OpenClaw to book dinner with payment confirmation
Eeshita Pande had her OpenClaw agent, EeClaw, find and book Osteria Vibrato, a new Italian restaurant in London. The choice was grounded in dining preferences held in onFabric, including her interest in Italian, Indian and Japanese food.
linkedin.com
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Use my dining preferences to find a Saturday dinner reservation two to four weeks ahead. Prepare the booking in the browser and request my confirmation before payment.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- Eeshita Pande
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- Pande reported a booked and paid Osteria Vibrato reservation after manual payment confirmation, then configured a weekly dinner booking job.
- Human involvement
- Pande manually confirmed the payment; the proposed bulk approval arrangement was not part of the demonstrated run.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Give EeClaw access to dining preferences and an already configured card.
- Use Playwright and restaurant booking and payment skills to arrange the table.
- Confirm payment manually, then configure a weekly future booking job.
Eeshita Pande had her OpenClaw agent, EeClaw, find and book Osteria Vibrato, a new Italian restaurant in London. The choice was grounded in dining preferences held in onFabric, including her interest in Italian, Indian and Japanese food.
The agent set up a headless browser and used Playwright for the booking workflow. Pande reported that it created two skills, one for restaurant bookings and another for payments. She had already configured a card for it to use, so the payment stage did not require discovering a new payment service.
Her account's headline describes the agent finding, booking and paying, but the body supplies an essential checkpoint: Pande manually confirmed payment. The reported transaction therefore combined agent browser work with a human confirmation. There is no published total charge, receipt or account of eating at the restaurant.
After that run, she configured a weekly cron job to arrange Saturday dinners two to four weeks ahead. That is a reported recurring setup, rather than evidence that all later reservations succeeded. She also suggested bulk payment approval at the end of a day as a possible future improvement. It was an idea prompted by this booking, not a capability demonstrated in the completed run.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: www.linkedin.com · Eeshita Pande
Frequently asked questions
What preferences guided the selection?
The agent used onFabric records showing an interest in Italian, Indian and Japanese food.
Was payment fully unattended?
No. Pande explicitly said she had to manually confirm payment.
Were the later weekly bookings verified?
The post reports the cron setup, without confirming a series of subsequent successful reservations.
More details
About this account
EeClaw researched dining preferences and operated a Playwright browser to arrange the restaurant booking and payment workflow.
Firsthand source opened and read. Suggested prompt written by us from the reported workflow; no original task prompt is quoted.
Credit: Eeshita Pande
Source published
Added to Agents In Use
Source checked
Tools and topics
OpenClaw · onFabric · Playwright · Cron
Dinner booking · Payment approval · Dining preferences · Playwright
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.