{"person":{"bio":["I'm an AI consultant in Los Angeles. I work with founders, independent builders, and operations teams that want to put AI to work now.","For founders and other builders, that can mean building an AI product, repairing one that got stuck after an AI-assisted build, or setting up AI workflows for research, writing, operations, and decision-making. If you have something that mostly works but has become hard to debug, extend, or trust, that is exactly what a project review is for. I can teach the workflow, build it, or do both.","For companies, I focus on internal operations. I get close to the process as it actually runs, find where context is lost or work keeps getting repeated, and build an AI workflow around the tools and information the team already uses.","Before consulting, I built three AI products in San Francisco and led the teams that built them. My public work includes App Store apps, Python packages, open source evaluation and memory tools, and KERNEL, the plugin I use to run coding agents on real repositories.","I get a daily research digest and built a research paper reading app because I want the papers themselves to be one of my main sources, not only posts about them. I review new models, tools, methods, and research every week, then update existing work when a better approach becomes practical.","My work and writing are public at ariaxhan.com, including the experiments that failed. I'm available for a quick call or a project review."],"booking":{"line":"I'm available for a quick call or a project review.","url":"https://cal.com/aria-han/15min"},"email":"ariaxhan@gmail.com","handle":"ariaxhan","location":"Los Angeles, California","name":"Aria Han","oneLiner":"AI for work, AI for humans.","proof":{"benchmarkTests":{"label":"Verified benchmark tests","source":"llm-bench README","value":"21","verified":"2026-07-06"},"hackathonWins":{"label":"Hackathon wins","source":"Devpost and GitHub links on /hackathons; 5 wins, 1 finalist","value":"5","verified":"2026-07-06"},"liveProducts":{"label":"Live products","source":"ModelMind + Paper Rooms (App Store), our4cuts (web)","value":"3","verified":"2026-07-06"},"portableSkills":{"label":"Portable agent skills","source":"SKILL.md count, the-agent-library","value":"39","verified":"2026-07-06"},"publicRepos":{"label":"Public repositories","source":"api.github.com/users/ariaxhan","value":"62","verified":"2026-07-06"},"substratePieces":{"label":"Open source packages","source":"open source packages on GitHub","value":"7","verified":"2026-07-13"}},"role":"AI consultant","services":["AI product building and repair","AI project reviews","Practical AI workflow design and training","Internal AI workflow automation"],"socials":{"devpost":"https://devpost.com/ariaxhan","github":"https://github.com/ariaxhan","huggingface":"https://huggingface.co/ariaxhan","linkedin":"https://www.linkedin.com/in/ariahan/","medium":"https://medium.com/@ariaxhan","pypi":"https://pypi.org/user/ariaxhan/","x":"https://x.com/aria__han"},"strangeLine":"Workflows, systems, and everything else to go from “we need AI” to “we have AI.”","tldr":"Aria Han is an AI consultant in Los Angeles who builds and repairs AI products for founders and independent builders, and creates internal AI workflows for operations teams.","url":"https://ariaxhan.com","whatIDo":"I review new models, tools, methods, and research every week, then update existing work when a better approach becomes practical."},"routes":[{"path":"/","purpose":"Home. The ten-second introduction to Aria and the work."},{"path":"/about/","purpose":"Who Aria is, the working pattern, and the verified numbers."},{"path":"/systems/","purpose":"Shipped products and companies, each with proof."},{"path":"/open-source/","purpose":"Public repositories and research, each with proof."},{"path":"/writing/","purpose":"Essays grouped by theme, links stay on Medium."},{"path":"/proof/","purpose":"Proof of motion, an archaeological build record."},{"path":"/reading/","purpose":"Recent books and reading notes, the inputs behind the work."},{"path":"/timeline/","purpose":"Roles and milestones by year."},{"path":"/hackathons/","purpose":"Builds under pressure and hackathon wins."},{"path":"/contact/","purpose":"Engagement types, fit filter, and booking."},{"path":"/project-review/","purpose":"Structured intake for a paid project review."}],"endpoints":[{"path":"/llms.txt","purpose":"Concise agent guide to this site."},{"path":"/llms-full.txt","purpose":"Complete markdown mirror of the whole site."},{"path":"/api/site-index.json","purpose":"Site identity, route map, and endpoint list."},{"path":"/api/projects.json","purpose":"Structured records for every project."},{"path":"/api/writing.json","purpose":"Articles grouped by theme."},{"path":"/api/work-with-me.json","purpose":"Engagement types, fit filter, and booking."},{"path":"/.well-known/agent-card.json","purpose":"A2A agent card."},{"path":"/.well-known/mcp/server-card.json","purpose":"MCP server card."},{"path":"/.well-known/api-catalog","purpose":"Linkset of machine endpoints."},{"path":"/.well-known/agent-skills/index.json","purpose":"Agent skills index."},{"path":"/mcp","purpose":"MCP endpoint, JSON-RPC over streamable HTTP."}]}