Docs

Find one useful job for your Mind.

Start with the guide that matches the work in front of you. When an agent needs exact steps, switch the page to Machine or open its Markdown version.

Store and share knowledge

Keep company knowledge in files you own, and decide who can open each part.

  • Memory

    Keep decisions, notes and company know-how as plain files with their history.

  • Zones and permissions

    Choose what each person, and the agents working for them, can read, suggest or approve.

  • Team and roles

    Give each team member their own account, role and access.

Use your Mind

Reach it from the tools you already use, and let it bring work in and carry work out.

Keep control

Review changes, keep a second copy, and look after your Mind over time.

Before you start

Plain answers to what people ask before they say yes.

  • Questions

    Lock-in, hosting, cost, who did what, and what happens when an answer is wrong.

Decide if it fits

Start with a real job and a result you can check.

  • Decide whether Mensara fits a real job

    Mensara gives your team one shared memory, your Mind, that people and their connected agents read. Each agent stays within the access of the person it works for. It fits when the same background comes up again and again and you want answers that lead back to a source you can open.

  • See whether Mensara helps with your work

    Mensara helps when several people, and the agents working for them, keep needing the same decisions, while each should see only what they're allowed to.

Get a first result

Choose a useful question and see the source behind the answer.

  • Start with a question you can check

    Choose one small question that should have an answer in the records you are allowed to use. A good first job gives you a clear result and a source you can inspect.

  • Ask your first question

    Your first question should be small enough to check. Ask your connected agent about one record you expect it to be allowed to use, such as: “What does our client brief say about the next meeting?”

Use memory well

Carry context forward while keeping current claims tied to evidence.

  • Start from what's already decided

    Your agent can start a job from the decisions and background already in your Mind, instead of you rebuilding the same briefing each time.

  • Ask what is current, then ask why

    Two questions look alike but need different records: “What applies now?” and “Why did this change?” Ask the first for today's guidance and the second for the history behind it.

  • Ask to see the source behind an answer

    Ask your connected agent to name the records behind its answer, so you can open them and see what it's based on.

Set safe boundaries

Choose who can read, suggest, approve, and move information.

Work with agents

Connect tools, repeat useful work, and hand context between agents.

  • Choose the right kind of help

    Start by deciding what you want your agent to do: follow guidance, use an available service, or carry out a repeatable piece of work.

  • Try a recurring job with human review

    A recurring workflow takes on a job that comes round again and again, such as reviewing incoming support requests. Start with a small one whose result a person can check.

  • Help another agent continue the work

    When a colleague's agent picks up a job, it reads the same records in your Mind, but only the ones that colleague can see.

Agent references

Exact inputs, when you need them. These references list each tool's exact inputs and mark which behaviour has been tested.

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://app.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://app.mensara.ai/llms.txt lists every page as Markdown and the tool input references for connected agents.

---

# Find one useful job for your Mind.

Start with the guide that matches the work in front of you. When an agent needs exact steps, switch the page to Machine or open its Markdown version.

## Store and share knowledge

Keep company knowledge in files you own, and decide who can open each part.

- [Memory](https://app.mensara.ai/how-it-works/memory): Keep decisions, notes and company know-how as plain files with their history.
- [Zones and permissions](https://app.mensara.ai/how-it-works/zones-and-permissions): Choose what each person, and the agents working for them, can read, suggest or approve.
- [Team and roles](https://app.mensara.ai/how-it-works/multiplayer): Give each team member their own account, role and access.

## Use your Mind

Reach it from the tools you already use, and let it bring work in and carry work out.

- [Portal, MCP and CLI](https://app.mensara.ai/how-it-works/portal-mcp-cli): Use Mensara in a browser, an AI tool or a terminal.
- [Connections and capture](https://app.mensara.ai/how-it-works/connections-and-capture): Bring in email, calendar and document updates for review.
- [Skills, apps and automations](https://app.mensara.ai/how-it-works/skills-apps-automations): Give your agents written procedures, tools with their own access, and work that runs on a schedule.

## Keep control

Review changes, keep a second copy, and look after your Mind over time.

