Proof before promotion

Portfolio project briefs for practical AI work

These are original public briefs derived from the capabilities taught in Ropes. They are not student submissions, client case studies, or promises of commercial results.

AI automation
Lead qualification and routing system
Problem

A small sales team reviews every inbound lead manually.

Approach

Map qualification rules, add source-grounded enrichment, use AI only for ambiguous classification, and require approval before routing.

Portfolio deliverable

Workflow map, configured automation, evaluation cases, decision log, and handover guide.

RAG
Cited internal knowledge assistant
Problem

Employees cannot find consistent answers across policies and SOPs.

Approach

Prepare a safe document set, design retrieval, require citations, test unanswered questions, and state access assumptions.

Portfolio deliverable

Working RAG assistant, retrieval test set, limitations report, and operating documentation.

AI security
AI application security review
Problem

A tool-using assistant has been built without a structured threat review.

Approach

Map assets and trust boundaries, test injection and permission abuse, apply layered controls, and document residual risk.

Portfolio deliverable

Threat model, red-team cases, mitigation evidence, and review report.

AI testing
LLM regression evaluation suite
Problem

Prompt and model changes ship without evidence that quality remains acceptable.

Approach

Create a golden dataset, define task-specific criteria, benchmark a baseline, and add release thresholds.

Portfolio deliverable

Evaluation harness, results dashboard, regression policy, and findings summary.

MLOps
Production model pipeline
Problem

A useful model exists only as an untracked notebook.

Approach

Track experiments, package the model, expose an endpoint, monitor performance, and define retraining triggers.

Portfolio deliverable

Reproducible pipeline, container, endpoint, monitoring view, and runbook.

AI product management
AI feature PRD and evaluation plan
Problem

A team wants an AI feature but has not defined value, failure behaviour, or success criteria.

Approach

Research the user need, frame the AI role, define non-AI fallbacks, set evaluation metrics, and document trade-offs.

Portfolio deliverable

Feature brief, PRD, evaluation plan, risk register, and two-quarter roadmap.