Run agents, automations and loops

Choose the right kind of help

Mensara gives you several ways to work with the saved information in your Mind. You can ask a connected agent a question, give it a written procedure, install a program or supervise recurring work. This page explains those choices so you can start with the help your job needs.

Content updated .

Contents

Start with the job

A connected agent is the AI tool you use in a chat or coding client. A client is simply the application through which you connect to the Mind. Use it for a question or work you are supervising; it can use only the information and actions your account is allowed to use.

A skill is a written procedure the agent follows. It can help the agent repeat a method, but it does not keep a process running after your session ends.

An installed agent or app is a program set up on the server hosting your Mind to do a defined job. It has its own identity and permissions rather than borrowing your whole account. An agent uses an AI model, the service that generates its response, so the owner must allow the model and set its spending limits.

An automation starts a set of available actions when a trigger occurs, such as a scheduled time. A loop manages recurring work that also needs checks, a person's decision or a way to handle problems. It follows each individual attempt as a case, so you can inspect its progress and result.

Choose a first step

  • To find an answer, ask a small question and inspect its source.
  • To repeat a method in your chat, discover the available skills.
  • To run a custom program, build and test an agent bundle, then have it reviewed and installed.
  • To supervise recurring cases, start with a small loop and inspect its results.

Check what you have

Connecting a client proves that connection. A proposed bundle is waiting for review. An approved bundle still needs installation. An installed program needs an observed run with useful output before you can call the job working.

Related

Ask your first question · Build a governed AI agent · Build your first recurring workflow with a loop

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.

---

# Choose the right kind of help

Content updated 29 October 2026.

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

Mensara gives you several ways to work with the saved information in your Mind. You can ask a connected agent a question, give it a written procedure, install a program or supervise recurring work. This page explains those choices so you can start with the help your job needs.

[Page as Markdown](https://www.mensara.ai/how-it-works/right-kind-of-help.md)

## Start with the job

A **connected agent** is the AI tool you use in a chat or coding client. A client is simply the application through which you connect to the Mind. Use it for a question or work you are supervising; it can use only the information and actions your account is allowed to use.

A **skill** is a written procedure the agent follows. It can help the agent repeat a method, but it does not keep a process running after your session ends.

An **installed agent or app** is a program set up on the server hosting your Mind to do a defined job. It has its own identity and permissions rather than borrowing your whole account. An agent uses an **AI model**, the service that generates its response, so the owner must allow the model and set its spending limits.

An **automation** starts a set of available actions when a trigger occurs, such as a scheduled time. A **loop** manages recurring work that also needs checks, a person's decision or a way to handle problems. It follows each individual attempt as a **case**, so you can inspect its progress and result.

## Choose a first step

- To find an answer, ask a small question and inspect its source.
- To repeat a method in your chat, discover the available skills.
- To run a custom program, build and test an agent bundle, then have it reviewed and installed.
- To supervise recurring cases, start with a small loop and inspect its results.

## Check what you have

Connecting a client proves that connection. A proposed bundle is waiting for review. An approved bundle still needs installation. An installed program needs an observed run with useful output before you can call the job working.

## Related

- [Ask your first question](https://www.mensara.ai/how-it-works/first-useful-question)
- [Build a governed AI agent](https://www.mensara.ai/how-it-works/build-an-agent)
- [Build your first recurring workflow with a loop](https://www.mensara.ai/how-it-works/first-loop)

Previous page: [Review what needs your attention](https://www.mensara.ai/how-it-works/review-attention)

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

A skill is a written procedure your connected AI tool can read and follow.

[Join the waitlist](https://www.mensara.ai/?guide_attribution=eyJfcmFpbHMiOnsiZGF0YSI6eyJvcmlnaW5fcGF0aCI6Ii9ob3ctaXQtd29ya3MvcmlnaHQta2luZC1vZi1oZWxwIiwiY3RhX2lkIjoibWFya2Rvd24iLCJjb250ZW50X3JldmlzaW9uIjoiMDY5ZDBkNDQwNDhhMmJmZSJ9LCJwdXIiOiJndWlkZS1jbGljayJ9fQ%3D%3D--e57946f34d9006c51205dbe37b8ce50498fcb519#waitlist)