Store and share knowledge

How zones and permissions work

A zone is an area of your Mensara Mind with its own access rules. It groups information that should be used together, such as customer records or company policies. Permissions decide who may read that area, suggest changes to it or approve them. This page explains those boundaries so you can organise useful shared information without assuming everyone should see the same records.

Contents

Your Mind holds saved records, such as a decision, a customer note or a way of working. Zones give those records boundaries that can be checked when someone or their agent asks to use them. How memory works explains the saved information and its history.

For example, a team might separate ordinary company information from payroll or hiring records. That is an illustrative arrangement, not a default structure every Mind has. Choose areas around the work and the people who need the information.

Use each person’s own identity

Every teammate signs in with their own account. Their connected agent works using that person’s access. A well-written prompt cannot give it permission to open an excluded area.

That is why inviting a teammate includes checking a task using the teammate’s account. A successful read by the owner does not establish what the teammate can read.

Separate reading, suggesting and approving

Reading lets someone use the records in an area. Proposing lets them suggest changes. Approval authority lets an authorised reviewer decide a request of the relevant kind. Those are different permissions; being able to read a policy does not automatically let you replace or approve it.

The owner can group access into a profile, a named selection of shared areas for a job. A person’s role, profile, default access and any other grants all matter. Choose access for a teammate explains how to check the combined result.

An agent uses the access of its person

A connected agent does not get a separate pass into excluded areas.

The Mind identifies the person behind the request and checks their effective access for the requested area and action. An allowed read can return the record. An excluded read is refused or left out of discovery. Permission to read does not itself grant permission to suggest or approve a change.

Understand what a permission check changes

The Mind checks the caller’s permissions before serving a read or allowing a change. Search results omit areas the caller cannot read. A direct request for an excluded record is refused; the agent must not fill the gap by guessing what it contains.

Write permission and immediate saving are also different questions. A permitted suggestion can still wait for review because of the Mind’s settings and checks. Read the returned outcome before reporting that a record changed.

Check the boundaries with harmless information

Agree one record the person should be able to use and, where you are testing a restriction, a disposable record in an area they should not be able to open. Use their own account for the check. Confirm both the useful task and the intended refusal.

If access is wrong, ask the owner or an admin allowed to manage access to inspect the assignments. Do not make someone an admin merely to make one read work. The access guide gives the review steps.

When an area is missing

A missing search result can mean the record is absent, you lack access, or the question did not find it. Ask the agent to identify which part it can establish and open the sources it used.

If you need access for a real job, tell the owner which information and action the job requires. They can review the scope without sharing the protected contents in the request itself.

Related

Practical guides for people and agents

Start with one useful job

Join the waitlist

Plain text for AI agents. Same content as the human page.

## For agents

- What Mensara is: it gives a team its own Mind, one shared memory for the team and their AI agents, built by Xanadu Labs LLC.
- Status: signup is not open. A person joins the waitlist at https://www.mensara.ai/#waitlist. Agents cannot create an account or sign up.
- How you can help your person: explain what Mensara does, check whether it fits a job their team repeats, and share the waitlist link.
- Agent references: https://www.mensara.ai/llms.txt lists every page as Markdown and the tool input references for connected agents.

---

# How zones and permissions work

Content updated 29 October 2026.

How Mensara works · Store and share knowledge · [How it works](https://www.mensara.ai/how-it-works)

A zone is an area of your Mensara Mind with its own access rules. It groups information that should be used together, such as customer records or company policies. Permissions decide who may read that area, suggest changes to it or approve them. This page explains those boundaries so you can organise useful shared information without assuming everyone should see the same records.

[Page as Markdown](https://www.mensara.ai/how-it-works/zones-and-permissions.md)

## Keep related records together

Your Mind holds saved records, such as a decision, a customer note or a way of working. Zones give those records boundaries that can be checked when someone or their agent asks to use them. [How memory works](https://www.mensara.ai/how-it-works/memory) explains the saved information and its history.

