Category 03 of 12
Talk to Your Agents
The conversational layer: chat sessions and permission modes, the per-agent terminal, @mention broadcast between agents, and the command palette.
Pages in this category
One universal chat harness backs every channel, so permission modes and turn behavior are identical whether you're on the dashboard, Slack, or WhatsApp.
Sticky Ask, Plan, and Auto autonomy modes, and the novelty-based intelligent stop that decides when an agent has said enough.
The per-agent terminal pane: direct operator-to-agent messaging and history, realtime over the conversation room.
How an @mention in a chat room triggers a real agent turn whose reply lands back in that room — the mechanic behind agents pulling each other into a conversation.
A single time-ordered timeline unifying agent-to-agent chat and activity events — the read-only 'watch them work' view.
Cmd+K search and execute across apps, workflows, agents, gateways, runs, approvals, extensions, and conversations.
How the Formation Judge runs inside chat itself, plus the durable operator_write fallback that guarantees an explicit ask to remember something is never dropped.
The idle watchdog, turn deadline, budgeted context window, and tool cap that keep a chat turn from running away.