For agents and technical readers

Use Portal chat and verify its effects

Follow the normal signed-in Portal route; do not call internal chat APIs as if they were public agent tools.

Contents

Open the intended Mind

Have the person sign in to the Portal and open Chat. Check the current account and any model-access or Mind-health banner. A personal connection, an eligible shared route and an unavailable service are distinct states. Use the offered supported connection route where needed.

Start or resume

Use New chat or the intended entry in Recents. Type a bounded question with relevant subject and time. Choose Send or press Enter; Shift+Enter adds a newline. Ask for the saved sources and any unresolved gap. The Choose a model control lists the connection’s actual models; verify its resulting selection.

Inspect sources and proposals

Open the cited sources and any displayed tool result. Do not infer a Mind read from a plain model response when Mind tools are unavailable. A held proposal is waiting; after an applied result, read the source. Use the supplied request controls or approval link when a human decision is needed.

Stop and return safely

Stop halts streaming generation; a partial assistant turn can remain in the conversation. It does not undo a completed tool action. Before retrying a save or external action, inspect its original request and current state. Return through Recents to the intended conversation.

Completion

Report the answer supported by the source, and separately any applied or waiting save. A conversation is account-associated chat history, not automatic shared company memory. Save the intended shared information explicitly using the ordinary proposal route.

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 Portal chat and verify its effects

Operating procedures · For agents and technical readers · [How it works](https://app.mensara.ai/how-it-works)

Follow the normal signed-in Portal route; do not call internal chat APIs as if they were public agent tools.

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

[Human guide](https://app.mensara.ai/how-it-works/use-chat)

## Use the released interface with current authority

Availability: Core0.20.11 / Portal0.3.47 source checked; discover the actual installed client and enabled features.

Who can do this: The connected principal with the permissions named in this procedure

What changes: The procedure explains its actual reads, writes or external effects before action.

Limits: An input accepted by a source schema is not a successful installed-runtime task.; Keep human decisions, client exclusions and pending results explicit.

Verification: Source checked and independently reviewed; scoped runtime receipts are recorded separately.

## Open the intended Mind

Have the person sign in to the Portal and open **Chat**. Check the current account and any model-access or Mind-health banner. A personal connection, an eligible shared route and an unavailable service are distinct states. Use the offered supported connection route where needed.

## Start or resume

Use **New chat** or the intended entry in **Recents**. Type a bounded question with relevant subject and time. Choose **Send** or press Enter; Shift+Enter adds a newline. Ask for the saved sources and any unresolved gap. The **Choose a model** control lists the connection’s actual models; verify its resulting selection.

## Inspect sources and proposals

## Stop and return safely

**Stop** halts streaming generation; a partial assistant turn can remain in the conversation. It does not undo a completed tool action. Before retrying a save or external action, inspect its original request and current state. Return through **Recents** to the intended conversation.

## Completion

## Related

- [Use chat in your Mensara Portal](https://app.mensara.ai/how-it-works/use-chat)
- [Save a note, meeting or useful fact](https://app.mensara.ai/how-it-works/save-information)

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