Queue steering - Chat - CLI - Docs - Kiro
https://kiro.dev/docs/cli/chat/queue-steering/ • 212 KB fetched Open original page
Queue steering - Chat - CLI - Docs - Kiro
Loading image... Product
* About Kiro
* IDE
* CLI
* Web
* Mobile
* Crew
* Pricing
* Downloads
For
* Enterprise
* Startups
* Students
Community
* Overview
* Ambassadors
* Discord
* Events
* Powers
* Shop
* Showcase
Resources
* Docs
* Blog
* Changelog
* FAQs
* Report a bug
* Suggest an idea
* Billing support
Social
*
*
*
*
*
*
*
English
Site Terms License Responsible AI Policy Legal Privacy Policy Cookie Preferences English
Loading image...
* Apps
* CLI
* Web
* Enterprise
* Pricing
* Docs
* Community
* Resources
SIGN IN DOWNLOADS
Loading image...
Get Started
Installation Authentication Your first project
Models
Overview Available models Reasoning effort
Features
How Kiro works Specs
Steering Hooks
MCP
Permissions Custom agents
Agent Skills Powers
Cloud sessions Compaction Kiroignore Checkpoints and rewind Built-in tools
Configuration scopes
IDE 1.x
What's new in 1.0
Setup & First Run Editor
Chat
Experimental
Troubleshooting 0.x reference
CLI
What's new in 3.0
Setup & First Run Terminal UI
Chat
Session management
Goal
Queue steering
In-session settings
Prompts
File references
Context management
Responding to messages
Working with Git
Images
Custom diff tools
Voice mode Headless mode ACP Auto complete Experimental
2.x reference
Crew
Quick start Installation Running 24/7 Chat
Agent Capabilities
Features
Interfaces
Apps
System & storage Configuration Security Troubleshooting
Web
Setup & First Run Identity Center Connect your repositories
Working with the agent
Autonomous mode Automations Memory Configuration Sync Sandbox
Mobile - Preview
Overview
Commands and Reference
CLI commands Slash commands Built-in tools Exit codes Settings
Billing
Overview Managing your subscription Upgrading your plan Downgrading your plan Cancelling your plan Purchasing add-on credits Managing your payments Managing usage notifications Managing your taxes Contacting billing support Deleting your account Related questions
Enterprise
Concepts Onboarding quickstart Connecting your identity provider
Deployment options Subscribe your team Manage subscriptions Governance
Monitor and track
Settings Managed updates Billing IAM Supported regions
Privacy and Security
Overview Data protection Code references Compliance validation Infrastructure security IAM permissions Firewalls, proxies, and data perimeters VPC endpoints (AWS PrivateLink)
Guides
Overview Language support
Learn by playing
Migration
Migrating from Q Developer Migrating from VSCode Upgrading from Q CLI
* Docs
*
* CLI
*
* Chat
*
* Queue steering
Copy page View as Markdown
Queue steering
Copy page View as Markdown
Mid-turn steering lets you type a follow-up message while the agent is actively processing. Instead of waiting for the agent to finish or cancelling and starting over, you can send guidance that the agent incorporates into its work.
Kiro offers two follow-up modes that control when your message reaches the agent:
Mode Behavior Best for
Steer (default) Message reaches the agent mid-turn so it can adjust course Real-time course correction
Queue Message buffered locally, sent after turn ends Batching multiple follow-ups
Press Ctrl+S to switch between steer and queue modes.
How it works
Steer mode
* Type your message and press Enter while the agent is working
* Your message is sent to the agent
* The agent picks it up mid-turn at the next safe point and incorporates it
* The agent sees your guidance and adjusts its approach
* The agent acknowledges how it handled your input
Queue mode
* Type your message and press Enter while the agent is working
* Your message is added to a local buffer (visible in activity tray)
* The agent finishes its current turn normally
* The first queued message is sent as a new prompt
* Process continues until the queue is empty
When the agent sees your message
In steer mode, your message reaches the agent during the current turn and is picked up at the next safe point in its work — without interrupting an action that's already in progress. Multiple messages sent in steer mode are concatenated and delivered together.
