US$120 per agent per month, with a 30-day free trial (card required, nothing charged until it ends). Larger teams pay less: the rate drops by $1 for each agent added through the ninth, settling at US$110 per agent from 10 onwards. You bring your own model key and pay the provider directly for tokens
Free tier available to automate first process with no credit card required. Enterprise pricing is consumption-based, scaling with volume of automated transactions and complexity of agents rather than per-bot or per-user licensing.
Key features
AI software engineer agent
AI product manager agent
AI QA engineer agent
AI systems architect agent
AI SRE (Nadia Serrano)
GitHub, Linear, Slack and Microsoft Teams integration
Incident investigation workflow
Release verification
Granular permissions per agent
30-day free trial with no credit card charge
Hallucination-free AI automation through deterministic execution
English as Code for plain English programming of workflows
Patented Time Machine runtime with pause-patch-resume capability
200+ pre-built enterprise integrations
Builder Agent for no-code workflow creation
Symbolic Executor for deterministic execution
Resolution Agent for automatic exception handling
Context Graph for auditable business decisions
Role-based access control and audit governance
What makes it different
No separate token metering—you bring your own model key and pay the provider directly
Agents operate only with permissions you explicitly grant and can revoke
All changes require human approval before reaching production
One price per agent regardless of specialization
Integrates with tools your team already uses
Deterministic execution with zero hallucinations, unlike probabilistic AI systems
English as Code lets business users build automation without developers
12x lower maintenance cost compared to traditional RPA
Consumption-based pricing that scales with transaction volume, not per-bot licensing
Production deployment in 14-30 days for single workflows