Natural language to reviewed, deployable infrastructure

A hackathon design for turning infrastructure requests into pull-request-ready Bicep and Terraform, behind deterministic validation and a human approval gate.

  • Terraform
  • Bicep
  • MCP
  • Security review
  • Human-in-the-loop

Situation

Infrastructure requests queue behind the small number of engineers who can write Bicep and Terraform correctly. The bottleneck is not intent, it is translation and review. A hackathon was the chance to ask what a governed version of that would have to look like.

Constraint

Generated infrastructure code cannot be trusted on sight. Any design worth building assumes the model is wrong sometimes. Nothing reaches an environment without deterministic validation, a standards and security review, and an explicit human approval.

What I built

A multi-agent pipeline spanning consultation, code generation, deterministic validation, standards and security review, pull-request preparation, plan review, and a human deployment approval gate, across Azure AI Foundry, Microsoft Agent Framework, MCP servers and GitHub workflows.

What I owned

The architecture narrative and the shape of the pipeline: where the gates go, what each stage has to prove before the next one runs, and why engineer-controlled release is the point of the design.

Result

A hackathon entry, running since April 2026. It was built and demonstrated. It has never handled production requests, and it is on this page as architecture.

No production metric. This was built and demonstrated at a hackathon and never handled real requests.