Features
AI agent builder from natural language or SOPs
Live View: watch, intervene, and guide agents in real time
Run agents on Browser, Linux, or Windows environments
Gen 2 agents: write code, self-heal, and learn over time
Hybrid DOM-plus-vision approach for reliability
HIPAA compliance (BAA on Startup+)
Credit-based usage covering runtime, LLM, and proxies
Agent catalog with pre-built agents
Integration via API, Slack, Email, Google Sheets
Multiple concurrent environments (5-100+)
Frontier models including computer-use agents (CUA)
Visual graph editor for workflow creation
Portal search for thousands of web portals
Pay-as-you-go credits portable across runtime, LLM, proxies
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
