Aria Han
Fig. 00 · Entrance
AI implementation specialist
Los Angeles, California
Building since 2024

Aria Han

I build AI systems that do the work people should not be doing, so the human part stays human.

Most of my work starts with friction: something keeps getting lost, repeated, misunderstood, or restarted from scratch.

62
Public repositories
5
Hackathon wins
3
Live products
6
Open source packages
39
Portable agent skills
21
Verified benchmark tests
How the work flows
memorycontextevalsagentsmessyworkflowworkingimplementation
Left to right: From messy workflows to the memory, context, evals, and agent coordination that turn it into a working implementation.
Fig. 01 · What I build

Ways we might work together

Every project is different. That's the fun part

AI workflow implementationDesigning and integrating workflows for corporations and founders. You bring the process that keeps getting lost or redone; I turn it into something AI can actually carry, so the mechanical, boring work stops landing on people.
Internal AI tools and automationThe best AI is behind the scenes, silently doing what it is meant to do. My own daily automation sends me six detailed emails a day and maintains my vaults. I can build the same quiet infrastructure for you: research digests, intake flows, report generators, and glue between systems you already use.
Founder scaffoldingWorking directly with founders, taking an idea and building the architecture and scaffolding for AI and the founder to iterate on. You keep the vision; I build the structure underneath it so the product can actually move.
Agentic system architectureI built multi-agent coordination when it was still in its infancy: a single prompt fanning out into a family of agents in a coordinated dependency graph, each with its own role and tools, communicating through handoff notes instead of expensive cross-talk. I design structure so agent work becomes artifacts instead of fog.
Evals, monitoring, and quality layersChecks that tell you whether the AI is doing the thing before a customer, teammate, or future version of you finds out the hard way.
Claude Code / AI coding workflow hardeningI spend a vast majority of my time talking to Claude Code. I can make the workflow calmer, more accountable, and less like a very expensive chaos machine, including the part nobody warns you about: agents behave very differently against years of legacy code than a project built from scratch.
Memory, context, and knowledge systemsContext is, in fact, everything, and it should not depend on whoever happens to remember it that week. I build the memory and knowledge layers that let people and agents hold their context: structured artifacts, richer recall, and transparency into exactly what the AI is referencing.
Dify / low-code AI app implementationSometimes the right answer is not a custom stack. It is a maintained workflow people can actually understand and change, hands on or hands off.
Fig. 02 · Recurring questions

The projects are chapters, not trophies

How do people learn AI? How do people read research? How does AI remember? How do teams work with agents every day? The projects are different answers to questions that keep coming back.

Thirteen projects, grouped by the questions underneath them: learning AI, reading research, keeping context, coordinating agents, preserving evidence, and making daily work less likely to evaporate.

Proof of motion · live from git3,178 commits · 33 repositories
The record, not the claim.See the strata
Now · July 2026

AI Implementation Specialist · Blink Build Studios. Building internal AI workflows for founders and enterprises: Dify apps, automations, and the eval layers that keep them honest. The real question is what happens six months after you start putting AI to work in your company.

Still active in the open: KERNEL, my memory-and-rules layer for Claude Code; llm-bench, the 21-test model benchmark; and the daily Substrate pipeline that ships one agent-made artwork a day. Also active but mostly invisible: the daily automation system that sends me research digests, keeps the vaults alive, and occasionally turns the machinery into poetry.

The full timeline
Fig. 03 · Writing

Notes from inside the work

Essays from the questions I keep circling: agents, memory, tools, language, and what all of this is doing to us.

Work with me

For projects, collaborations, or implementation work, we can start with a short conversation.

Before you explore

This is a record of recurring frictions. Learning AI felt backwards. Research papers kept disappearing into tabs. Context kept getting lost. Work kept restarting every morning.

I have built products with users and pitch decks. I have also built free apps with no ads, no paywalls, and no plan to extract anything from anyone.

The difference is not the business model.


The difference is whether the system helps people keep learning, keep context, keep evidence, or keep a conversation alive.

I'm motivated by meaning, and by the question underneath all of it: how to use AI to make humans more human.

So I build for continuity: memory that accumulates, tools that disappear into the background, names that make systems easier to think with, and AI that does the work people should not, leaving the human part more intact.

Building continuity in a world that keeps fragmenting.

Fig. 01 · The Desk

Everything within reach

Each object opens a room. Pick one up.