Skip to content
PC Investigator Request access

Less time. More answers.

Tell PC Investigator what a user noticed. It checks the evidence on that device, finds the likely cause and suggests what to do. Nothing runs on the device until you approve it.

Waiting for approvalOne extra checkApproveRejectWindowsAgent · collects evidencemacOSAgent · collects evidenceLinuxAgent · collects evidenceAn administratorapproves every commandYour HubSelf-hosted · keeps the evidenceYour AI providerYour key · only what’s needed

Everything on the grid runs in your environment. Only the evidence an investigation needs goes to your AI provider.

  • Your devices run an agent that collects evidence and connects out over HTTPS.
  • Your Hub is self-hosted and keeps the evidence.
  • Your AI provider gets only what an investigation needs, with your key.
  • An administrator approves every command before it runs.

How it works

Three steps, from a user’s complaint to an answer you can act on.

  1. 1Describe the problem

    In plain words, or start from a ready-made question for that device.

  2. 2It gathers the evidence

    Events, system state and history from the device, read-only, with facts kept separate from guesses.

  3. 3You approve, it explains

    Any extra check waits for you. The result comes back with a clear conclusion and next steps.

AI investigations

Likely causes ranked, with what supports each one and what is still unknown.

An assistant for every device

Ask about one device. Answers show their evidence and end with a conclusion.

A dashboard that triages

Open findings, full disks and offline devices first, everything else after.

Safe by design

Powerful enough to answer hard questions, never powerful enough to get around your controls.

How we keep it safe →
  • Read-only by default

    Investigations only read. The AI can ask for more evidence but cannot run commands on its own.

  • Nothing runs without approval

    Scripts and AI suggestions wait for an administrator, and you can require a second one.

  • Everything is logged

    Roles for viewers, technicians and administrators, and an audit log of every sensitive action.

Runs on your infrastructure

Host the Hub yourself, use your own AI key, and keep the evidence in your environment.

Windows, macOS, Linux

Native agents, installed with one command and updated from the console.

No inbound ports

Agents connect out to your Hub over HTTPS.

Your AI key

Use your own OpenAI, Claude or Gemini key and pick the model. What will it cost?

Docker in minutes

Docker Compose, with a Kubernetes manifest included.

How setup works →

Try it on your own devices

Join early access for the self-hosted preview. Pricing is being shaped with early users. See pricing

Add your company or the problems you want to solve (optional)

No spam. Early-access contact only. See our privacy notice.