Build and share

Install an approved agent

An installed agent is a program that does a defined job on your Mind with its own permissions. Installation makes an approved program available to run; it still needs the right information, connections and schedule. This guide helps an owner or permitted admin check those requirements and its first useful result.

Contents

What you are installing

An agent's bundle is the reviewed set of files describing its program and the access it needs. A catalog entry offers a version you may be able to install; a local bundle is one somebody has built and proposed for your Mind. Both need an authorised installation route.

Approval accepts the reviewed files. Installation registers the program, and a scheduled run is a later attempt to do its job. If you first need to create the program, start with Build a governed AI agent.

Before you start

Use an owner account or an admin whose delegated installation rights cover this bundle. For a locally authored bundle, an admin cannot approve or install their own submission.

Check what the program reads, proposes, calls and costs. A catalog listing, an approved local bundle and an installed app are different states.

Install and check

  1. Choose the exact approved bundle or available catalog version.
  2. Review its access, service prerequisites, schedule and budget with the owner.
  3. Install through the available supported interface.
  4. Check the installed identity and trigger.
  5. Observe a scheduled run and inspect its output.

Owner actions may still be needed for model access or service connections. Installation cannot grant capabilities the installer does not hold.

When the result is missing

Check for a run failure, a held output proposal, an empty input area or a trigger that is not yet due. Resume from the observed stage. Do not reinstall blindly.

Related

Build a governed AI agent · Choose the right kind of help

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://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.

---

# Install an approved agent

Guides · Build and share · [How it works](https://app.mensara.ai/how-it-works)

An installed agent is a program that does a defined job on your Mind with its own permissions. Installation makes an approved program available to run; it still needs the right information, connections and schedule. This guide helps an owner or permitted admin check those requirements and its first useful result.

[Page as Markdown](https://app.mensara.ai/how-it-works/install-an-agent.md)

## What you are installing

An agent's **bundle** is the reviewed set of files describing its program and the access it needs. A catalog entry offers a version you may be able to install; a local bundle is one somebody has built and proposed for your Mind. Both need an authorised installation route.

Approval accepts the reviewed files. Installation registers the program, and a scheduled run is a later attempt to do its job. If you first need to create the program, start with [Build a governed AI agent](https://app.mensara.ai/how-it-works/build-an-agent).

## Before you start

Use an owner account or an admin whose delegated installation rights cover this bundle. For a locally authored bundle, an admin cannot approve or install their own submission.

Check what the program reads, proposes, calls and costs. A catalog listing, an approved local bundle and an installed app are different states.

## Install and check

1. Choose the exact approved bundle or available catalog version.
2. Review its access, service prerequisites, schedule and budget with the owner.
3. Install through the available supported interface.
4. Check the installed identity and trigger.
5. Observe a scheduled run and inspect its output.

Owner actions may still be needed for model access or service connections. Installation cannot grant capabilities the installer does not hold.

## When the result is missing

Check for a run failure, a held output proposal, an empty input area or a trigger that is not yet due. Resume from the observed stage. Do not reinstall blindly.

## Related

- [Build a governed AI agent](https://app.mensara.ai/how-it-works/build-an-agent)
- [Choose the right kind of help](https://app.mensara.ai/how-it-works/right-kind-of-help)

Previous page: [Build a governed AI agent](https://app.mensara.ai/how-it-works/build-an-agent)

Next page: [Invite a teammate to your Mind](https://app.mensara.ai/how-it-works/invite-a-teammate)

Send once and distinguish invited, joined and access checked.

[Join the waitlist](https://app.mensara.ai/#waitlist)