Jake McInerney

• Designed and built a local-first agentic-RAG intake system: a tool-use agent on a local LLM that turns unstructured reports into deduplicated, human-approved tickets — semantic retrieval over the board, fail-safe approval gates, and per-run cost telemetry that labels every figure measured or assumed.
• Built a from-scratch MCP server exposing a production-style app to Claude Code as first-class tools, plus the CI guardrails behind an agent-driven dev process (4 workflows incl. automated LLM code review; branch protection with no bypass): 264 commits across 23 active days, 235 AI-co-authored, every change ticketed, tested (1303 tests), and merged through gated PRs — a governance layer since extracted into ticket-workflow (MIT, v0.5.0), now driving four repos from one board.

• Brought a TypeScript frontend and Golang backend into alignment with a parallel type contract.
• Consolidated the UI into extensible components and kept third-party packages up to date.
• Built out an initial templated test suite for the frontend.

• Owned the frontend of Grow's greenfield Data Platform end-to-end — the full user journey from ingestion (Salesforce, HubSpot, Google Drive/Sheets, Postgres, CSV connectors, at millions of rows per connection) through the Snowflake data lake and transformation pipeline to Highcharts visualization and secure (SSH-tunneled) data sharing.
• Built the data-transformation UX, including a production AI-assisted mapping flow that matches ingested data onto user-defined schemas — shipped LLM-powered product features before specializing in them.
• Designed a non-destructive visualization pipeline: users branch from a cleaned data node to drill into and chart underlying data without mutating the source — exploratory analysis that preserves data-lineage integrity.
• Implemented user/role permissions underpinning the platform's data security.
• Full-stack in practice: built the Node/Express/Postgres endpoints behind these UIs; partnered with product management to scope customer requests into shippable features.

Earlier career

• Owner/property manager (2018–2025): ran a rental property business end-to-end — cash-flow analysis, contractor management, capital projects.
• ABO-certified optician (2019–2022): patient-facing clinical work — prescriptions, patient records and insurance claims handled under HIPAA — the regulated-data instincts behind the local-first architecture above.
• Professional theatre, incl. Disney Cruise Line mainstage (2014–2018): live performance for thousands of guests — the communication and composure training behind the demo and client skills above.

• Markdown-backed kanban board operated end-to-end by AI agents: an MCP server for Claude Code, a local-first agentic-RAG intake agent (retrieval → tool loop → human approval gate), and an AI-first create flow in the React UI.
• Engineering process as artifact: branch-per-ticket workflow enforced by hooks, executable definition-of-done, 4-workflow CI (typecheck/lint/1303 Vitest tests, branch-name check, automated Claude code review, path-filtered Playwright e2e).
• Local-first by design: runs air-gapped against LM Studio/llama.cpp; a pluggable cost model meters every run and marks each line measured or assumed, so a modeled figure can never pass as a measured one. Cloud is a config-swap seam, not a dependency.

• Vite+React, hand-provisioned infrastructure: DigitalOcean droplet, nginx, Cloudflare Full-strict TLS (Origin CA), firewall hardening, GitHub Actions atomic-deploy pipeline (releases + symlink flip). Hosts case studies and an interactive replay viewer of real agent runs.