Attorney & Software Developer
I’m Julian Bryant, a San Diego attorney working at the intersection of law and technology. My path started at the University of Notre Dame, where I studied Japanese and Computer Applications. This led to seven years in Okinawa, Japan—first with the JET Programme and later developing software for the Navy Marine Corps Intranet (NMCI). After returning to the U.S. to earn my J.D. from Georgetown Law, I briefly practiced venture capital law at Cooley. Realizing my passion lay elsewhere, I returned to tech to build iOS applications both at a digital agency and through my own company. In 2022, the sudden passing of a friend without an estate plan changed my trajectory. Navigating the probate process for their family showed me the profound impact I could have, prompting my return to legal practice. Today, I bridge these two worlds by building legal tech applications. I develop custom tools to optimize my own practice and automate workflows, with the ultimate goal of creating scalable solutions that help other attorneys provide more efficient, accessible service to their clients.
This is a browser-based interactive timeline tool for trust & estate matters, built for solo and small-firm attorneys who need to make sense of decades of mixed evidence — life events, medical records, financial transactions, court filings, and disputes — without the overhead of a full case-management platform. Matters are stored as single JSON files on your own disk (no backend, no cloud), with documents linked in place via the File System Access API and excerpts attached to specific events. An optional LLM import flow uses your own Claude API key to extract structured events from PDFs and images, with a human-in-the-loop review screen. In the screenshot and demo URL, I extracted all case citations and events from Louisiana v. Callais SCOTUS opinion as an interactive timeline.
I built an internal tool that uses language models to stress-test estate planning documents against large sets of client-specific hypothetical scenarios. The idea is to essentially borrow the software concept of unit testing and applying it to a trust or will. The process works in four steps. First, I sit down with the client's priorities. Some priorities are universal ("avoid unnecessary tax exposure"), some specific to them (in my walkthrough example, "provide for Rose and Leo, the client's children"). Second, I generate a comprehensive set of "what-ifs." Rather than just asking a model for ten scenarios and hoping it covers the right ground, I work from a matrix where the columns are stakeholders (grantor, trustee, beneficiary, etc.) and the rows are categories of life events (family dynamics, asset changes, health situations, and so on). Each cell, such as "beneficiary gets married", becomes a prompt the model expands into client-specific hypotheticals grounded in the actual family. That structure is what gives me confidence the coverage is systematic rather than whatever happens to come to mind. Third, for every scenario, I feed the model three things: the trust document, the scenario, and one client priority, and ask it to assess how exposed the client is if that scenario occurs. Fourth, the results land in a spreadsheet I can scan for elevated-risk items worth a second look. One important caveat on the scoring: the model returns a number between 0.0 and 1.0, but I don't treat the absolute value as meaningful — run the same scenario twice and you'll get different numbers. What stays consistent is the relative ranking within a set, so the same handful of weak spots keep surfacing across runs. That's what I act on. Tech stack is intentionally simple: Google's Gemini for the language model work, Google Sheets for the scenario matrix on the input side and the risk-score report on the output side, and Python to orchestrate everything. Documents and client information stay on my local machine for confidentiality; only the output analysis lives in (secured) Sheets. Full write-up, including a concrete walkthrough using a fictional "Snow White" family and trust is available at the link.
I wanted a tool that would help me collect and review news from different domains that affect my practice and interests. So I my first web application was an AI-powered news aggregator built for solo and small-firm practitioners. The tool pulls from legal trade publications, vendor blogs, and specific Google News queries, then uses Claude to cluster related stories, score each story's relevance to small-firm practice, and produce a curated weekly briefing across two news "beats": Legal Tech (practice management, AI, billing, cybersecurity) and Wills, Trusts & Probate. Built in Python with a local web UI. App is only available locally as it was meant more as a personal tool and proof of concept than a web app I wanted to scale and support for others. I can click "Regenerate" and gets a fresh, ranked newsletter in about a minute.
Since 2009, I've been participating in, organizing, and facilitating Startup Weekend events around the world. These are 3-day events where developers, designers, and entrepreneurs gather to pitch ideas for new products or businesses. They form teams and work with coaches during the weekend to hopefully launch something by Sunday night. It's a great way to help build local entrepreneurial communities and give participants a chance to take startup life for a hands-on test drive. This is a video from a more recent event I facilitated at USC in 2024.
Technology is always changing which is inThe ABA's Model Rules say lawyers have a duty of technology competence. What the rules don't address is that the economics of practice point the other way. The billable-hour model rewards time spent, not problems solved efficiently. Clients rarely have the means to evaluate which lawyer is actually using better tools. The result is a profession with a clear duty to understand technology and almost no structural incentive to act on it. I'm excited about how I think the legal market will fundamentally change in the next few years and overall I think this will benefit society.
Community doesn't happen on its own. I'm a fan of Priya Parker and her book "The Art of Gathering," where she argues that the difference between a gathering people remember and one they forget usually comes down to the intention the host or organizers brought to it. That idea resonates with me. As a biracial gay person, I've spent plenty of time in rooms where I wasn't sure I belonged, and I know how much it matters when someone notices and makes space. Building community, helping other people feel genuinely welcome, takes real effort. I try to put that effort in, both in my practice and outside of it. "True belonging doesn't require you to change who you are; it requires you to be who you are." -Brené Brown