Should my code agent use my credentials?
Source: Dev.to
If the agent uses my credentials, every action looks like mine
If the agent uses my account, the audit log will probably say that I performed the action.
Technically, I gave it access, but operationally it isn’t the same as me manually doing every step with full context.
There is a difference between a human making a decision and an agent executing a chain of actions because it interpreted a task in a certain way. That difference matters—not because agents are bad, but because they are powerful. A code agent with broad access can move very fast in the wrong direction.
The agent should not be a ghost user
I do not think a code agent should silently borrow human authority forever. If it is doing autonomous or repeatable work, it probably needs its own identity.
Creating a dedicated credential does not automatically make the setup safer. If I create a user called ai-agent and give it admin access to everything, I have not solved anything; I have just created a robot with too much power.
The value of a dedicated credential is that it can be smaller, more limited, easier to audit, and easier to revoke. That is the real point.
Dedicated credentials make more sense when the agent has responsibility
When the agent is performing automated reviews, dependency updates, issue triage, pull‑request comments, repository maintenance, scheduled tasks, or CI/CD automation, a dedicated identity starts to make a lot more sense.
- You can see what the agent did.
- You can limit what it can do.
- You can rotate the token.
- You can revoke access without touching a human account.
Most importantly, you can separate human actions from agent actions. That separation is important if we want agents to become a serious part of the engineering workflow.
The simple rule
- Helping me work – using my credentials can be okay.
- Working on my behalf – the agent needs its own limited identity.
- Risky actions (deploying, changing infrastructure, touching production data, accessing secrets) – the agent should not be free to do them alone; it needs approval, limited access, and a clear audit trail.
The goal is not to make AI‑assisted development harder, but to make it safe enough to scale. Code agents are becoming part of how we build software, and if they are going to act like real workers, they also need real boundaries.