📄️ Introduction
Agent prompts are the instructions that define how agents behave, talk to each other, and collaborate. Configure them from the dashboard: click ⋮ → Manage prompts on any agent.
📄️ Agent Types
Four types of agents. Each has a specific job and a specific memory model — picking the right type is the first decision you make when designing a swarm.
📄️ Conversation Flow
How swarm AI actually plays out: who sees what, when each prompt runs, and how memory bridges conversations over time.
📄️ Expert Prompts
Expert agents provide specialised knowledge in a single domain. They have three prompts ⋮ → Manage prompts.
📄️ Facilitator Prompts
The facilitator is the conversation orchestrator. It has three prompts ⋮ → Manage prompts.
📄️ Human & Digital Twin
Human agents and digital twins bridge AI and human participants. Humans have no prompts — they type in Slack. Digital twins are AI clones of a human, created from that human's conversation history.
📄️ Dynamic Fields Reference
Agent prompts are Go templates. Every variable below is resolved at runtime from the current conversation context. Use double curly braces ({{ .VariableName }}) and optionally trim whitespace with {{- / -}}.
📄️ Prompt Templates
Two ready-to-use templates covering the two core agent roles. Copy them, replace the domain-specific bits, and paste into the dashboard's prompt editor.
📄️ Prompt Writing Guide
Practical patterns that work across agent types. Read this once, then use Prompt Templates as your starting point.