Get a first result

Use chat in your Mensara Portal

Chat in your Portal lets you ask an AI model questions and work with your Mind’s records in the same web interface. The model generates the response; the Mind supplies only the information and actions available to your signed-in account. This guide explains starting a conversation, choosing an available model and returning to work you have already begun.

Contents

Check the model and Mind connection

Open Chat in the intended Mind. The page explains whether you have a personal model connection, an eligible shared model or a connection that needs attention. Follow the offered Connect one or Connect your own route when needed. A shared model can have a daily limit; repeated retries do not remove it. Model and spending settings explains those separate controls.

A model answering does not establish that its Mind tools are working. Read any warning that the Mind is unavailable or needs attention. Do not assume an answer came from saved records when the source tools were unavailable.

Start one conversation

Choose New chat or open a conversation in Recents. Type the question and choose Send, or press Enter. Shift+Enter adds a new line. Give the model the subject, relevant time and result you want. Ask it to show the saved sources behind claims about your work.

Use your first question as a pattern: a small answer you can compare with a record, with any missing evidence made clear.

Choose a model or skill

The model control opens Choose a model, listing models available through that connection. Select one and check the resulting choice; an error means the change did not complete. Changing the model does not widen access to saved records.

Open Skills from the conversation list to browse written procedures. A skill is guidance the agent follows, not a service that continues running after the conversation. The available skills depend on access and the client’s capabilities. Ask for a supported alternative if a skill requires a coding client.

Read the result before relying on it

Open source links and inspect any tool result or proposed change. An answer, an applied save and a held proposal are different results. Review rules explain why a suggested edit can wait for a person.

Stop and return

While a response is streaming, choose Stop to halt that generation. A partial response may be saved with the conversation. Stopping generation does not undo a tool action already completed. Before repeating a write or external action, inspect its original result.

Return through Recents and open the conversation you intended. Conversations are associated with the signed-in account; sharing a team Mind does not make another member’s conversation list your shared knowledge store. Save the useful shared record explicitly through saving information.

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.

---

# Use chat in your Mensara Portal

Guides · Get a first result · [How it works](https://app.mensara.ai/how-it-works)

[Page as Markdown](https://app.mensara.ai/how-it-works/use-chat.md)

[Operating procedure](https://app.mensara.ai/how-it-works/portal-chat-procedure)

## Check the model and Mind connection

Open **Chat** in the intended Mind. The page explains whether you have a personal model connection, an eligible shared model or a connection that needs attention. Follow the offered **Connect one** or **Connect your own** route when needed. A shared model can have a daily limit; repeated retries do not remove it. [Model and spending settings](https://app.mensara.ai/how-it-works/mind-settings#models-and-spending) explains those separate controls.

## Start one conversation

Choose **New chat** or open a conversation in **Recents**. Type the question and choose **Send**, or press Enter. Shift+Enter adds a new line. Give the model the subject, relevant time and result you want. Ask it to show the saved sources behind claims about your work.

Use [your first question](https://app.mensara.ai/how-it-works/first-useful-question) as a pattern: a small answer you can compare with a record, with any missing evidence made clear.

## Choose a model or skill

The model control opens **Choose a model**, listing models available through that connection. Select one and check the resulting choice; an error means the change did not complete. Changing the model does not widen access to saved records.

Open **Skills** from the conversation list to browse written procedures. A skill is guidance the agent follows, not a service that continues running after the conversation. The available skills depend on access and the client’s capabilities. Ask for a supported alternative if a skill requires a coding client.

## Read the result before relying on it

Open source links and inspect any tool result or proposed change. An answer, an applied save and a held proposal are different results. [Review rules](https://app.mensara.ai/how-it-works/mind-settings#why-changes-wait-for-review) explain why a suggested edit can wait for a person.

## Stop and return

While a response is streaming, choose **Stop** to halt that generation. A partial response may be saved with the conversation. Stopping generation does not undo a tool action already completed. Before repeating a write or external action, inspect its original result.

Return through **Recents** and open the conversation you intended. Conversations are associated with the signed-in account; sharing a team Mind does not make another member’s conversation list your shared knowledge store. Save the useful shared record explicitly through [saving information](https://app.mensara.ai/how-it-works/save-information).

## Related

- [Portal, MCP and CLI](https://app.mensara.ai/how-it-works/portal-mcp-cli)
- [Save a note, meeting or useful fact](https://app.mensara.ai/how-it-works/save-information)
- [Recover from a missing or poor answer](https://app.mensara.ai/how-it-works/improve-an-answer)

Previous page: [Ask your first question](https://app.mensara.ai/how-it-works/first-useful-question)

Next page: [Start from what’s already decided](https://app.mensara.ai/how-it-works/carry-context)

Saved context is the information a later conversation can use without you rebuilding the whole briefing.

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