Agents In Use
What’s new todayLast update
1005 additions

How to use OpenClaw for a living family scrapbook

OpenClaw turns family photos and school projects into journal entries with calendar context and grandparent comments; inferred details remain unverified.

Published linkedin.comAgent: OpenClaw
OUR ADAPTATION

Suggested prompt

Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.

Turn the family photos we intentionally send into draft scrapbook entries. Distinguish visible image details from calendar-inferred locations or attendees, and flag uncertain context for parent review. Provide access-controlled family and grandparent views with comments; do not create calendar events or import additional private material without approval.

What happened

Lai reports recurring family use of the generated scrapbook and grandparent comments; security assurances and inferred event context are not independently audited.

Reported by Jonathan Lai — LinkedIn

How the agent did it

  1. The parents text OpenClaw photographs of art, projects and family moments during the day.
  2. The agent converts images into journal entries and draws contextual inferences from the shared calendar.
  3. Family members read the entries while grandparents follow and comment through the web app.

Where a person stepped in

The parents select and submit the images. The post does not describe a formal per-entry approval process or independent verification of inferred calendar context.

Jonathan Lai and his wife use OpenClaw as a living family scrapbook. Throughout the day, they text it photographs of their children’s art, school projects and ordinary moments instead of separately composing journal entries.

The agent scans those images and converts them into written entries. It also consults the shared family calendar to infer locations, attendees and events. That context enriches a photo’s description, although an inferred connection is not independently confirmed merely because the calendar contains a matching event.

Grandparents can follow and comment through a web application. Lai reports that the children enjoy reading the entries and remind their parents to send pictures to the bot. One specific example is its recognition of an imaginary animal his son created, showing the playful material this household actually submits.

The source calls the app secure but publishes no security assessment or access-control configuration. Uploading school handouts to create calendar events is listed as future work, not part of the demonstrated scrapbook. The actual result is reported recurring family use of photo-to-journal entries and shared comments, with parents supplying the material and contextual inference remaining a limitation.

Prompt
Suggested prompt (written by Agents In Use, not the author's)

Source: LinkedIn · Jonathan Lai

Frequently asked questions

Does the agent only store photographs?

No. It converts them into journal entries and uses family-calendar context for inferences.

Can grandparents participate?

The author says they can follow and comment through the web application.

Does it already create events from school handouts?

No. That is explicitly a roadmap item in the original post.

More details

About this account

The parents text OpenClaw photographs of art, projects and family moments during the day. The agent converts images into journal entries and draws contextual inferences from the shared calendar.

Primary post and exact main JSON-LD date opened. Actual family use is author-reported. Calendar details are inferences, secure-app wording is not an audit, and school-handout calendar uploads remain future scope. Suggested prompt written by Agents In Use; no verbatim original task prompt was supplied.

Credit: Jonathan Lai — LinkedIn

Source published 15 Mar 2026

Source checked 14 Oct 2026

Tools and topics

OpenClaw · Text messaging · Family calendar · Web app

family scrapbook · image journals · calendar context

Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.