Portfolio case studies

Proof of work, written as operating evidence.

These public-safe case studies translate working AI-agent systems into recruiter-readable evidence: problem, constraints, architecture, operational decisions, impact, and next improvements.

View Projects Download Resume

Index

Case studies from shipped products and local operating systems.

OpsPilotAI Public-safe showcase

OpsPilotAI: AI Automation Planning With Responsible Guardrails

OpsPilotAI is a deployed AI operations and automation concept built around a practical question: before automating a business workflow, can the team define the problem, pilot scope, risk posture, human-review requirements, and success measures clearly enough to act safely?

Read case study

Hermes Agent System Draft public-safe

Turning YouTube Research Into Operational Memory

Useful AI and automation lessons were arriving as videos, but raw links are not durable knowledge. This workflow turns source material into searchable, provenance-preserving operating context without wasting tokens or publishing private internals.

Read case study

Hermes Agent System Draft public-safe

Searchable Learning Ledger and Opportunity Finder

The learning system produced useful JSON ledgers, Markdown demos, skills, and scripts. This case study shows the layer that turns those artifacts into an auditable implementation queue.

Read case study

Hermes Agent System Draft public-safe

No-LLM YouTube Trigger and Cost-Control Pattern

Simple structured events should not wake a model on a schedule. This case study shows how the YouTube learning workflow moved toward cheap event detection and reserved LLM reasoning for actual analysis.

Read case study

Hermes Agent System Draft public-safe

Skill Curator Audit for Agent Memory Hygiene

An assistant that learns over time needs governance. This case study shows a report-first curator pattern that improves memory hygiene without unsafe automatic deletion.

Read case study