For agents and technical readers

Read current memory and historical evidence

Choose the view that fits the requested claim and retain the distinction between current guidance and earlier evidence.

Contents

Choose the view before reading

Call orient and navigate the relevant authorised map. Use memory_view: "current" for current guidance. The dedicated memory system can withhold pending, expired, superseded, conflicted or malformed entries from that projection. Ordinary records are not all special memory entries.

Read current information

Read the identified source with this input shape:

{"path":"<authorised-source-path>","memory_view":"current"}

Inspect its status and sources. For missing support, state the gap. Do not automatically retry a current-view exclusion as historical evidence.

Read evidence for a historical job

Only when the user’s question requires history, use the evidence view on an authorised record.

{"path":"<authorised-historical-source-path>","memory_view":"evidence"}

Keep the historical statement’s date and scope. Follow any mapped history timeline and the pages it names for prior conversations. Cross-zone restrictions still apply; historical mode does not widen access.

Resolve conflicts and corrections

Compare current guidance with the evidence explaining its revision. If no authorised source settles a conflict, ask the responsible person to decide. For a needed correction, use the ordinary correction procedure and the record’s current revision contract. Read back the applied result before treating it as new guidance.

Completion

State what applies now or what was recorded then, according to the job. Cite the relevant source and label unresolved uncertainty. A logged save proves the system saved the change; evidence of the underlying decision is a separate claim.

Related

Ask what is current, then ask why · Understand activity and the history of a change

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.

---

# Read current memory and historical evidence

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

Choose the view that fits the requested claim and retain the distinction between current guidance and earlier evidence.

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

[Human guide](https://app.mensara.ai/how-it-works/current-and-evidence)

## 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.

## Choose the view before reading

Call `orient` and navigate the relevant authorised map. Use `memory_view: "current"` for current guidance. The dedicated memory system can withhold pending, expired, superseded, conflicted or malformed entries from that projection. Ordinary records are not all special memory entries.

## Read current information

Read the identified source with this input shape:

```
{"path":"<authorised-source-path>","memory_view":"current"}
```

Inspect its status and sources. For missing support, state the gap. Do not automatically retry a current-view exclusion as historical evidence.

## Read evidence for a historical job

Only when the user’s question requires history, use the evidence view on an authorised record.

```
{"path":"<authorised-historical-source-path>","memory_view":"evidence"}
```

Keep the historical statement’s date and scope. Follow any mapped history timeline and the pages it names for prior conversations. Cross-zone restrictions still apply; historical mode does not widen access.

## Resolve conflicts and corrections

Compare current guidance with the evidence explaining its revision. If no authorised source settles a conflict, ask the responsible person to decide. For a needed correction, use the ordinary correction procedure and the record’s current revision contract. Read back the applied result before treating it as new guidance.

## Completion

State what applies now or what was recorded then, according to the job. Cite the relevant source and label unresolved uncertainty. A logged save proves the system saved the change; evidence of the underlying decision is a separate claim.

## Related

- [Ask what is current, then ask why](https://app.mensara.ai/how-it-works/current-and-evidence)
- [Understand activity and the history of a change](https://app.mensara.ai/how-it-works/activity-history)

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