Usage
Type and press Enter while the agent is working:
bash
> Refactor the auth module
[ Agent starts working, reading files .. . ]
> Actually, focus on the login function first
[ In steer mode: sent to the agent mid-turn ]
[ In queue mode: message added to local buffer ]
Viewing queued messages
The activity tray shows your pending messages:
* Press Ctrl+X to expand the activity tray
* The tab shows "Steer" (steer mode) or "Queue (N)" (queue mode with N items)
* Press Delete or Backspace to clear the message or selected item
Cancel and redirect
Press Ctrl+C or Esc while a steering message is queued to implement "stop that and do this instead":
* The current operation is cancelled
* Your queued message is automatically sent as a new prompt
bash
> Write unit tests for the user service
[ Agent starts writing tests .. . ]
> Actually, let 's do integration tests
> [press Ctrl+C or Esc]
Redirecting to: Actually, let' s do integration tests
[ New turn starts with integration test focus ]
Steer vs. queue vs. cancel
Action What happens Use when
Steer (type + Enter) Agent adjusts mid-turn at the next safe point You want immediate course correction
Queue (Ctrl+S, then type) Messages buffer, sent after turn ends You want to batch multiple follow-ups
Cancel (Ctrl+C or Esc) Agent stops, queued steer message sent as new prompt You want to stop and pivot immediately
Configuration
Set the startup default via /settings → terminal → interrupt behaviour .
Limitations
* Steer mode : Only one message slot — multiple messages concatenate with \n\n
* Queue mode : Messages sent sequentially, not batched
* Timing dependent : If the agent finishes before your message is queued, it becomes a normal prompt
Related
* Goal — autonomous agent loop with built-in verification
* Responding to messages — how to interact with agent responses
* Rewind — fork a conversation at an earlier turn
* Settings — configure keybindings and display preferences
Page updated: August 4, 2026
Goal
In-session settings
Links found on this page
- About Kiro [direct]
- IDE [direct]
- CLI [direct]
- Web [direct]
- Mobile [direct]
- Crew [direct]
- Pricing [direct]
- Downloads [direct]
- Enterprise [direct]
- Startups [direct]
- Students [direct]
- Overview [direct]
- Ambassadors [direct]
- Discord [direct]
- Events [direct]
- Powers [direct]
- Shop [direct]
- Showcase [direct]
- Docs [direct]
- Blog [direct]
- Changelog [direct]
- FAQs [direct]
- Report a bug [direct]
- Suggest an idea [direct]
- Billing support [direct]
- Site Terms [direct]
- License [direct]
- Responsible AI Policy [direct]
- Legal [direct]
- Privacy Policy [direct]
- Cookie Preferences [direct]
- Loading image... [direct]
- SIGN IN [direct]
- Installation [direct]
- Authentication [direct]
- Your first project [direct]
- Overview [direct]
- Available models [direct]
- Reasoning effort [direct]
- How Kiro works [direct]
- Specs [direct]
- Steering [direct]
- Hooks [direct]
- MCP [direct]
- Permissions [direct]
- Custom agents [direct]
- Agent Skills [direct]
- Powers [direct]
- Cloud sessions [direct]
- Compaction [direct]
- Kiroignore [direct]
- Checkpoints and rewind [direct]
- Built-in tools [direct]
- Configuration scopes [direct]
- What's new in 1.0 [direct]
- Setup & First Run [direct]
- Editor [direct]
- Chat [direct]
- Experimental [direct]
- Troubleshooting [direct]
- 0.x reference [direct]
- What's new in 3.0 [direct]
- Setup & First Run [direct]
- Terminal UI [direct]
- Chat [direct]
- Session management [direct]
- Goal [direct]
- In-session settings [direct]
- Prompts [direct]
- File references [direct]
- Context management [direct]
- Responding to messages [direct]
- Working with Git [direct]
- Images [direct]
- Custom diff tools [direct]
- Voice mode [direct]
- Headless mode [direct]
- ACP [direct]
- Auto complete [direct]
- Experimental [direct]
|
|