Features
No-code agent builder with drag-and-drop actions
Centralized agent registry with verification and revocation
Role-based access control (RBAC) across teams
Automatic permission mirroring from 50+ sources
Human-in-the-loop approval for sensitive actions
PII redaction before model processing
Full audit logging with export to Splunk, Datadog
Multi-model support: Claude, GPT-4o, Gemini, custom LLMs
Risk monitoring with real-time alerts and blocking
Multi-agent workflow orchestration
Action-level governance with per-action approvals
Cloud-hosted, single-tenant, and on-prem deployment
SAML/SCIM and Okta integration
SOC 2 Type II and HIPAA-ready compliance
50+ pre-built data source integrations
No-code agent builder (Invent) with natural language description
Drag-and-drop multi-agent workflow canvas (Workforce)
Built-in agent evaluation and quality scoring (Evals)
Human-in-the-loop oversight with approval gates
Real-time monitoring dashboard with Timeline view
Role-based access controls (RBAC) and audit logs
PII masking and data residency controls
LLM-agnostic: supports Claude Sonnet, GPT-5.5, Claude Opus 4.7, Gemini 3.5 Flash
Gemini 3.5 Flash with 1M-token context and 64K-token output
100+ pre-built integrations including HubSpot, Gmail, Salesforce, Confluence, Notion
Agent escalation when confidence is low
Scheduling and triggers for automated execution
Confluence Knowledge Sync for auto-updating knowledge bases
MCP access for Member role
Version control and rollback for agents and tools