- [Changes and approvals](https://app.mensara.ai/how-it-works/changes-approvals-receipts): Review suggested edits and see who did what.
- [Backup, restore and ownership](https://app.mensara.ai/how-it-works/backup-restore-ownership): Keep a second copy and recover your Mind if something fails.
- [Setup and ongoing care](https://app.mensara.ai/how-it-works/setup-and-ongoing-care): Choose one useful job, then improve your Mind as you use it.

## Before you start

Plain answers to what people ask before they say yes.

- [Questions](https://app.mensara.ai/how-it-works/questions): Lock-in, hosting, cost, who did what, and what happens when an answer is wrong.

## Decide if it fits

Start with a real job and a result you can check.

- [Decide whether Mensara fits a real job](https://app.mensara.ai/how-it-works/what-is-mensara): Mensara gives your team one shared memory, your Mind, that people and their connected agents read. Each agent stays within the access of the person it works for. It fits when the same background comes up again and again and you want answers that lead back to a source you can open.
- [See whether Mensara helps with your work](https://app.mensara.ai/how-it-works/who-it-helps): Mensara helps when several people, and the agents working for them, keep needing the same decisions, while each should see only what they're allowed to.

## Get a first result

Choose a useful question and see the source behind the answer.

- [Start with a question you can check](https://app.mensara.ai/how-it-works/choose-a-job): Choose one small question that should have an answer in the records you are allowed to use. A good first job gives you a clear result and a source you can inspect.
- [Ask your first question](https://app.mensara.ai/how-it-works/first-useful-question): Your first question should be small enough to check. Ask your connected agent about one record you expect it to be allowed to use, such as: “What does our client brief say about the next meeting?”

## Use memory well

Carry context forward while keeping current claims tied to evidence.

- [Start from what's already decided](https://app.mensara.ai/how-it-works/carry-context): Your agent can start a job from the decisions and background already in your Mind, instead of you rebuilding the same briefing each time.
- [Ask what is current, then ask why](https://app.mensara.ai/how-it-works/current-and-evidence): Two questions look alike but need different records: “What applies now?” and “Why did this change?” Ask the first for today's guidance and the second for the history behind it.
- [Ask to see the source behind an answer](https://app.mensara.ai/how-it-works/maps-and-navigation): Ask your connected agent to name the records behind its answer, so you can open them and see what it's based on.

## Set safe boundaries

Choose who can read, suggest, approve, and move information.

- [Give each person and their agent the right access](https://app.mensara.ai/how-it-works/right-access): Decide which areas a person should use, and give access only for the work they need to do. Their connected agent works within that access.
- [Know what an agent may read or change](https://app.mensara.ai/how-it-works/read-and-propose): Reading a record, suggesting a correction, and approving a change are separate permissions.
- [Decide where your information may go](https://app.mensara.ai/how-it-works/ownership-data-flow): Before you put important records in your Mind, decide where they're stored, which AI and backup providers can receive them, and who runs the systems involved. The answer depends on the setup you choose.
- [Suggest a correction and check its result](https://app.mensara.ai/how-it-works/suggest-a-correction): If it's allowed to suggest changes, your agent can suggest a correction. Once someone allowed to approve accepts it, the next person who can read the record gets the corrected version.

## Work with agents

Connect tools, repeat useful work, and hand context between agents.

- [Choose the right kind of help](https://app.mensara.ai/how-it-works/right-kind-of-help): Start by deciding what you want your agent to do: follow guidance, use an available service, or carry out a repeatable piece of work.
- [Try a recurring job with human review](https://app.mensara.ai/how-it-works/first-loop): A recurring workflow takes on a job that comes round again and again, such as reviewing incoming support requests. Start with a small one whose result a person can check.
- [Help another agent continue the work](https://app.mensara.ai/how-it-works/continue-the-work): When a colleague's agent picks up a job, it reads the same records in your Mind, but only the ones that colleague can see.

## Agent references

Exact inputs, when you need them.

These references list each tool's exact inputs and mark which behaviour has been tested.

- [Tool input reference](https://app.mensara.ai/how-it-works/tool-inputs.md)
- [Tool input schemas](https://app.mensara.ai/how-it-works/tool-input-schemas.md)
- [Explicit machine schemas](https://app.mensara.ai/how-it-works/explicit-machine-schemas.md)