Triage-Saurus

Trace a public endpoint through App Gateway, APIM, and AKS using harvested subscription data.

On-demand Playwright audit of a subscription's rendered React Flow diagrams - verifies the UI matches harvested Azure reality using screenshots, DOM checks, interaction tests, and diagram-to-asset comparison.

Run Triage-Saurus diagram review (screenshots, threat-model smells, and before/after report).

Promote validated learnings from a completed experiment — create detection rules, update strategy JSON, and update agent instructions for future experiments.

Validate generated architecture diagrams for hierarchy issues, missing internet ingress, network segmentation gaps, and missing components.

Generate per-resource-type cloud summaries (Key Vault, Storage Account, AKS, etc.) and persist them to the DB for the web app after triage completes.

Run two-phase repo context discovery — automated baseline (Phase 1) then intelligent code analysis (Phase 2) — to build architecture diagrams and inform scan scope.

LLM-enrich raw scanner findings with titles, descriptions, proposed fixes, and severity scores (Phase 4 of the triage pipeline).

Orchestrate a full 6-phase triage experiment — context discovery, code context, opengrep scan, LLM enrichment, skeptic reviews, and report generation.

Generate or refresh the executive risk register spreadsheet aggregating all findings with severity scores, owners, and remediation priorities.

Run Dev Skeptic and Platform Skeptic reviews on enriched findings to challenge scores, verify exploitability, and populate TL;DR executive summaries (Phase 5).