Trabajo
Instagram DM funnel 3×/day: suggest next reply, you mark Sent
Price questions sink in Instagram DMs and nobody follows up.
Qué dolía
@RafaelGaldino runs two Grok Bot routines 3×/day (10:47, 15:47, 20:47): pull Instagram DMs into a CRM list with stages, then suggest each conversation's next step. He marks Enviei (Sent) or Não enviar (Don't send) — bot organizes and suggests; he replies and approves. Author-quoted Portuguese prompt. Not affiliated with xAI.
Qué instalar o crear
Fixed pulls → stage each lead → suggest reply → you mark Sent / Don't send.
Bots
DM funnel bot
Pulls DMs on a schedule, stages leads, suggests next replies; never sends.
Plugins
Navegador
Opcional
Archivos
Lead stages: arrived / replied / in conversation / closed.
Rutinas
A few times daily: pull DMs; suggest next replies; wait for Sent / Don't send.
El prompt
DM stage + suggest next reply (author-quoted)
Quoted from @RafaelGaldino — as published. Do not invent a second system prompt.
Leia as conversas novas do direct. Para cada uma, diga em que etapa o lead está, o que ele pediu e sugira a próxima resposta. Não envie nada. Me mostre a lista e espere eu marcar Enviei ou Não enviar.
Primer uso
- 1Read https://x.com/RafaelGaldino/status/2113754178224783531 (credit @RafaelGaldino).
- 2Build one list for DMs with stages: arrived, replied, in conversation, closed.
- 3Hang a routine a few times a day to pull new DMs into that list.
- 4Paste the author-quoted prompt so the bot suggests the next reply per thread and waits.
- 5For each suggestion mark Sent or Don't send; nothing goes out without that mark.
Valla de aprobación
Bot never sends; you mark Sent or Don't send on every suggestion.
Qué ajustar
Steal the buttons: suggest is free; send waits for your mark.
Fuente
Rafael Galdino @RafaelGaldino · Publicación original
Sin afiliación con xAI. No escribimos este prompt. Siguen aplicando las condiciones de las plantillas de terceros.
Paquete Pro
¿Quieres la configuración completa, no solo la idea?
Los paquetes Pro te dan el texto de la tarea, los prompts, los horarios y los tropiezos de los casos de uso más populares.