Security at AgentTeams

Enterprise-grade security for your AI workforce.

Data Protection

AES-256 encryption for all data at rest
TLS encryption for all data in transit
Agent credentials encrypted with dedicated encryption keys
No customer data used for model training

Access Control

Role-based access control across your organization
OAuth 2.0 authentication via Google (more providers coming)
Per-agent permissions scoped to specific tools and data
Comprehensive audit log for every action taken

Infrastructure

Hosted on Google Cloud Platform (GCP)
Cloud SQL with automated daily backups
Cloud Run for isolated, auto-scaling containers
No shared tenancy — your data is fully isolated

Compliance

Working toward SOC 2 Type II certification
GDPR-aware data handling practices
Data residency options coming soon
Regular third-party security assessments planned

Agent Guardrails

Supervised and autonomous modes for every agent
PM agent reviews sensitive actions before execution
Human approval workflows for high-stakes operations
Confidentiality guardrail scans all agent outputs before delivery

Questions about security?

We are happy to walk you through our security practices and answer any questions your team may have.