Features
Hire AI agents and assign tasks in plain language
Long-running isolated sandboxes with persistent SSD Drive
Live viewing of agent work across files, browser, terminal, and Git
Automate SOPs into reusable Skills and schedule Automations
Connect channels: Slack, Discord, WeChat, Teams, WhatsApp, Telegram, Feishu
Marketplace to install agents, skills, and workflows
Agent Drive per agent, Space Drive for shared files
Multi-agent coordination via Organizer (CEO → Organizer → Claws model)
Approval-first agent workflows (human-in-the-loop)
Top-up credits that never expire, shared across agents in a Space
REST API for programmatic hosted agents
Embed agent workspaces and MCP support
Supports 18 frontier AI models with credit-based usage
Image generation (Nano Banana 2, GPT Image 2)
Video generation (AI video from prompts)
No-code visual workflow builder
Omnichannel deployment (web, phone, mobile)
Low-latency voice (500ms)
High throughput (300k messages/min)
Integrated prototyping and NLU modeling
Entry conditions for playbooks/workflows
Required variables for workflows
Organization-level usage breakdown
Voiceflow Core optimized model (May 2026)
Transcript filtering by workflow and tool
