The dark factory pattern—autonomous production systems with no human in the loop—is well-documented for application code, but applying it to infrastructure is significantly harder. Using Pulumi as the substrate, this post maps out how to build a lights-out infrastructure pipeline using the Automation API, CrossGuard policy enforcement, ESC for short-lived credentials, and Pulumi Cloud Deployments as a governed runner. The core architectural insight is the mandatory isolation between code generation and validation: a separate evaluator runs plain-English holdout scenarios against ephemeral deployments, and the generator never sees the test criteria. A four-phase rollout is outlined—from improving agent context with AGENTS.md today, to spec-driven PRs with holdout scenarios, to removing humans from the merge loop only after measurable quality gates hold over 20+ PRs, and finally full lights-out operation. Key risks covered include validator approval of bad changes, agents acquiring destructive permissions, and runaway costs, with concrete mitigations for each.

10m read timeFrom pulumi.com
Post cover image
Table of contents
What a dark factory actually isThe wall between generator and validatorWhy infrastructure is the harder versionThe interesting workA four-phase rolloutWhat could go wrongWhere to start

Sort: