Run agents, automations and loops

Install an approved agent and check its first result

An installed agent is a program that does a defined job on your Mind with its own permissions. Installation registers an approved program so it can run; the job also needs the right records, model route, connections and trigger. This guide helps an owner or permitted admin inspect those requirements and check the first useful result.

Content updated 29 October 2026.

Contents

An agent's bundle is the set of files describing its program and declared access. A catalog entry offers a version you may be able to install. A local bundle is one somebody has built for your Mind. Review, installation and a successful run are separate results in either route.

Choose the intended bundle

Open the available catalog through your Mind's Agents area or use the approved local proposal reference. Check the publisher, purpose and version. A listing does not prove that the app is installed or that your Mind meets its prerequisites. Apps, sensors and connectors explains the selected offerings and their setup needs.

If you need to create the program, start with Build a governed agent. Keep the approved files and their proposal reference so the installer can act on that exact bundle.

Review scope before installation

Check what the program reads, proposes, calls and costs. Review its record areas, verbs, outside-service endpoints and connections, model route and rolling seven-day model caps. Autonomy, budgets and access explains those separate limits.

Use the owner account or an admin whose delegated installation authority covers the bundle. An admin's installation route remains bounded by that admin's grants; local app connection or capability grants can require the owner. Do not broaden the person's role merely to make an installation attempt succeed.

Approve and install through the supported route

For a local bundle, have an authorised reviewer inspect and approve the proposal before installation. A submitting admin cannot approve their own bundle. Approval saves the reviewed files; installation separately registers the program. The installer checks the current bundle and authority again.

A catalog installation has its own consent flow. Review what that flow asks before accepting it. If the client cannot perform installation, hand the exact bundle or catalog reference to an authorised operator with a compatible interface. Do not report it as installed because its files were saved.

Check the first useful result

Inspect the installed identity, version, status and trigger. Confirm any owner-configured model route and required service connections. Wait for the intended normal trigger, then inspect the run and its output. A draft can still need review; open the saved source after it is applied.

If a result is missing, check the observed stage: trigger not due, suspended agent, refused access, missing connection, exhausted budget, run failure or held proposal. Keep the original references and reconcile them before reinstalling or submitting again.

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.

---

# Install an approved agent and check its first result

Content updated 29 October 2026.

Guides · Run agents, automations and loops · [How it works](https://www.mensara.ai/how-it-works)

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

## Choose the intended bundle

Open the available catalog through your Mind's **Agents** area or use the approved local proposal reference. Check the publisher, purpose and version. A listing does not prove that the app is installed or that your Mind meets its prerequisites. [Apps, sensors and connectors](https://www.mensara.ai/how-it-works/apps-sensors-connectors) explains the selected offerings and their setup needs.

If you need to create the program, start with [Build a governed agent](https://www.mensara.ai/how-it-works/build-an-agent). Keep the approved files and their proposal reference so the installer can act on that exact bundle.

## Review scope before installation

Check what the program reads, proposes, calls and costs. Review its record areas, verbs, outside-service endpoints and connections, model route and rolling seven-day model caps. [Autonomy, budgets and access](https://www.mensara.ai/how-it-works/control-agent-autonomy) explains those separate limits.

## Approve and install through the supported route

## Check the first useful result

## Related

- [Build a governed AI agent](https://www.mensara.ai/how-it-works/build-an-agent)
- [Pause, upgrade or remove an installed agent](https://www.mensara.ai/how-it-works/manage-an-agent)
- [Control agent autonomy, budgets and access](https://www.mensara.ai/how-it-works/control-agent-autonomy)
- [Understand settings](https://www.mensara.ai/how-it-works/mind-settings#models-and-spending)

Previous page: [Use a skill or turn a repeated job into one](https://www.mensara.ai/how-it-works/use-and-create-skills)

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

Your Mind is your team's shared Mensara workspace for saved information and work.

[Join the waitlist](https://www.mensara.ai/?guide_attribution=eyJfcmFpbHMiOnsiZGF0YSI6eyJvcmlnaW5fcGF0aCI6Ii9ob3ctaXQtd29ya3MvaW5zdGFsbC1hbi1hZ2VudCIsImN0YV9pZCI6Im1hcmtkb3duIiwiY29udGVudF9yZXZpc2lvbiI6IjhjMzE0ZDY3MThjMjFhMTUifSwicHVyIjoiZ3VpZGUtY2xpY2sifX0%3D--6f685e306d2d5ec4cb358076b15899856c56a8a2#waitlist)