Put a conversation on your automation.
A real-time chat interface for your robots. Business teams operate complex back-end systems by chatting with a robot — Guided step-by-step, or Conversational with an AI agent.
Two modes, one canvas
Present rich, governed input in Guided mode, or hand the conversation to an AI Agent in Conversational mode — the same nodes and robot power both.
Like ChatGPT, backed by your agents
A free-form chat the user drives, usually backed by an AI Agent node. The agent reasons over the question, calls its RPA tools, and streams a clean answer in real time.
- A free-form chat box, like talking to ChatGPT — backed by an AI Agent node.
- The agent reasons, calls your RPA flows and tools, then streams the answer back live.
- Best for open-ended Q&A, assistants, and agentic sessions that decide what to do.
The flow drives, step by step
The robot presents structured widgets and waits for each answer before moving on. It's the deterministic way to capture controlled input and walk a person through a process.
- The robot presents structured widgets — buttons, dropdowns, date pickers, text, file upload.
- Each step blocks and waits for the answer, then the flow moves on. Fully deterministic.
- Best for wizards, checklists, controlled data capture, and "operate this system for me" flows.
Everything the chat can do
16+ widget types, real-time streaming, secure file exchange — all from drag-and-drop nodes.
Rich input widgets
ButtonGroup, Dropdown, Checkbox, Radio, Datepicker, and Textbox — each blocks and waits for the user.
File exchange
Users upload documents to the robot, and the robot can offer files back — even as a public link.
Streaming & progress
Stream an LLM answer token-by-token, or show a live progress indicator the flow updates in place.
Pairs with AI Agents
Chat In → LLM Agent (with your tools) → Streaming Text → Chat Out. The Chat Assistant is how an agent gets a face.
End-to-end encrypted
Browser and robot negotiate keys (RSA then AES-256-GCM); the proxy only routes ciphertext, never reads it.
One canvas, both modes
Guided widgets or a free-form agent — the same nodes and robot power both, chosen per flow.
Give your automation a face
Teams learn one chat; the robot runs the back-end systems. Build a Guided wizard or an agentic assistant on the same canvas.