Staff-level engineer focused on AI developer experience and local-first tooling. I build the things that help developers enter flow state and stay there.
Five years building the core browsing experience at hulu.com. Currently a founding member of the AI Advance Team — a cross-disciplinary group driving AI solutions and adoption across Disney Streaming's engineering organization.
A local-first developer tool implementing the Model Context Protocol for Disney's engineering workflow. 48 tools across 10 categories: semantic code search via ChromaDB and CodeBERT embeddings, AI edit change tracking, git workflow integration, npm monorepo support, and full web project analysis. All running on the developer's machine, not in the cloud. Designed for simple npm/git-clone distribution across Disney engineering teams.
A native macOS application for managing, editing, and sending prompts to AI assistants. Built with SwiftUI and a hybrid JavaScript editor, Promptdown treats prompts as first-class documents — taggable, searchable, and reusable — with direct integration into Claude Desktop and ChatGPT via accessibility APIs.
promptdown.ai
Created and hosted an internal podcast at Disney covering MCP development, agentic runbooks, AI-assisted workflows, and developer tooling. Two seasons, seven-plus episodes — built to shift engineering culture, not just ship code.
A speech-to-text tool built internally at Disney to streamline voice-driven developer workflows. Converts spoken input into structured text for use across development tools and communication platforms. Adopted across multiple teams.
A comprehensive architecture specification (v8) for a human-in-the-loop AI orchestration system. Coordinates agents, artifacts, and decisions through filesystem I/O and append-only event sourcing. Restart-safe and crash-recoverable by design — workflows survive agent failures, machine reboots, and session loss, then rehydrate from canonical artifacts and event receipts. Features a monitor agent for external health observation, autonomous correction before human escalation, and Git worktree isolation for concurrent workflows.
The developer's local machine is the most under-invested surface in AI tooling. The industry is racing to put agents in the cloud. I think the bigger opportunity is making the individual developer's daily experience dramatically better — their editor, their terminal, their flow. That's what every project above is about.
I started at Microsoft, where I shipped Windows Movie Maker v1 as a program manager. From there I founded Spiral9, a design and development consultancy I ran for 17 years — scaled it to 14 people with clients including Adobe, TiVo, Cisco, Facebook, and Disney. Full lifecycle: sales, hiring, architecture, development, deployment across web, mobile, desktop, and connected TV.
Along the way I'm a co-inventor on multiple US patents for mobile device customer self-support methods — originally filed via SNAPin Software, now held by Microsoft Technology Licensing.
I went back to deep individual contributor work because the most interesting problems in software right now are in the developer's hands, not in the org chart.
Open to conversations about AI developer experience, local-first tooling, and product engineering roles.
keldon@rushkeldon.com