Skip to content
agentusehub

Book weekly restaurants and surface daily discoveries from your data

An OpenClaw agent with access to ChatGPT, Google and Instagram history books weekly restaurants, sends daily recommendations, and proposes memory updates for the user to approve.

Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

An OpenClaw agent with access to ChatGPT, Google and Instagram history books weekly restaurants, sends daily recommendations, and proposes memory updates for the user to approve.

Reported experience

  1. What they did

    The commenter gave an OpenClaw agent access to their ChatGPT, Google and Instagram history through context-use. The agent uses years of Instagram stories to find and book a restaurant each week. Each day it sends three discoveries drawn from their activity, plus a proposed memory diff that the user edits and approves by hand.

  2. How it went

    The agent found and booked Osteria Vibrato, where the user dined the previous night. It also suggested The God of Small Things after spotting an upcoming Kerala trip, and the user loved the book.

  3. Worth knowing

    The commenter is on the team building context-use, so this is a firsthand but promotional account, and it gives no cost or setup detail.

Example prompts

Try with OpenClaw
Using my [ChatGPT/Google/Instagram] history that I've given you access to, learn my food tastes and find [number] restaurants in [city] I'd probably like. Each [day of week], propose one booking for [party size] on [preferred evening], and each morning send me one recommendation. Pause and ask me before making any reservation, and show me any memory updates for approval before saving them.
Life Admin & Home

Coach training and diet from wearable data

The poster uses Claude with Apple Health, nutrition and lifting app data, plus medication and bloodwork files, and has it maintain an HTML dashboard.

Claude