Why won’t
my files sync?”

Rapport pairs cloud AI with a local device harness in a conversational workspace for IT. The harness manages the tool loop and permitted execution on each enrolled device. Ask a device why it is slow: the agent runs diagnostic tools on demand on that endpoint, explains what it finds and proposes the next step. Inspect the results, review a proposed action and continue the conversation. Device intelligence, diagnostics, remediation and fleet controls support that central Agent Workspace experience.

No. The homepage shows short, illustrative conversations based on internal workflows. The detailed Agent Workspace walkthroughs condense real internal sessions, with identities removed and wording edited for clarity. Neither connects to a device or executes an action. Supporting fleet examples use fictional data. In your configured workspace, the endpoint agent runs the tools and the gateway calls our AI provider, Anthropic.

Workspace access requires a tenant operator with an MFA-verified session. Enabled tools and configured limits govern the work; held commands are shown for an approve or decline decision. Approval applies to the individual requested command, not every later action. The agent is a privileged service, so these controls do not replace careful scoping of operator access.

No. The AI model runs in the cloud, and the device runs only the tools you permit. AI features are off until your administrator turns them on. When they are on, prompts, conversation context and bounded tool results go through Rapport’s gateway to our AI provider, Anthropic, in the United States. Under our agreement, Anthropic does not keep this data after processing or use it to train models. Provider keys stay server-side, and conversation history is stored in Rapport in the United States. See the AI Use Statement.

Choose Try Rapport to create your account and organization directly. Verify your email and complete multi-factor authentication, then install the signed agent on a supported device using your organization’s enrollment token. Configure AI access and the permitted tools before starting an Agent Workspace conversation. The getting-started guide and illustrated documentation cover each step.

Rapport supports eligible Windows and macOS devices, with Windows MSI and macOS PKG deployment paths. Linux is available as a preview. Measurements and actions vary by operating system and configuration. Check the deployment page for OS versions, installation privileges, hardware guidance and network requirements before enrolling a device.

Routine monitoring never collects keystrokes, screen content, clipboard contents, browsing history, or the content of documents or messages, and Rapport does not score individual productivity. Workforce activity is off unless your organisation turns it on, and is shown only for groups of at least five devices. Support tools that IT staff use when needed (scripts, file transfer and the AI assistant) can access device content, so tell employees how you use them. Our Employee Privacy Notice template helps.

No. AI-assisted investigations use read-only diagnostics to assemble observations and recommend next steps. Device changes follow the enabled endpoint policy and applicable approval and verification requirements. A finding's confidence is an aid to review, not a guarantee of root cause or a permission to execute.

Yes. Patch deployments use maintenance windows, staged rings and evidence gates. Agent releases have a separate choice of individual approval, explicit automatic adoption or hold, with rollout and timing controls. A hold stops future eligible update attempts; an installation already in progress may finish. Device-management administrators still control packages they deploy directly.