For example, a team might separate ordinary company information from payroll or hiring records. That is an illustrative arrangement, not a default structure every Mind has. Choose areas around the work and the people who need the information.

## Use each person’s own identity

Every teammate signs in with their own account. Their connected agent works using that person’s access. A well-written prompt cannot give it permission to open an excluded area.

That is why [inviting a teammate](https://www.mensara.ai/how-it-works/invite-a-teammate) includes checking a task using the teammate’s account. A successful read by the owner does not establish what the teammate can read.

## Separate reading, suggesting and approving

Reading lets someone use the records in an area. Proposing lets them suggest changes. Approval authority lets an authorised reviewer decide a request of the relevant kind. Those are different permissions; being able to read a policy does not automatically let you replace or approve it.

The owner can group access into a **profile**, a named selection of shared areas for a job. A person’s role, profile, default access and any other grants all matter. [Choose access for a teammate](https://www.mensara.ai/how-it-works/right-access#roles-and-profiles) explains how to check the combined result.

### An agent uses the access of its person

A connected agent does not get a separate pass into excluded areas.

The Mind identifies the person behind the request and checks their effective access for the requested area and action. An allowed read can return the record. An excluded read is refused or left out of discovery. Permission to read does not itself grant permission to suggest or approve a change.

## Understand what a permission check changes

The Mind checks the caller’s permissions before serving a read or allowing a change. Search results omit areas the caller cannot read. A direct request for an excluded record is refused; the agent must not fill the gap by guessing what it contains.

Write permission and immediate saving are also different questions. A permitted suggestion can still wait for review because of [the Mind’s settings and checks](https://www.mensara.ai/how-it-works/mind-settings#why-changes-wait-for-review). Read the returned outcome before reporting that a record changed.

## Check the boundaries with harmless information

Agree one record the person should be able to use and, where you are testing a restriction, a disposable record in an area they should not be able to open. Use their own account for the check. Confirm both the useful task and the intended refusal.

If access is wrong, ask the owner or an admin allowed to manage access to inspect the assignments. Do not make someone an admin merely to make one read work. [The access guide](https://www.mensara.ai/how-it-works/right-access#check-effective-access) gives the review steps.

## When an area is missing

A missing search result can mean the record is absent, you lack access, or the question did not find it. Ask the agent to identify which part it can establish and [open the sources it used](https://www.mensara.ai/how-it-works/maps-and-navigation).

If you need access for a real job, tell the owner which information and action the job requires. They can review the scope without sharing the protected contents in the request itself.

## Related

- [Choose access for a teammate](https://www.mensara.ai/how-it-works/right-access)
- [Understand your Mind’s settings](https://www.mensara.ai/how-it-works/mind-settings)
- [Invite a teammate to your Mind](https://www.mensara.ai/how-it-works/invite-a-teammate)
- [Review changes and check what was saved](https://www.mensara.ai/how-it-works/changes-approvals-receipts)

Previous page: [How Mensara memory works](https://www.mensara.ai/how-it-works/memory)

Next page: [Team and roles](https://www.mensara.ai/how-it-works/multiplayer)

A team shares a Mensara Mind through separate accounts.

[Join the waitlist](https://www.mensara.ai/?guide_attribution=eyJfcmFpbHMiOnsiZGF0YSI6eyJvcmlnaW5fcGF0aCI6Ii9ob3ctaXQtd29ya3Mvem9uZXMtYW5kLXBlcm1pc3Npb25zIiwiY3RhX2lkIjoibWFya2Rvd24iLCJjb250ZW50X3JldmlzaW9uIjoiMjc2NDUwZTZhMWI2NzhhYyJ9LCJwdXIiOiJndWlkZS1jbGljayJ9fQ%3D%3D--5e8eb79289eebdfe1b29523090637414d443c33f#waitlist)