Tool permission boundaries in Agentic AI

Introduction

Tool permission boundaries help control what actions an AI agent can perform, keeping it safe and focused.

When you want an AI agent to use only certain tools and avoid others.

When you need to protect sensitive data from being accessed by AI tools.

When you want to limit AI actions to prevent mistakes or harmful behavior.

When managing multiple AI tools with different access levels.

When ensuring AI agents follow rules in a shared environment.

Syntax

Agentic AI

tool_permission_boundaries = {
    "tool_name": {
        "allowed_actions": ["action1", "action2"],
        "restricted_data": ["data1", "data2"]
    }
}

Define which actions each tool can perform inside 'allowed_actions'.

List any data or resources the tool should NOT access in 'restricted_data'.

Examples

This example allows the email_sender tool only to send emails and blocks access to user passwords.

Agentic AI

tool_permission_boundaries = {
    "email_sender": {
        "allowed_actions": ["send_email"],
        "restricted_data": ["user_passwords"]
    }
}

Here, the file_manager can read and write files but cannot access system files.

Agentic AI

tool_permission_boundaries = {
    "file_manager": {
        "allowed_actions": ["read_file", "write_file"],
        "restricted_data": ["system_files"]
    }
}

Sample Model

This program creates two tools with specific permissions. It shows which actions are allowed or blocked based on the permission boundaries.

Agentic AI

class Tool:
    def __init__(self, name, permissions):
        self.name = name
        self.permissions = permissions

    def perform_action(self, action):
        if action in self.permissions.get("allowed_actions", []):
            return f"{self.name} performed {action}"
        else:
            return f"{self.name} is not allowed to perform {action}"


# Define permission boundaries
permissions = {
    "calculator": {
        "allowed_actions": ["add", "subtract"],
        "restricted_data": []
    },
    "file_tool": {
        "allowed_actions": ["read"],
        "restricted_data": ["secret.txt"]
    }
}

# Create tools
calculator = Tool("calculator", permissions["calculator"])
file_tool = Tool("file_tool", permissions["file_tool"])

# Test actions
print(calculator.perform_action("add"))
print(calculator.perform_action("multiply"))
print(file_tool.perform_action("read"))
print(file_tool.perform_action("write"))

Important Notes

Always clearly define what each tool can and cannot do to avoid unexpected behavior.

Permission boundaries help keep AI agents safe and trustworthy.

Review and update permissions regularly as your AI system grows.

Summary

Tool permission boundaries limit what actions AI tools can perform.

They protect sensitive data and prevent harmful actions.

Setting clear boundaries helps build safer AI systems.

Practice

1. What is the main purpose of tool permission boundaries in agentic AI systems?

easy

A. To limit what actions AI tools can perform

B. To increase the speed of AI computations

C. To improve the visual design of AI interfaces

D. To store large amounts of data efficiently

Solution

1. Step 1: Understand the role of permission boundaries

   Permission boundaries restrict the actions AI tools can take to ensure safety and control.

2. Step 2: Identify the main goal

   The main goal is to limit actions to prevent harmful or unauthorized behavior.

3. Final Answer:

   To limit what actions AI tools can perform -> Option A

4. Quick Check:

   Permission boundaries = limit actions [OK]

Hint: Permission boundaries control AI actions to keep systems safe [OK]

Common Mistakes:

• Confusing permission boundaries with data storage
• Thinking permission boundaries speed up AI
• Assuming permission boundaries affect UI design

2. Which of the following is the correct way to define a permission boundary for an AI tool in pseudocode?

easy

A. permissions = 'full_access'

B. allow_actions = ['read', 'write', 'execute']

C. actions = ['all']

D. permission_boundary = { 'allowed': ['read', 'write'], 'denied': ['delete'] }

Solution

1. Step 1: Identify correct permission boundary structure

   A permission boundary should clearly specify allowed and denied actions.

2. Step 2: Compare options

   permission_boundary = { 'allowed': ['read', 'write'], 'denied': ['delete'] } explicitly defines allowed and denied actions, which fits permission boundary concept.

3. Final Answer:

   permission_boundary = { 'allowed': ['read', 'write'], 'denied': ['delete'] } -> Option D

4. Quick Check:

   Permission boundary = allowed and denied actions [OK]

Hint: Look for explicit allowed and denied lists in permission definitions [OK]

Common Mistakes:

• Using vague permissions like 'all' or 'full_access'
• Not specifying denied actions
• Confusing action lists with permission boundaries

3. Given this pseudocode for an AI tool permission check:

def can_perform(action, permissions):
    return action in permissions['allowed'] and action not in permissions['denied']

permissions = {'allowed': ['read', 'write'], 'denied': ['delete']}
action = 'delete'
print(can_perform(action, permissions))

What will be the output?

medium

A. True

B. False

C. Error

D. None

Solution

1. Step 1: Understand the function logic

   The function returns True only if action is in allowed and not in denied.

2. Step 2: Check the action 'delete'

   'delete' is not in allowed but is in denied, so condition fails.

3. Final Answer:

   False -> Option B

4. Quick Check:

   Action denied = False output [OK]

Hint: Check if action is both allowed and not denied for True [OK]

Common Mistakes:

• Ignoring denied list and returning True
• Assuming 'delete' is allowed by default
• Confusing function return values

4. Identify the error in this permission boundary check code:

def check_permission(action, permissions):
    if action in permissions['allowed'] or action not in permissions['denied']:
        return True
    else:
        return False

permissions = {'allowed': ['read'], 'denied': ['delete']}
print(check_permission('delete', permissions))

medium

A. Incorrect dictionary keys

B. Missing return statement

C. Using 'or' instead of 'and' in condition

D. Syntax error in function definition

Solution

1. Step 1: Analyze the condition logic

   The condition uses 'or' which allows action if either allowed or not denied.

2. Step 2: Understand correct logic for permission

   It should be 'and' to ensure action is allowed and not denied simultaneously.

3. Final Answer:

   Using 'or' instead of 'and' in condition -> Option C

4. Quick Check:

   Permission check needs 'and' not 'or' [OK]

Hint: Permission checks require 'and' to combine allowed and denied rules [OK]

Common Mistakes:

• Using 'or' allowing denied actions
• Confusing dictionary keys
• Forgetting to return a value

5. You want to design a permission boundary for an AI tool that can read and write files but must never delete or modify system files. Which permission boundary setup below best enforces this?

hard

A. {'allowed': ['read', 'write'], 'denied': ['delete', 'modify_system_files']}

B. {'allowed': ['read', 'write', 'delete'], 'denied': ['modify_system_files']}

C. {'allowed': ['read'], 'denied': ['write', 'delete', 'modify_system_files']}

D. {'allowed': ['read', 'write', 'modify_system_files'], 'denied': ['delete']}

Solution

1. Step 1: Identify required allowed actions

   The tool must be allowed to read and write files.

2. Step 2: Identify denied actions

   It must never delete or modify system files, so these must be denied.

3. Step 3: Match options to requirements

   {'allowed': ['read', 'write'], 'denied': ['delete', 'modify_system_files']} allows read and write, denies delete and modify_system_files, matching requirements exactly.

4. Final Answer:

   {'allowed': ['read', 'write'], 'denied': ['delete', 'modify_system_files']} -> Option A

5. Quick Check:

   Allowed read/write, denied delete/system modify = {'allowed': ['read', 'write'], 'denied': ['delete', 'modify_system_files']} [OK]

Hint: Match allowed and denied lists exactly to requirements [OK]

Common Mistakes:

• Allowing delete when it should be denied
• Denying write when it should be allowed
• Missing deny for system file modifications