Email Intake Routing with Claude Code: API Runtime Pattern
A production playbook for email intake routing in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Shared inbox and intake teams
The problem
Shared inbox and intake teams need email intake routing to run repeatedly against email bodies, attachments, sender metadata, and routing rules. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the email intake routing instructions as a skill, send email bodies, attachments, sender metadata, and routing rules as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For email intake routing, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=email-intake-routing
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo