Use memory well

Understand activity and the history of a change

Activity records help explain which identity asked for something and what the Mind did. A saved record’s history shows how its wording changed. The evidence behind that wording is a third question. This guide explains how to follow those connections without treating a logged action as proof that the underlying claim was true.

Contents

Start with the result you need to explain

Keep the record path, task or proposal reference and the relevant time. Ask whether you need today’s state, an earlier version or the result of a particular action. Read the current record first when the job depends on what applies now.

An applied proposal changed a saved record; a held proposal did not. Reviewing changes explains checking that state and reading the saved result.

Identify the actor and action

A connected person’s agent acts through that person’s identity. An installed app has its own app identity and scope. Network participants and other visiting agents have separate trust and permission arrangements. Read the identity recorded for the action rather than attributing every automated action to the owner.

The record tells you what the system observed under that identity. It does not establish that every claim made by the person or app was correct.

Follow the reason back to its source

For an illustrative policy change, compare the earlier wording, the proposal’s reason and supporting decision, and the applied wording. Keep their dates and scopes attached. If a decision remains unresolved, record that uncertainty instead of inferring agreement from an edit.

Current information and evidence explains historical questions. Historical access remains limited by your account’s permissions.

Handle an incomplete trail

Ask the agent to identify the records it could inspect and the step it could not establish. A missing result, failed connection or incomplete page does not prove that no action happened. If a write response was lost, reconcile the original request and current source before repeating it.

Leave a verifiable explanation

State the actor identity, action, observed outcome and the source supporting each conclusion. Separate “the change was saved” from “the business decision was valid” and “the external action completed”. Those claims can require different evidence.

Related

Review changes and check what was saved · Ask what is current, then ask why · Share work without sharing everything

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.

---

# Understand activity and the history of a change

Guides · Use memory well · [How it works](https://app.mensara.ai/how-it-works)

Activity records help explain which identity asked for something and what the Mind did. A saved record’s history shows how its wording changed. The evidence behind that wording is a third question. This guide explains how to follow those connections without treating a logged action as proof that the underlying claim was true.

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

## Start with the result you need to explain

Keep the record path, task or proposal reference and the relevant time. Ask whether you need today’s state, an earlier version or the result of a particular action. Read the current record first when the job depends on what applies now.

An applied proposal changed a saved record; a held proposal did not. [Reviewing changes](https://app.mensara.ai/how-it-works/changes-approvals-receipts) explains checking that state and reading the saved result.

## Identify the actor and action

A connected person’s agent acts through that person’s identity. An installed app has its own app identity and scope. Network participants and other visiting agents have separate trust and permission arrangements. Read the identity recorded for the action rather than attributing every automated action to the owner.

The record tells you what the system observed under that identity. It does not establish that every claim made by the person or app was correct.

## Follow the reason back to its source

For an illustrative policy change, compare the earlier wording, the proposal’s reason and supporting decision, and the applied wording. Keep their dates and scopes attached. If a decision remains unresolved, record that uncertainty instead of inferring agreement from an edit.

[Current information and evidence](https://app.mensara.ai/how-it-works/current-and-evidence#ask-why-something-changed) explains historical questions. Historical access remains limited by your account’s permissions.

## Handle an incomplete trail

Ask the agent to identify the records it could inspect and the step it could not establish. A missing result, failed connection or incomplete page does not prove that no action happened. If a write response was lost, reconcile the original request and current source before repeating it.

## Leave a verifiable explanation

State the actor identity, action, observed outcome and the source supporting each conclusion. Separate “the change was saved” from “the business decision was valid” and “the external action completed”. Those claims can require different evidence.

## Related

- [Review changes and check what was saved](https://app.mensara.ai/how-it-works/changes-approvals-receipts)
- [Ask what is current, then ask why](https://app.mensara.ai/how-it-works/current-and-evidence)
- [Share work without sharing everything](https://app.mensara.ai/how-it-works/share-work)

Previous page: [Recover from a missing or poor answer](https://app.mensara.ai/how-it-works/improve-an-answer)

Next page: [Choose access for a teammate](https://app.mensara.ai/how-it-works/right-access)

Access is the information and actions a person is allowed to use in your Mensara Mind.

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