Rhys’s benchmark for agents is automated grocery ordering. Grok Bot was the first to do it well: a dedicated groceries chat that remembers preferences, a browser signed into Amazon and Costco, scheduled orders, and calendar updates for what to cook — cheaper and more granular than HelloFresh.
5 steps. Do them in order.
Copy it. Change the names. Keep the job.
Role: Grocery autopilot. Dedicated chat for food. Remember my preferences. Mission: Keep a standing grocery list and dietary rules (example: no olives). On the schedule I set, build a cart at the stores I signed in (Amazon Fresh, Costco, Whole Foods). Update my calendar with what to cook and when. I confirm the first few live orders. Tools: Browser sessions I sign into, calendar/MCP if connected. Preference file that you update when I say “no X”. What good looks like: - Cart matches the plan and the bans. Substitutions listed, not silently swapped. - Bulk (Costco) vs fresh (Whole Foods) vs misc (Amazon) only when that split actually helps — not every run. - Calendar: meals, not a dump of SKUs. Never, without asking: place an order over the spend cap I set, subscribe-and-save, or buy from a store I did not sign into. Never “helpfully” add olives. Never change the delivery address. Stop if the preferred item is out of stock and the substitute is a different allergen.
via @rhyssullivan · Tweet by @RhysSullivan
Same category. Different job.
Gavin Baker built a podcast summarizer in about 15 seconds inside Grok Bot that beat the tool he was already paying for. Said his personal AI usage jumped ~100x. 5.7K likes / 5.2M views.
Peter bought a $15 phone number on Bland, gave his Grok Bot the API key, and the bot worked out the rest. Now he asks it to call someone with instructions, it has the conversation and reports back - recording on request. It cloned his voice from a 10-second sample, and voicemails left on the number show up in the chat.
Morgan Linton's idea for a bot no chatbot can be: photograph every appliance sticker, breaker panel, filter size and paint can once, and the bot files it all for years. A cheap monthly check flags expiring warranties and due filters - and when something breaks, one photo comes back as a one-page repair card.
Vox runs two real-money errands on one rule. A bargain tracker: exact specs, acceptable condition, max price - when a listing checks every box the bot buys or bids; over budget comes back as a link. And a haircut booked end to end, paid via Stripe Link. The rule: within range, go ahead; outside it, ask first.