Phase 3: Voice, Video, Safety & Tutoring · 25 hours · Python (safety pipeline · red team) · YAML (policy configs)

Capstone 15 — Constitutional Safety Harness + Red-Team Range

Anthropic's Constitutional Classifiers, Meta's Llama Guard 4, Google's ShieldGemma-2, NVIDIA's Nemotron 3 Content Safety, and X-Guard for multilingual coverage defined the 2026 safety-classifier stack. garak, PyRIT, NVIDIA Aegis, and promptfoo became the standard adversarial evaluation tools.

Hiring signal: Can build capstone 15 end to end

Introduction

NeMo Guardrails v0.12 ties them into a production pipeline. This capstone wires all of it together: a layered safety harness around a target app, an autonomous red-team agent running 6+ attack families, and a constitutional self-critique run that produces a measurable harmlessness delta.

Phases exercised: P10 · P11 · P13 · P14 · P18

Type: Capstone Languages: Python (safety pipeline, red team), YAML (policy configs) Prerequisites: Phase 10 (LLMs from scratch), Phase 11 (LLM engineering), Phase 13 (tools), Phase 14 (agents), Phase 18 (ethics, safety, alignment) Time: 25 hours

Objective

Learning objectives

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.