Quotes needed from shower glass suppliers in the area. OpenClaw researched them, sent out the emails, collated the responses and handled the back-and-forth, all in one chat thread.
Result Their first useful non-code agent experiment
“my first useful non-code agentic experiment was @openclaw getting quotes from shower glass suppliers in the area. It was cool to go from research to having it send out emails, collate responses and handle back-and-forth, all in a chat thread”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
They wanted quotes from shower glass suppliers in their area. They set OpenClaw on the task from a single chat thread, having it research suppliers and then send out emails asking for quotes.
OpenClaw collated the suppliers’ responses and handled the back-and-forth, all within the same chat thread. They called it their first useful non-code agentic experiment.
Ask your agent (such as OpenClaw) to find local suppliers for [item or service], email each one requesting a quote, then collate the replies and handle any follow-up questions itself in the same chat thread so you can compare quotes without switching between emails.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.