Prototype Constitutional-AI Style Guardrails for an Internal Chatbot
Overview
What this challenge is about.
Prototype Constitutional-AI Style Guardrails for an Internal Chatbot. Advanced challenge in code. Writing production code that solves real engineering proble...
The Brief
What you'll do, and what you'll demonstrate.
Prototype a Constitutional-AI-style guardrail system for an internal research chatbot and document deployment readiness.
This is not a coding exercise. It is the work a software engineer does between a Jira ticket and a merged PR. That distinction matters to every hiring manager who has seen candidates solve LeetCode problems and none who have shipped production code under real constraints.
When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."
Earning criteria — what you'll demonstrate
- Author an internal-use constitution for an LLM application
- Implement a critique-and-revise loop in code
- Measure over-refusal as honestly as refusal — both are failures
- Plan a staged shadow-deployment for an AI guardrail system
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Constitutional Ai
Apply constitutional ai to solve real industry problems and demonstrate production-level capability.
- Alignment Techniques
Apply alignment techniques to solve real industry problems and demonstrate production-level capability.
- Llm Evaluation
Apply llm evaluation to solve real industry problems and demonstrate production-level capability.
- Prompt Engineering
Apply prompt engineering to solve real industry problems and demonstrate production-level capability.
- Safety Evaluation
Apply safety evaluation to solve real industry problems and demonstrate production-level capability.
- Ai Governance
Apply ai governance to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Safety Researcher
Building practical alignment scaffolding (constitution + critique loop + over-refusal eval) is exactly the safety researcher's contribution to a deploying org.
This challenge sharpens
- constitutional-ai
- alignment-techniques
- safety-evaluation
Prompt Engineer
Designing critique prompts and measuring their effect on outputs is the prompt engineer's daily craft applied to safety.
This challenge sharpens
- prompt-engineering
- constitutional-ai
- llm-evaluation
AI Solutions Architect
Translating guardrail design into a deployment plan with rollback conditions is the architect's bridge between policy and product.
This challenge sharpens
- ai-governance
- alignment-techniques
- safety-evaluation