AI agents for specific business functions that rehearse tasks as test runs before execution
Real-time steering and guardrails for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
DE
Not given
Pricing model
Paid
Freemium
Pricing
Roles range from € 99 to € 499 per month excluding VAT, with included monthly tasks varying by role: Administrative Assistant and Association Secretary at € 99/mo (40-45 tasks); Secretary at € 109/mo (50 tasks); Process Documentation and Planner at € 129/mo (15-40 tasks); Customer Service at € 229/m
Team: Free per organization, unlimited users, 200 session-hours per month. Enterprise and Gateway: Custom pricing, billed annually.
Key features
Pre-built roles from a catalogue (31 roles)
Fingerprint verification on approval (SHA-256)
Full audit trail of proposals, test runs and approvals
Integration with 12+ pre-connected services
Custom REST API and MCP server connections
Servers in Germany within EU
AI Act compliance file (limited risk classification)
Reads every tool call agents make and blocks unsafe ones before they run
Catches stalled and runaway sessions while they run
Steers agents back when they go past what was asked
Tracks every session's tokens against usual usage
Stops credential and data leaks before they leave the machine
Inventories all agents, MCP servers and skills in use
Blocks dangerous calls before they run in agent hooks and at the gateway
Sends every finding to Slack, webhook or SIEM
Verifies each agent's identity before access
Keeps audit-grade masked records of every action and decision
What makes it different
Test runs show actual outcomes with no side effects before real execution
No automatic approvals—every proposal requires explicit human approval
Approved test run and execution count together as one task, not two
Declined proposals are free and don't count against quota
Works with Claude Code, Codex, Cursor, Devin and more
Runs on your machines, gateways and in the cloud
Active steering corrects or stops drifting runs
One policy applied across all MCP servers, plugins and skills
Continuously monitors components for known vulnerabilities
Stilops
Stacktrace