Docs

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

Chat Sessions & the Universal Harness

One universal chat harness backs every channel, so permission modes and turn behavior are identical whether you're on the dashboard, Slack, or WhatsApp.

ChatSessions
Permission Modes: Ask, Plan, Auto

Sticky Ask, Plan, and Auto autonomy modes, and the novelty-based intelligent stop that decides when an agent has said enough.

PermissionsAutonomy
The Agent Terminal

The per-agent terminal pane: direct operator-to-agent messaging and history, realtime over the conversation room.

Terminal
Broadcast & @Mentions: Agents Talking to Agents

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.

BroadcastMentions
The Interactions Feed: Watch Agents Work Together

A single time-ordered timeline unifying agent-to-agent chat and activity events — the read-only 'watch them work' view.

InteractionsObservability
The Command Palette

Cmd+K search and execute across apps, workflows, agents, gateways, runs, approvals, extensions, and conversations.

Command paletteProductivity
Memory Capture From Chat

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.

MemoryChat
Chat Reliability: Watchdogs, Turn Deadlines & Budgeted Context

The idle watchdog, turn deadline, budgeted context window, and tool cap that keep a chat turn from running away.

ReliabilityLatency

Continue