## 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.

---

# Capture information and verify the saved result

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

Keep the source and date, choose an authorised destination, submit one bounded proposal and report applied or held accurately.

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

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

## 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.

## Discover the intended destination

Call `orient` with `{}` and follow its maps. The caller needs propose access to the destination. For a capture job, discover the available skill with `list_skills` `{}` and `get_skill` below. Follow the served procedure rather than assuming another Mind’s folders.

```
{"name":"capture"}
```

The released capture skill keeps a note for later triage, with the date and available source, and does not prioritise or act on it.

## Prepare one new ordinary note

Use the actual authorised folder and a new non-conflicting filename. Include the required frontmatter and content for that area. The example below is a shape with placeholders, not a runnable destination or a claim that every area has the same schema.

```
{"changes":[{"op":"create","path":"<authorised-folder>/<new-note>.md","content":"<complete note with the area’s required metadata, date, source and captured information>"}]}
```

Use `check_write` for the capture skill’s validation step, correct a concrete structural finding, then submit the same intended changes with `propose_write`. Do not rephrase a review requirement to evade it. Special memory records require their advertised lifecycle schema and revision/base contract; this ordinary-note example is not that contract.

## Check disposition

Inspect the returned state. An applied result is a save; a held result is a review request. Preserve its proposal reference and report it as waiting. The Mind’s area rules, proposer authority and checks determine the result; personal Automatic approval is separate.

## Read back

After an applied result, call `read` with the actual saved path. Check wording and location. If the response was lost, inspect the original proposal and destination before submitting again. For a held result, follow the ordinary review procedure or send the existing reference to the authorised reviewer.

## Completion

Report what was saved and where, or what is held and its reference. Do not claim that saving a note made an external action happen, established a policy decision or created a task assignment.

## Related

- [Save a note, meeting or useful fact](https://app.mensara.ai/how-it-works/save-information)
- [Read, correct and verify memory](https://app.mensara.ai/how-it-works/correct-memory-procedure)

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