Admin panel
Centralized management for team administrators to configure Warp settings, control agent behavior, and enforce security policies across your organization.
The Admin Panel provides administrators with centralized control over team settings in Warp. Configure agent behavior, security policies, codebase indexing, and collaboration features for your entire organization from a single interface.
What is the Admin Panel?
The Admin Panel is your control center for managing Warp at scale. It allows IT admins, platform teams, and engineering managers to:
Control agent behavior - Set autonomy levels, command permissions, and safety guardrails organization-wide
Enforce security policies - Configure secret redaction, telemetry controls, and data handling
Manage team resources - Enable Codebase Context, configure BYOLLM, and control sharing permissions
Monitor usage - Track credit consumption and set spending limits
Maintain compliance - Apply consistent policies that meet your organization's security requirements
Warp restricts Admin Panel access to team administrators. Regular team members can view settings that affect them but cannot modify organization-wide policies.
Accessing the admin panel
For team admins
Access the Admin Panel in two ways:
Option 1: Direct URL
Navigate to app.warp.dev/admin.
Log in with your SSO credentials.
The Admin Panel opens with all organization settings.
Option 2: From Warp Settings
Open Warp and click your profile icon in the top right.
Click Settings.
Navigate to the Admin Panel tab (visible only to team admins).
For team members
Team members see organization-enforced settings in their personal Settings panel:
Settings controlled by admins appear grayed out
Indicated by message: "Your organization has configured this setting"
Users retain control over settings where admins have selected "Respect User Setting"
How settings enforcement works
The Admin Panel uses a three-tier enforcement model that keeps administrators in control while allowing appropriate flexibility.
Setting enforcement levels
Organization enforced
Setting applies to all team members regardless of individual preferences
Users cannot override these settings
Use for security-critical policies (e.g., secret redaction, command denylists)
Respect user setting
Allows individual team members to control the setting themselves
Admins set a default, but users can customize
Use for preferences that don't impact security or compliance (e.g., AI model selection)
Tier restricted
Setting is locked based on billing plan
Cannot be changed until plan is upgraded
Indicated by message: "Configuring this setting is not available on your plan"
Testing before enforcement
Changes made in the Admin Panel take effect immediately for all team members. Test settings in your own Warp environment before applying organization-wide enforcement.
To safely roll out new policies:
Configure settings with "Respect User Setting" initially.
Test with a small group of users.
Gather feedback and adjust configuration.
Switch to "Organization enforced" once validated.
Plan limitations
The features available in the Admin Panel scale with your Warp plan:
Free tier
Most settings are fixed and non-configurable
Limited Codebase Context (2 repositories)
No BYOLLM support
Basic sharing features
Business plans
Most settings become configurable by administrators
Enhanced agent autonomy control
Advanced sharing and privacy features
Increased Codebase Context limits
Enterprise plans
Full admin control - Configure all available settings
Enterprise secret redaction - Custom regex patterns for secrets
BYOLLM - Route inference through your cloud infrastructure
Self-hosting cloud agent workers - Deploy Oz cloud agent workers on your own infrastructure
Advanced compliance - SOC 2, HIPAA, and custom data handling agreements
Priority support - Dedicated Slack/Teams channels
For complete plan details, visit warp.dev/pricing or contact sales.
Admin panel sections
The Admin Panel is organized into five main areas:
AI settings
Configure how agents behave across your organization, including autonomy levels and command permissions. This is where you balance agent productivity with organizational safety requirements.
General AI settings
AI in remote sessions
Controls whether agents are available during SSH sessions and remote connections
Enterprise plans can toggle this setting
Consider disabling for production servers or sensitive environments
Prompt summarization caching
When conversations become long, the LLM provider caches summaries temporarily
Improves performance for extended agent interactions
Zero Data Retention agreements cover caching (short-lived)
Autonomy settings
Configure how much independence agents have when performing actions. Choose between:
Agent Decides - Agent acts autonomously when confident, asks when uncertain (recommended)
Always Ask - Require explicit approval for every action
Always Allow - Maximum autonomy without confirmations
Respect User Setting - Allow individual users to set their preference
Apply code diffs Controls whether agents can apply code changes without approval. For production-critical codebases, consider "Always Ask" to maintain tight control.
Create plans Whether agents can create structured task plans (/plan command) without user approval.
Execute commands Manages the agent's ability to run terminal commands autonomously. Pair with command allowlists/denylists for granular control.
Read files Controls agent access to reading files in the codebase. Enable for better context, restrict for sensitive repositories.
Directory and command control
Directory allowlist Specify directories where agents can read files without restriction. Use absolute paths:
~/git/internal-tooling- Grant access to specific projects/home/user/repos/public-*- Use wildcards for patterns
Command allowlist Regular expressions matching commands agents can execute without asking permission. Common patterns:
grep .*- Text searchls(\\s.*)?- Directory listinggit status- Version control querieswhich .*- Finding executables
Command denylist Regular expressions for commands that always require explicit user approval, regardless of autonomy settings:
rm -rf.*- Recursive deletionsudo.*- Administrative commandscurl.*|wget.*- Network requestsdocker rm.*- Container operations.*production.*- Commands containing "production"
Command denylist rules take precedence over allowlist rules and agent autonomy settings. Use denylists to prevent high-risk operations even in high-autonomy configurations.
