For agents and technical readers

Discover and open a published Mind View

Use the active member's own connection to discover a published View, resolve its address and inspect the authorised data result. View tools require a Mind version with the released View feature.

Contents

List and resolve

Call orient and verify the intended Mind and principal. Discover the actual tool schema. Call view_list with {}. Choose the route returned for the intended published View, then call view_resolve:

{"route":"<returned route>"}

Open the returned route on that same Mind in the normal Portal session. If no View route is returned, report unavailable or refused from the actual result. Do not guess an app id from a display name.

Read only the declared data

For a programmatic dataset read, obtain the installed View's actual app id and declared dataset name, then call view_data:

{"app_id":"<installed View app id>","op":"dataset","args":{"name":"<declared dataset name>"}}

The exact dataset argument shape must agree with the current installed View contract. Do not substitute a guessed folder or use a broader alias to obtain excluded records. The declared sources, current viewer grants and all release authors' current read access constrain the result.

Check completeness and freshness

Read partial, freshness and refusal indicators before using rows or totals. Inspect the underlying permitted source when the conclusion matters. An empty or partial result does not prove that the full team has no matching records.

Static assets are read with view_asset using the actual app_id and path when an author or diagnostic needs them; that does not grant more data authority. A View cannot write records, run a schedule or access outside network resources.

Handle a missing route or failed read

Check account, Mind, route and the installed View's current state. Suspension or removal can make a formerly valid page unavailable. If a live data read fails, retain its result and hand it to the authorised builder; do not display bundled sample data as if it were a current result.

Related

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.

---

# Discover and open a published Mind View

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

Use the active member's own connection to discover a published View, resolve its address and inspect the authorised data result. View tools require a Mind version with the released View feature.

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

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

## 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.

## List and resolve

Call `orient` and verify the intended Mind and principal. Discover the actual tool schema. Call `view_list` with `{}`. Choose the route returned for the intended published View, then call `view_resolve`:

```
{"route":"<returned route>"}
```

Open the returned route on that same Mind in the normal Portal session. If no View route is returned, report unavailable or refused from the actual result. Do not guess an app id from a display name.

## Read only the declared data

For a programmatic dataset read, obtain the installed View's actual app id and declared dataset name, then call `view_data`:

```
{"app_id":"<installed View app id>","op":"dataset","args":{"name":"<declared dataset name>"}}
```

The exact dataset argument shape must agree with the current installed View contract. Do not substitute a guessed folder or use a broader alias to obtain excluded records. The declared sources, current viewer grants and all release authors' current read access constrain the result.

## Check completeness and freshness

Read partial, freshness and refusal indicators before using rows or totals. Inspect the underlying permitted source when the conclusion matters. An empty or partial result does not prove that the full team has no matching records.

Static assets are read with `view_asset` using the actual `app_id` and `path` when an author or diagnostic needs them; that does not grant more data authority. A View cannot write records, run a schedule or access outside network resources.

## Handle a missing route or failed read

Check account, Mind, route and the installed View's current state. Suspension or removal can make a formerly valid page unavailable. If a live data read fails, retain its result and hand it to the authorised builder; do not display bundled sample data as if it were a current result.

## Related

- [Open a team View and check its information](https://app.mensara.ai/how-it-works/team-views)
- [Build and publish a team View](https://app.mensara.ai/how-it-works/build-a-team-view)

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