The problem
What was broken before AI
Customer-facing work creates a lot of invisible follow-up. Meeting notes need to be summarized. CRMs need to be updated. Customer context needs to be found before the next call. Support conversations contain useful knowledge, but that knowledge often disappears inside Slack threads or ticket histories. None of these tasks is glamorous, but skipping them makes the team less prepared and the knowledge base less useful.
What changed
What the use case made possible
Reid connects Claude to Zapier’s automation layer so AI can reach the apps where the work actually happens. In one workflow, Claude follows detailed project instructions and uses Zapier-connected tools to update CRM records from meeting notes. In another, a Zap prepares customer research before an interview. A third turns closed support conversations into proposed FAQ entries, with a human approving them before they become part of the knowledge base.
Why this matters
Why this use case is worth studying
Reid’s workflow is useful because it does not force every task into the same AI shape. Some work belongs inside a conversational assistant, especially when judgment and context matter. Other work is better as a background automation that runs the same way every time. By using both, he gets the flexibility of Claude and the reliability of Zapier without pretending one tool should do everything.
Use this when
When this pattern applies
Use this pattern when important follow-up work keeps falling between meetings, support conversations, and internal systems. It works especially well when the task has both judgment and repetition: AI can interpret messy notes or conversations, while automation moves the result into the right place every time.
