See consequential actions
Capture tool calls, shell commands, file access, network destinations, and sensitive data movement at the control point.
While agents act
Control risky agent actions. Before they execute.
Runtime is the part of Signals Corps that checks AI agent actions while they run. Evaluate tool calls, shell commands, file access, and network activity in the flow of work, then allow, warn, request approval, or block.
Priced per device, with free devices on every plan. See pricing
Runtime
Decisions in the moment
Security that understands prompts and the actions they trigger.
Evaluate what an agent is attempting with the identity, tool, destination, repository, and policy context needed to make a useful decision.
Decide with context
Allow routine work, warn when risk is explainable, request approval for ambiguity, and block clear policy violations.
Keep people in flow
Explain the matched rule and offer a safe next step inside the coding session, keeping users in their existing workflow.
How it works
From requested action to explainable decision.
- 01Observe
A hook, gateway, proxy, extension, or API captures the proposed action.
- 02Enrich
Signals Corps adds user, agent, repository, destination, and capability context.
- 03Decide
The shared policy returns allow, warn, approve, or block with matched evidence.
- 04Record
The employee gets an immediate explanation while security receives the audit trail.
Coverage without lock-in
Protect the tools employees already use.
Apply the same intent through the deepest control point each environment exposes. Enforcement strength remains explicit, so availability is never mistaken for automatic protection.
- Claude Code and Codex hooks
- Windsurf, Cursor, and compatible IDE adapters
- Agent frameworks, MCP gateways, and proxies
- Custom agents through the engine API
Runtime capabilities
Move from visibility to enforcement safely.
Policy simulation
Preview decisions against real activity before introducing friction.
Approval workflows
Route exceptional actions to the right owner with their context intact.
Secret boundaries
Stop credentials and sensitive files moving to untrusted tools or destinations.
Local decisions
Keep feedback fast and preserve control where cloud connectivity is constrained.
Session timelines
Reconstruct the actions, policies, approvals, and outcomes behind an event.
Custom policy
Express organization-specific controls without forking every integration.
Headers, llms.txt, and robots.txt compared: what made AI agents act
One sign-up instruction in a header, llms.txt, and robots.txt. Under a plain prompt no Claude agent signed up; granting the site authority moved Sonnet and Haiku, not Opus or robots.txt.
Team Threat Research
Signals Corps Control Plane
Reduce risk across every stage from one security platform.
Set policy, see coverage, stop high-risk actions, and investigate incidents across every agent and team from one operational view.
Author once and adapt decisions to each control point.
Connect users, devices, agents, teams, and tools.
Keep the rule, relevant details, decision, and outcome together.
Deploy one endpoint agent, then manage exceptions, approvals, and reporting.
After agents act
Investigate what the agent did.
Search AI activity and turn agent logs into investigation-ready evidence.