See Qpoint in Action
Short recordings of Qpoint running underneath real agents as a real-time, dynamic sandbox for macOS, Windows, and Linux.
Control the hidden agent surface
Agents write and run scripts, and the agent harness can’t see which files those scripts read or where they send requests. Qpoint runs underneath the agent, so its policies apply to what those scripts do. In the demo, one rule flags any read of a secrets file, catching Claude Code with curl and again with a Python script, then blocks the read when the rule is switched to deny.
Enforce an agent’s purpose
An agent often needs permission to use a tool, but not for everything that tool can do. A pull request review agent needs to post comments, for example, but it shouldn’t approve the PR on behalf of the team. Qpoint uses a System One model to check each action against the purpose you define for the agent, so the review comments go through and the approval is blocked, even when the project’s instructions tell the agent to approve it.
Catch an agent retrying a denied action
When an agent is blocked from doing something, it often tries again a different way. Qpoint looks at the recent history of the session to tell when a new action is really a workaround for something that was just blocked. In the demo, an agent that can’t comment on GitHub through its MCP server tries the GitHub CLI instead, and Qpoint catches it.
Restrict where agents send data
Agents need to read from the web, but you probably want control over where they send data. With this policy, agents can still read from any site, but they can only send data to destinations you’ve approved. It also blocks the agent’s own telemetry from being sent out.
Keep agents out of your secrets
Most machines have files with passwords and tokens that any agent can read. A single Qpoint policy stops agents from reading those files, whether they open the file directly, use a command, or write a script to do it. In the demo, the policy stops both Claude Code and Grok.
Catch a poisoned skill
Skills from outside marketplaces can contain hidden instructions, such as quietly sending files off the machine. Qpoint uses a System One model to review any skill that isn’t already trusted before the agent loads it. In the demo, a skill that sends out a credentials file is caught, and normal skills still load as usual.
Allowlist skills and MCP servers
Most teams want to control which skills and MCP servers their agents use. With Qpoint, you keep a list of the approved ones, and anything that isn’t on the list is blocked. When you add a new one, it works right away, without restarting the agent or changing how anyone works.
Block destructive changes with an intent-based policy
Agents can do serious damage, like wiping a production database or turning off backups. Instead of trying to list every risky command, you describe what you don’t want in plain English, and Qpoint checks each action against that description. In the demo, a request to reset a database without a backup is blocked in both Claude Code and Grok.