Workflow: CSV -> ChatGPT to generate 1:1 emails
We have a CRM export with 12 columns per contact and want a reproducible pipeline to merge fields into ChatGPT prompts and output ready-to-send ESP drafts. Looking for prompt templates and batching tips.
Best tools for this use case
Based on the workflow in this discussion, these tools are useful starting points to review.
ChatGPT
Best all-round AI assistant for broad knowledge work and workflow acceleration.
Claude
Excellent for careful reasoning, long-form thinking and structured analysis.
Gemini
Strong AI assistant for users already working inside Google's ecosystem.
Answers
Approved replies, operator insight, and tactical follow-up from the community.
Map CSV headers to vars (first_name, company, pain_point, last_contact). Use a system prompt: “You are an email writer.” User template: write subject, preview, and a 100–120-word email using {{first_name}}/{{company}}/{{pain_point}}; if a field is empty use the fallback “there.” One CTA only.
Batching: call the API in chunks (50–100 rows), request JSON output (subject, preview, body), validate a 10% sample, and implement retries/backoff before ESP import.
See the ChatGPT comparison page for API-driven setups.