← Back to Agent

Agent Permissions

Control risk levels, blocked actions, approval workflows, rate limits, constraints, and organization policies — the full security profile for this agent.

Contents

Overview

For Everyone

Permissions define the boundaries of what your agent is allowed to do. They answer questions like: Can this agent send emails without approval? How many actions can it perform per hour? Is it allowed to delete data or run code?

There are three ways to set permissions:

  1. Role Templates — One-click personas that set identity, personality, skills, and permissions together (e.g., "Customer Support Agent" or "Research Analyst").
  2. Permission Presets — Quick profiles focused just on permissions (Restrictive, Standard, Permissive).
  3. Custom Profile — Full manual control over every setting.

Organization-wide policies also apply automatically and are shown at the bottom of this page.

For Developers

The permission system uses several endpoints:

Role templates also update agent config (identity, personality, description) via hot-update or config patch, and optionally apply a suggested permission preset. The profile object contains: maxRiskLevel, blockedSideEffects, sandboxMode, requireApproval, rateLimits, and constraints.

How It Works

  1. Open the Permissions tab on the agent detail page. You'll see the current permission profile (or an empty state prompting you to create one).
  2. Choose a starting point:
  3. In edit mode, configure: maximum risk level, blocked side effects, approval requirements, rate limits, and constraints.
  4. Save — Changes are persisted via PUT /profiles/:id and take effect on the next agent action.
  5. Review policies — The Applicable Policies table shows organization-level rules that apply regardless of the agent's profile.
Tip: Role templates are the fastest way to get started. Apply one, then use "Edit" to fine-tune individual settings.

Key Concepts

Role Templates (Souls)

Role templates are pre-configured agent personas that bundle together:

Templates are organized by category (e.g., "Customer Facing," "Internal Operations," "Creative"). Each category has metadata including an icon and display name. Applying a template:

  1. Updates the agent's config.identity (role, personality, description) via hot-update or config patch
  2. If the template has a suggestedPreset, applies that permission preset as well

The template gallery supports search (by name, description, and tags) and can be collapsed/expanded.

Permission Presets

Presets are quick permission profiles that replace the entire current profile. They configure risk levels, blocked actions, rate limits, and approval requirements in one click. The currently active preset is highlighted with a checkmark and accent border.

Common presets:

Maximum Risk Level

Defines the highest risk tier of tools the agent can use. Four levels:

Tools above the maximum risk level are blocked entirely, regardless of other settings.

Blocked Side Effects

Side effects are categories of real-world impact. You can block specific types entirely:

Blocked side effects are shown as red badges. Any tool that produces a blocked side effect will be denied.

Approval Settings

When enabled, the agent must get human approval before performing certain actions. You configure:

Note: Approval is different from blocking. Blocked side effects are denied outright. Approval-required actions are paused and wait for human confirmation.

Rate Limits

Rate limits prevent runaway behavior and control costs. Four configurable limits:

When a limit is reached, subsequent tool calls are denied until the window resets. Set to 0 for unlimited (not recommended for production).

Constraints & Sandbox Mode

Operational limits that govern the agent's resources:

Tool Overrides

The permission profile can include explicit tool-level overrides:

This section only appears when overrides are configured.

Applicable Policies

Organization-level policies that apply to this agent. Policies are rules defined at the org level — they're not per-agent but apply to agents based on scope. The table shows:

Best Practices

Start with a Preset, Then Customize

Pick the preset closest to your needs (usually "Standard"), then use "Edit" to adjust specific settings. This avoids starting from a blank slate.

Enable Approval for External Actions

At minimum, require approval for sends-email and financial side effects. This prevents the agent from sending messages or spending money without human confirmation — especially important during initial deployment.

Set Reasonable Rate Limits

The defaults (30/min, 500/hr, 5000/day) work for most agents. Lower them for agents with external actions to prevent spam. Raise them for batch-processing agents that need high throughput.

Use Sandbox Mode for Testing

When developing or testing a new agent, enable sandbox mode. The agent can read data and plan actions but can't execute anything with real-world impact. Disable it once you're confident in the agent's behavior.

Review Organization Policies

Check the Applicable Policies table to understand what org-level rules affect this agent. Mandatory policies can block actions even if the agent's own profile allows them.

Role Templates for New Agents

When creating a new agent, apply a role template first. It sets identity, personality, and permissions in one click — a much faster starting point than configuring everything manually.

Troubleshooting

Agent can't perform an action it should be able to

Check in order: (1) Is the tool's category enabled in the Tools tab? (2) Is the tool's risk level within maxRiskLevel? (3) Is the side effect type blocked? (4) Is there a mandatory org policy blocking it? (5) Has a rate limit been hit?

"No permission profile assigned" message

The agent has no profile yet. Apply a role template, select a preset, or create a custom profile. Without a profile, the agent may use system defaults which vary by deployment.

Preset doesn't seem to apply

Presets replace the entire profile. If you see stale values, refresh the page — the profile is re-fetched from the server. Also check the browser console for errors from POST /profiles/:id/apply-preset.

Role template only changes identity, not permissions

Not all role templates have a suggestedPreset. If the template doesn't include one, only the agent's identity (role, personality, description) is updated. Apply a permission preset separately if needed.

Approval requests timing out

The default timeout is 30 minutes. If approvers consistently miss the window, increase the timeout in the approval settings. Also consider reducing which actions require approval to only the most critical ones.

Policies show as "Disabled" but should be active

Policies are managed at the organization level, not per-agent. If a policy appears disabled here, it was disabled org-wide. Contact your organization admin to re-enable it.

Organization Policies

When an agent belongs to a client organization, permissions are governed by that organization's policies:

Tip: If you cannot raise the risk level or remove a blocked side effect, the organization may have enforced a ceiling. Check with your org administrator.
AgenticMail Enterprise Documentation Report an issue