agent Guard monitoring is $49/month, cancel anytime. A free mini-check is also available. Prices in USD."},"name":"How much does AgentCheck cost?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Whether a pushy visitor can talk the bot out of its rules (discounts or promises the business never made); whether it keeps private details private (other customers' details, internal notes, setup text); whether its prices and policies match the ones on the website; how it handles rude and off-topic visitors; and whether it gets stuck in loops or answers that never end. The Full Audit adds a setup review: what the agent is connected to, where its API keys live, whether it works under hard limits, and whether its actions are logged outside the agent."},"name":"What does AgentCheck check?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"No. We talk to your chatbot the same way a customer does: through its public chat window. No passwords, no API keys, no code access, nothing to install."},"name":"Do you need access to my systems, passwords, or code?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"We start once we have your details and payment. The report arrives by email."},"name":"How long does an audit take?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Custom GPTs, Claude projects, Intercom / Drift / Tidio / Zendesk widgets, custom API agents, and most website chatbots. If customers can talk to it, we can review it."},"name":"Which chatbots and agents can you audit?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Yes. The free mini-check reads your public pages the way a careful visitor would: which chatbot you run, whether anything sensitive is visible in your page source, and whether the HTTPS and privacy basics hold up. It is instant, shown on screen and by email — no calls, nothing to install."},"name":"Is there a free check?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Then your report says so, check by check — and you keep a written record of what your agent told a visitor on that day. That record is what insurers or partners ask for."},"name":"What if the audit finds nothing wrong?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"No. A review is a snapshot: it shows how your agent answered on the days we checked it. Changing its instructions, its model, or a connected tool can change its answers afterwards — which is why Agent Guard re-checks after every update. Anyone who promises permanent safety is overselling."},"name":"Does a clean report mean my agent is safe forever?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"The setup review in the Full Audit ($299). Based on the setup details you share, it lists what your agent is connected to — files, email, calendars, payment tools, your network — and flags the connections its job does not need. It also notes where API keys are stored, whether the agent works under hard limits such as spending caps and approval steps, and whether its actions are logged outside the agent itself."},"name":"What is the setup review?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"An agent should never be able to move money, delete data, or widen its own permissions without a human approving that specific action. Give it only the access its job needs — read-only where possible."},"name":"What permissions should an AI agent never have?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Never inside the agent's own instructions or chat text, where they can surface in its answers. Keys belong in a separate, access-controlled store, handed to the agent's tools only at the moment of an approved action."},"name":"Where should an agent's API keys be stored?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"Agent Guard ($49/month) keeps watching your agent after the review: scheduled re-checks of its public chat window, alerts when its answers change, and a written review after every bot update. Guard monitors from the outside — it does not sit inside your systems, so spending limits stay in your own provider settings, where only you control them. Cancel anytime."},"name":"What is Agent Guard?"},{"@type":"Question","acceptedAnswer":{"@type":"Answer","text":"If we haven't started the work yet, you get a full refund. Once work has begun, payments are non-refundable. Agent Guard is a monthly subscription and can be cancelled anytime."},"name":"What is the refund policy?"}],"schema_version":"ado-qa/1.0","url":"https://getshieldcheck.com/agentcheck/"}