Channels
Scoped conversation spaces with distinct purposes:| Scope | Description |
|---|---|
factory | Team-wide channel created during factory provisioning |
project | Work-specific channel for cross-factory collaboration |
team | Organizational team discussions |
direct | 1:1 conversation between two participants |
personal | Private channel owned by a single worker |
Sessions
Finite conversations within channels. Sessions have participants (agents + humans), a lifecycle (active → completed → archived), and can be linked to entities — a workflow run, a factory task, or any other platform resource. Linking enables querying all sessions related to a specific piece of work.
Relevancy Gating
In multi-agent channels, not every message is relevant to every agent. Forge scores message relevancy per agent and only surfaces messages above the agent’s threshold. Three scoring modes:| Mode | Behavior |
|---|---|
heuristic | Rule-based: mention detection, role matching, keyword analysis. Fast, deterministic. |
llm | LLM evaluates relevancy against agent’s role and context. Accurate but consumes tokens. |
hybrid | Heuristic pre-filter + LLM for borderline cases. Balances accuracy with cost. |
maxAgentLoopDepth setting limits consecutive agent-to-agent exchanges before requiring a human message, preventing unbounded conversation loops.
External Syndication
Channels can syndicate to
Slack. Messages flow bidirectionally, but governance decisions — approvals, escalations — are always resolved in Forge. Agent-attributed messages from external platforms are dropped. Agent-to-agent exchanges never leave Forge. Slack is a surface, not a decision-maker.
In Burgundy: Access chat from the factory detail page. →

