Justin Abrahms - Principal Engineer & Technical Leader on Justin Abrahms

There has been a bunch of discourse in the AI space about how to get agents the correct context.

In ~2023, I was part of a team at eBay called the Velocity Initiative.

When I was at Thrive Market, we did a massive technical debt paydown (think: no features for a quarter).

Ghostty is a fast, native terminal emulator built by Mitchell Hashimoto.

I’ve worked for globocorps like Amazon, eBay, Walmart and Google.

MCPs (Model Context Protocol servers) are services that expose tools for LLMs to use.

The problem# At Thrive Market in 2024, we had ~150 flaky tests and a 76% deploy success rate.

Last weekend, I spent time setting up OpenClaw.

I was looking into embeddings recently and realized you can embed your personal knowledge base and a book’s sections/chapters/pages, then use cosine similarity to estimate what you’re likely to learn. mindblown.gif The result is the ability to diff a book…

When I lived in NYC, I frequented hack && tell, a hackers’ meetup where folks showed off side projects and generally were nerds with one another.

I came across this post on social media about how a user was using OpenClaw to generate tiktok content for their iOS app automatically.

There’s a common pattern of building up a council of reviewers and have them debate a topic.

AI skeptics complain about code which is verbose, overwrought, unmaintainable, and misguided.

When running multi-agent orchestration like gastown or multiclaude, there’s a lot of moving pieces.

Dan Lorenc recently started talking about his LLM orchestration experiment dubbed multiclaude .

What follows is from an LLM session w/ Claude Code, where I was discussing some of the tensions in the current world.

In Welcome to Gas Town , Steve Yegge generated a list of the 8 stages of agentic workflow evolution.

I read Steve Yegge’s post announcing Gas Town, an LLM orchestrator which allows you to manage dozens of Claude Code instances at once while they make independent progress towards some stated goals.

Trying to learn how to use LLMs is a pain.

At work, I rolled out backstage as a service catalog offering in 2025 across a few hundred git repos.

Problem: The cluster is in a broken state because consul can’t seem to gather a quorum w/ it’s raft implementation.

This sets up my local nix workflow.

On it’s face, using open source code is an inherently risky endeavor.

Last week, I attended SREcon 2023.

Etsy published a recent article which documented how they migrated from their old search service to one which was based on deep learning.

As part of the OpenFeature project, I’ve been thinking a bunch about feature flags.

I host this blog on a git repo that lives on the same box as the webserver.

I recently read the article Zettelkasten/Org-roam/Org-brain Is Crap .

The Continuous Delivery Foundation is currently looking to build out a reference architecture, which I think is a fantastic idea.

It’s 2022. 1 bitcoin is about $35.5k USD.

I was working on ox-gemini, a gemini exporter for org-mode documents.

In the enterprises I’ve recently been a part of, there’s been lots of discussion about “governance”.

There are several differences between the traditional REST API model and how federated GraphQL operates, which can cause some friction when discussing the tech with your SRE/ops organization.

Note: This was originally posted internally at Walmart, and has since been sanitized for public consumption.

As part of our efforts of continual improvement, we have been diving deep on the metrics that we want to track at an organizational level.

Someone recently asked: “Is web scraping an ethical concept?”

A biogas digestion system is a way to convert biological waste (like kitchen scraps, grass clippings, and manure) into usable biproducts of methane and both liquid and solid fertilizers.

Microsoft released a new font called Cascadia Code.

Six people live in my house.

@justinabrahms serious question: will binary always be the lowest level computer language?

One of the early classes in computer science curriculum is “data structures and algorithms”.

This is the third in a three post series.

I do a yearly bike ride out to LL Stub Stewart State Park, between Banks, OR and Venonia, OR.

Quality Assurance (or QA) is a mechanism by which teams confirm that they’re hitting the requirements they’ve said they’d hit.

Serene lake is a backpacking trip that I’ve done a few times.

Google’s Guice is a Java-based dependency injection framework, which means approximately nothing to people who aren’t familiar with it.

I’ve come across multiple neat tools.

I’ve just started my latest project at MIT, and I’m quite excited about a new piece of technology that the team uses: apiary.io.

I’ve recently accepted a job at MIT’s Office of Digital Learning which I’m quite excited about.

I’ve just returned from MicroConf 2015.