Customer Email Drafting with Claude Code: Result JSON Schema

A production playbook for customer email drafting in cross-industry operations using Claude Code: result json schema, run-scoped inputs, logs, typed results, and artifacts.

Audience: Customer-facing teams

The problem

Customer-facing teams need customer email drafting to run repeatedly against tickets, account context, policy, and tone examples. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Define the outer result contract once, let the customer email drafting skill own body.data, and reject terminal output that does not match the expected schema.

Tradeoffs and failure modes

Schema enforcement adds upfront design work, but removes prompt parsing from the product surface. For customer email drafting, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.

Result shape

{
  "schema_version": "argo.result.v1",
  "summary": "customer email drafting completed",
  "body": { "type": "customer_email_drafting", "data": {}, "exceptions": [] },
  "artifacts": []
}

Run this on Argo