# Assistants, agents, and permissions

Taiga Learning · Worksheet
https://taiga.training/en/lessons/assistants-agents/

Use fictional or approved information. Do not put secrets in this worksheet.

## Learning objectives
- Explain the difference between an assistant and a tool-using agent.
- Identify actions that need an explicit permission boundary.
- Define a useful stop condition.

## Exercise
Select one AI tool available to your team. List what it can read, change, execute, and publish. Identify where a person must approve an action. Verify one boundary in the actual configuration.

## Your response
- Scenario and scope:
- Assumptions and open questions:
- Proposed answer or decision, with reasons:

## Verify your response
| Claim or criterion | Evidence or test | Result or gap | Owner |
| --- | --- | --- | --- |
| | | | |
| | | | |
| | | | |

## Next action
- Action, owner, and date:
- When will you review this response?

## Principle to retain
Assess the actions a system can perform. The product label does not define its authority.

## Sources
- [Anthropic: Building effective agents](https://www.anthropic.com/engineering/building-effective-agents)

This worksheet supports learning. Completing it does not itself authorize a production change.