Privacy settings
Manage data collection and security policies to meet your organization's compliance requirements.
User-generated content (UGC) data collection Controls how Warp collects and uses user-generated content to improve the service:
Disabled - Warp collects no UGC data from your organization
Enabled - Allow data collection for service improvement
Respect User Setting - Let individual users decide
Enterprise teams with Zero Data Retention agreements can disable this completely.
Enterprise secret redaction Automatically detects and redacts sensitive information before sending data to LLM providers:
Enterprise plans enable this by default
Includes automatic detection of common secret patterns (API keys, passwords, certificates)
Supports custom regex patterns for organization-specific secrets
Applies unconditionally across all team members
Configure custom patterns in the Admin Panel to match your organization's secret formats.
Code settings
Control codebase indexing and agent code features for your team.
Codebase Context Determines whether Warp indexes your team's Git repositories to provide context for agents:
Disabled - No codebase indexing
Enabled - Index codebases for improved agent responses across large, multi-repo systems
Respect User Setting - Allow individual control
When enabled, agents understand your code patterns, architecture, and conventions across all indexed repositories. Enterprise plans support:
Unlimited repositories
Up to 200,000 files per repository
Team-wide indexing with centralized configuration
Billing settings
Configure billing preferences and spending controls to manage costs at scale.
Usage-based pricing Enable pay-as-you-go billing for credits beyond your plan's included quota:
Set monthly spending limits to control costs
View current overage usage and costs
Receive alerts when approaching spending thresholds
Credit allocation For Enterprise plans with negotiated credit pools:
Allocate credits across teams or projects
Monitor usage by team
Set per-team spending limits
Contact your account manager to configure advanced credit allocation.
Sharing settings
Control how team members collaborate and share Warp Drive resources.
Direct link sharing Allow team members to share Notebooks, Workflows, Prompts, and other Warp Drive objects via direct links:
Enabled - Team members can generate shareable links
Team only - Links work only for team members
Disabled - No link sharing
Anyone with link sharing Enable public access to shared objects:
Enabled - Anyone with the link can view content without being a team member
Disabled - Links require team membership to access
For organizations with sensitive internal processes, disable "Anyone with link" sharing to prevent accidental exposure.
Multi-admin functionality
Warp supports multiple team administrators to prevent single points of failure and enable distributed management.
Promoting and demoting admins
Team admins can grant or revoke admin privileges:
Navigate to Settings > Teams > Team Members.
Find the user you want to modify.
Click the role dropdown next to their name.
Select Admin or Member.
Click Save.
We recommend at least one admin in addition to the Team Owner to prevent access issues if one is unavailable. The Team Owner has full access and can transfer ownership; Team Admins have the same permissions except they can't transfer ownership.
Admin activity tracking
For audit purposes, admin actions are logged and visible to all team admins:
Settings changes (what changed, when, by whom)
User role modifications
Team membership changes
Billing and spending limit adjustments
Access admin activity logs through the Admin Panel under Settings > Audit Log.
Common admin workflows
Initial enterprise setup
After purchasing a Warp enterprise plan:
Configure SSO - Set up authentication with your identity provider.
Enable Codebase Context - Index your organization's repositories.
Set agent autonomy - Configure initial safety levels.
Apply secret redaction - Add custom patterns for your organization.
Configure BYOLLM (optional) - Route inference through your cloud accounts.
Create shared resources - Populate team Warp Drive with Workflows, Rules, and Prompts.
See Roles and permissions for details on user roles and access controls.
Adjusting policies for different teams
For organizations with multiple teams (e.g., DevOps, Data, Frontend):
Create separate Warp teams for each group.
Assign team-specific admins.
Configure different autonomy levels per team.
Use directory allowlists to scope agent access to team repositories.
Responding to security incidents
If an agent performs an unintended action:
Immediate: Review agent action logs in the affected user's session.
Short-term: Add specific commands to the command denylist.
Long-term: Adjust autonomy settings to prevent similar incidents.
Audit: Review Admin Panel audit logs to understand what settings were in effect.
Warp logs all agent actions with full context, making incident investigation straightforward.
Troubleshooting
Users can't see new settings
Problem: You changed a setting in the Admin Panel, but users report they don't see the change.
Solution:
Verify the setting is not set to "Respect User Setting".
Ask users to restart Warp to force a settings refresh.
Confirm users are members of the correct team.
Check that users have logged in with SSO (not a personal account).
Setting is grayed out in Admin Panel
Problem: A setting you want to configure appears grayed out or shows "Not available on your plan."
Solution:
This setting is restricted to higher-tier plans
Review plan features at warp.dev/pricing
Contact your account manager or sales team to upgrade
Command allowlist not working
Problem: Agents still ask permission for commands that match your allowlist patterns.
Solution:
Verify regex patterns are correct (test with a regex validator).
Check that commands don't also match the denylist (denylist takes precedence).
Confirm autonomy settings allow command execution.
Remember: Some commands are always restricted regardless of allowlist.
Support
Enterprise customers have access to priority support:
Dedicated channels - Private Slack or Teams channels with Warp engineers
Account manager - Direct contact for escalations and feature requests
Technical support - Help with Admin Panel configuration and troubleshooting
Reach out through your dedicated support channel or email [email protected].
Last updated
Was this helpful?