AI-native managed operations for service businesses
A persistent team of coding agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
GB
Not given
Pricing model
Paid
Open source
Pricing
Setup fee: £350–£500 (one-time). Monthly retainer from £750/month: Essentials plan £750/month for one managed workflow; Growth plan £1,200/month for multiple workflows; Advanced plan £2,000+/month for full operations coverage.
Not given
Key features
Capture enquiries from website, email, chat, or WhatsApp 24/7
Respond to common questions using approved business information
Qualify leads by collecting customer details and identifying intent, urgency, and service fit
Apply human oversight to uncertain, sensitive, or high-value cases
Execute actions including booking, routing, follow-ups, and document collection
Deliver ready-to-act lead summaries with all details structured for immediate handover
Automated appointment booking and callback routing
Review management and automated review request campaigns
Client intake and automated document collection
Weekly workflow performance review and continuous improvement
Start teams with one command and manage agents across multiple machines
Mix Claude Code, Codex and Pi agents in one team
Agents delegate and coordinate work with named task assignments and queue ownership
Agents message each other directly and read each other's screens
Restore agent conversations after restart or reboot from snapshots
Choose different models and reasoning effort per agent
Bring custom harnesses and integrate with MCP servers and Claude Desktop
Start Docker Compose services alongside agent teams
Control message filtering with typing guards and chat broadcasts
What makes it different
Managed service, not software — we run the workflow and bear operational responsibility, not you
Human-in-the-loop by design with automatic escalation of sensitive and regulated enquiries
Outcome-based pricing reflects value delivered, not features or hours
Start with a focused pilot — prove value with one workflow before expanding
Approved knowledge base ensures AI responds only from verified business information, no AI guessing
One conversation interface with a lead agent coordinating specialists behind the scenes
Mix multiple coding models and harnesses in one managed team
Run entirely self-hosted on your own machine with no external coordination
Open source with Apache 2.0 license and extensible harness contracts
Cognumi
OpenRig