Featured
- ★herdr-fleetA terminal dashboard, written in Rust, for a fleet of Claude Code agents running in herdr panes. One screen shows each agent's status, model, context use, estimated spend, time in its current state, last line of output, and flags for agents that look stuck or are looping on the same command.
Agent skills
Seven skills I use daily, published in my GitHub profile repository. Each is a folder with a SKILL.md plus the scripts and notes it relies on, and each runs in Claude Code, Codex and the ChatGPT desktop app (install instructions).
- S1shipA closed-loop acceptance gate. It builds the app, has a fresh verifier use it for real, fixes from the repro and re-verifies, until it passes or provably stops converging.
- S2cloud-browser-loginLogs into my own accounts on any website from a cloud session, in a real Chromium browser. It picks the safest login route, asks once for exactly the secrets it needs, and records what it learns about each site.
- S3retell-voice-agentDesign, build, audit and verify Retell AI voice and SMS agents, with a three-layer verification method and a catalogue of pitfalls found on real calls.
- S4deepgram-voice-agentBuild and gauntlet-test Deepgram Voice Agent API agents against persona scenarios, checking the real bookings and emails rather than the chat.
- S5dialoraBuild, configure and verify Dialora.ai voice agents end to end, from prompts and knowledge bases to tools, phone numbers and agency sub-accounts.
- S6autonomous-systems-auditA read-only health audit of a self-driving agent harness, its test suite, knowledge graph and memory stores, backed by a telemetry probe and file and line citations.
- S7pme-cdpDrives an already-logged-in Chrome over CDP instead of a fresh browser that gets bot-blocked and logged out.
Background
Independent AI engineer and full-stack developer, working remotely from New Hampshire since October 2025. Before that, 17 years in enterprise technology sales covering networking infrastructure, cybersecurity and cloud.
Client work since January 2026 includes a marketing agency's website rebuild in Next.js 16, TypeScript and Tailwind CSS. Other projects listed on the resume are a job-application pipeline (Python, Playwright, Claude API, Supabase) and an algorithmic trading platform (Node.js, Next.js, PostgreSQL).
Anthropic Academy course certificates from April 2026 cover the Claude API, Claude Code, agent skills, subagents and the Model Context Protocol.
Tools
Languages
- Python
- TypeScript
- JavaScript
- Bash
- SQL
Front end
- React 19
- Next.js
- Vite
- Tailwind CSS
AI
- Anthropic Claude (Code, API, Agent SDK)
- OpenRouter
- LangGraph.js
- Retrieval-augmented generation
- Multi-agent orchestration
Automation
- Playwright
- n8n
- MCP
Hosting and data
- Netlify
- Cloudflare
- Supabase
- PostgreSQL
Applications
Featured project, separate from the 13 demo applications below:
- ★company-ops-agentA tool-using agent that answers questions about a real public UK retail data set and says plainly when the data cannot answer. It runs on a free server, so the first request after a pause can take about 30 seconds.
The 13 demo applications live in one repository, JDGAFX_CG_GITHUB_PORTFOLIO_APPS. Each demo is hosted on Netlify. The applications page describes what each one does.
- 01AgentFlowMulti-Agent Research Orchestrator
- 02DocMindRAG Document Intelligence
- 03CodeLens AIVerified Code Review
- 04VoxAIStreaming Voice Assistant
- 05DataPilotAI Data Analyst
- 06ModelArenaBlind Model Arena
- 07ContentForgeAgentic Content Pipeline
- 08VisionLabMultimodal Vision AI
- 09InsightHubnpm Download Analytics
- 10BrowseBotBrowser Agent with Visual Replay
- 11GraphScoutLangGraph Research Agent
- 12GraphGateGitHub Issue Triage with Approval
- 13GraphSwarmLangGraph Map-Reduce