
Exposing internal systems to agents without exposing your data
Connecting an agent to an internal system is easy. Connecting it so it sees only what the job needs, and cannot act beyond it, takes design. This page sets out that design: narrow views, separate accounts, read before write and a person on every consequential action.
The short answer
You let agents work with internal systems safely by giving each one a narrow view built for its job: its own account, only the data the job needs, read before write, and a person's approval on every consequential action.
Anything an agent can see, it can repeat.
Definition
Scoped agent access: access to an internal system given to an agent through its own account and a view limited to the data and actions one job needs, with consequential actions held for a person's approval.
What goes wrong when an agent gets the keys?
The quickest way to connect an agent is to give it an existing account, often one with broad access, and let it read whatever it needs. It works in the demo. Then the agent can see salary fields it never needed, customer records outside its job, and actions nobody meant it to take. An instruction hidden in an email or a document it reads can steer it toward any of them.
Who needs to settle this before anything is built?
The IT lead or security owner responsible for the system, the operations lead who wants the agent, and the developer who will connect it. The stakes rise with what the system holds: personal data, financial records, credentials, or actions that cannot be reversed.
How does scoped access compare with a quick connection?
| Design choice | The quick connection | Scoped access |
|---|---|---|
| Account | A person's account, or a shared admin one | Its own account, named for the agent and the job |
| What it can see | The whole system | A view with only the fields and records the job needs |
| What it can do | Whatever the account allows | Read first; specific write actions only once justified |
| Risky actions | Taken directly | Held for a named person's approval |
| Record | Mixed in with the person's activity | Every call logged against the agent's account |
How it works, step by step
Designing scoped access is a sequence the system owner runs before any connection is made.
Write down the job
List the data the job needs
Build a view, not a door
Give it its own account
Human gate: the system owner approves the access and every consequential action
Log and review
Remove what is no longer used
Which rules keep the data out of reach?
One account per agent
Never a person's or a shared administrator account.
A view built for the job. Sensitive fields left out entirely.
Read before write
Write actions added only when needed, one at a time.
A person on consequential actions
The agent proposes; a named person approves.
Regular review. Access checked and trimmed like anyone else's.
Where this fits
Access design is a foundation for every workflow that reads an internal system, and the Platform page covers how it is built. Pick the jobs worth connecting with the readiness checklist. When several agents share systems, as in the agent-run operations back office, each still gets its own scoped access. Customers often ask how you control this, which is where security questionnaire automation comes in. The use case library shows the workflows these rules protect.
How does agent access differ from a new employee's access?
| Question | New employee | Agent |
|---|---|---|
| How it learns what to do | Training and judgment | Instructions, which hostile input can imitate |
| What it does with what it sees | Uses discretion | May repeat it in output |
| How access should start | The role's standard access | Narrower still: one job's view |
| What stays the same | Approvals, reviews and removal | Approvals, reviews and removal |
Related reading
- Security questionnaire automation: answering customers about the controls on this page.
- The agent-run operations back office: many agents, each with its own access.
- Document intake, extraction, and filing: a workflow that reads documents hidden instructions can hide in.
