I audit how teams work, build self-reviewing multi-agent workflows with clear human checkpoints, and wire the cross-family LLM quality gates that keep production output accurate.
- Portfolio & Live 3-Model JD/Workflow Diagnostic: https://jdurey.github.io
- Entity Profile & Career Bridge: https://jdurey.github.io/joshua-durey/
- Hire / 2-Week Fixed-Scope Workflow Sprints: https://jdurey.github.io/hire/
- Live 3-Minute Interactive AI Video Twin: https://jdurey.github.io/interview/
- Book a 20-Minute Scope Call: https://cal.com/joshua-durey-wqgvgp/20-min-scope-call
- Remote Streamable HTTP MCP Server (
io.github.jdurey/human-creative):https://josh-employer-funnel.josh-durey.workers.dev/mcp(source)
Earlier in my career, I spent fifteen years in international schools and curriculum leadership across Asia and the US and earned an M.A. in Applied Linguistics from the University of Birmingham. Treating prompts, rubrics, and model outputs as testable linguistic specs led directly into large-scale agentic engineering: governing 52,167 multi-agent .jsonl sessions, wiring 30+ deterministic Python hook gates, auditing 88,000 API calls across 12 models, and building automated SOP-to-SCORM 1.2 compilers before founding Human Creative.
Today my work is horizontal across operations, customer support, compliance, and enterprise L&D teams (US Citizen in Seoul, working 100% remotely in English via US W-2 EOR, US LLC B2B contract, or fixed-scope sprints).
| Metric | Verified Production Proof |
|---|---|
| 52,167 | Multi-agent .jsonl sessions governed with 30+ Python hook gates and SHA-256 merge receipts |
| 88,000 | API calls audited across 12 models, catching 324 silent HTTP 200 length truncations (telemetry-gates) |
| $17 | Total API spend across 23,740 calls via a 6-rung policy & cost router at 0.0% false-pass (6-rung guide) |
| 55+ | Runnable workflow, rubric, and quality-gate case studies published at https://jdurey.github.io/work/ |
- Hiring an Applied AI Enablement Lead: 30-60-90 Day Playbook
- Enterprise AI Workflow Audit Checklist: Payoff, Risk & Human Checkpoints
- Self-Reviewing Agentic Workflows Non-Technical Teams Trust
- LLM-as-a-Judge Calibration: Stopping Self-Bias & Silent Truncations
- SOP-to-SCORM 1.2 AI Pipeline: Zero-Hallucination Corporate Training
- 6-Rung LLM Cost & Latency Routing
- AI Curriculum & QTI Assessment Quality Control
- Two-Week Fixed-Scope AI Workflow & QC Sprints
- Corporate L&D Zero-Hallucination SOP-to-SCORM & Video Factory ($99 Instant Download + 65m Video Masterclass): https://whop.com/checkout/plan_y1ACgqNYGtul8/ | Live SCORM 1.2 Demo
- Enterprise AI Eval, 6-Rung Cost Router & REA AgentEnv Pro Kit ($79 Instant Download + 64m Video Masterclass): https://whop.com/checkout/plan_lGsdWjQsePkvO/
- Amazon Paperback (ISBN
9798142559005, ASINB0HRQFWFPR): AI for Corporate Training & Instructional Design: The UbD Glass-Box Playbook - Udemy Instructor Hub (31,500+ Learners): https://www.udemy.com/user/joshuadurey/