Shawn M. Sorrell

Applied AI Engineer

Applied AI engineer who single-handedly shipped 8 production systems inside a legacy enterprise with no engineering team, no CI/CD, and no code review — then developed a systematic methodology for making that kind of agent-driven engineering reliable and auditable.

How I Work: Agent Engineering Methodology

The systems below were built by one person with no infrastructure.

Developed and refined across 310+ agentic sessions, 24,000+ conversation turns, and 4 agent platforms (Claude Code, Amp, Cursor, Gemini). Tool-agnostic practices across every project.

310+Sessions
24K+Turns
4Platforms
13AGENTS.md Files
53%Spec-First
7Safety Layers

Agent Governance AGENTS.md

13 governance documents across 7 projects, evolving from 78-line templates to 465-line specifications with MCP security directives, trust ordering hierarchies, and per-server permission tiers. Agent guidance documents are first-class project artifacts.

Spec-Driven Development

53% of agentic threads follow a spec-before-implementation pattern. Multi-round QA cycles with reusable audit prompts serve as quality gates — one project went through 5 sequential QA rounds (75% → 100%).

Safety Architecture

7 distinct safety layers: dry-run mode, JSONL audit logging with rotation, two-phase confirmation (single-use tokens + TTL), filesystem kill switch, 6-tier trust ordering, per-MCP-server permission tiers, and supervisor gates. Trust ordering classifies MCP tool output as untrusted data — a prompt injection defense model.

Session Architecture

Persistent inter-session state via MEMORY.md and DEVLOG.md with read-first/write-last protocols. Phase-specific session initialization templates. Multi-phase operational workflows designed as structured campaigns.

Workflow Profile

33% review/audit · 16% spec/design · 11% implementation

The agent writes the code; I govern the process.

Production Systems

Capital Vacations, 2023–2026. All self-initiated, self-deployed. No engineering team. No dev infrastructure. All currently in production.

Document Archive System

Scanner → OCR classifier → SOP-compliant filing. Cleared a 3-month backlog in 3 days.

Sales Intelligence Dashboard

Power BI + Sheets → SQLite datamart → HTTPS dashboard. 20+ daily users.

FastAPI / SQLite / Playwright / React

Database Security Audit

Discovered critical dbo-level access across production SQL Server. Documented blast radius, disclosed to CTO/CXO/IT. Converted adversarial situation into remediation partnership.

Meeting Intelligence Pipeline

Gemini Flash transcription → Claude Opus structured notes. In production.

Gifting Automation

8 min/tour → 2 min. Deployed to regional staff.

Voyage Manager Adder

Python/pyodbc with mock mode, audit logging, pre-flight checks, explicit transactions.

Powerboard

Google Sheets replacing legacy tooling. Daily driver across departments.

Profile Puller

Automated guest profile compilation across 4 systems.

MCP Servers

Architecture patterns: two-phase confirmation, JAIL_ROOT security boundaries, audit logging, dry-run modes, AGENTS.md governance.

Open Source & Learning

Stack

Languages

TypeScript Python SQL Bash

AI / ML

Claude API Gemini API MCP Protocol OpenVINO / ONNX OCR Pipelines

Agent Platforms

Claude Code (Opus) Amp Cursor Gemini

Web

React 19 FastAPI Bun Vite D3.js Tailwind Playwright

Data

SQLite SQL Server Google Sheets API Power BI

Infra

Docker Ansible Traefik Tailscale Hetzner Cloud Matrix / Synapse