Features
Deploy named AI agents with specific roles and SOPs
Persistent short-term, mid-term, and long-term memory with vector search
Isolated agent containers with safety layer and human approval for high-stakes actions
Desktop automation via full Linux/Windows VMs (real browsers, desktop apps, RPA)
Platform-level integrations shared across agents (no per-agent reauthentication)
Cloud-hosted infrastructure (nothing to install or maintain)
Pre-configured starter teams (Sales, Engineering, Customer Ops)
Multi-team coordination and advanced workflows on higher plans
Custom integrations via Xircuits component libraries and MCP servers
Audit trails and governance for enterprise compliance
Chat, voice, and email communication channels
Open-source local runtime (XpressCLAW) for on-premise testing
3GB to 200GB knowledge storage depending on plan
Task management for agent assignments
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
