Energy: Asset Maintenance Log Review with Claude Code: API Runtime Pattern
A production playbook for asset maintenance log review in energy operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Energy and industrial maintenance teams
The problem
Energy and industrial maintenance teams need asset maintenance log review to run repeatedly against maintenance logs, sensor exports, work orders, and failure reports. In energy operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the asset maintenance log review instructions as a skill, send maintenance logs, sensor exports, work orders, and failure reports 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 asset maintenance log review, 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=energy-asset-maintenance-log-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo