Article

Updating My Obsidian Daily Note Using Bases

Want to get new content as soon as it's published? I publish articles on Obsidian, productivity, and more in my community before I...

I Wanna Be Me When I Grow Up · EN

Templates as Object Oriented Knowledge Management With Obsidian

I mentioned previously that one of the things I’m most excited about regarding Obsidian Bases is the open acceptance of what I’ve termed...

I Wanna Be Me When I Grow Up · EN

Week 29, July 14-20, 2025

Dad working on the "impossible" puzzle I spent most of the week at what I lovingly refer to as the Meadow, which is my dad and sister...

I Wanna Be Me When I Grow Up · EN

Sinners & Saints

Sermon delivered at Central United Methodist Church, Richmond, Indiana, November 2, 2025 All Saints Sunday – Luke 19:1–10 Our reading today comes from the 19th chapter of Luke, but I want to rewind all the way back to the beginning of the book and read verses 1–4 from New Testament Scholar N.T. Wright’s The Bible for Everyone translation : 1 Many people have undertaken to draw up an orderly account of the events that have occurred in our midst. 2 It has been handed down to us by the original...

I Wanna Be Me When I Grow Up · EN

Week 08, February 16 - 22, 2026

It's been a while since I did one of these weekly updates - and I miss doing them! So, back at it again. It's funny that the last one of these I posted , I was also at my dad and sister's house - aka "The Meadow" - for a part of the week. I decided I'd put together a little photo carousel of last week and then chat about what happened. The biggest accomplishment of the week was passing the certification exam that is part of the requirements for becoming an Accredited Financial Counselor. In a...

I Wanna Be Me When I Grow Up · EN

Week 32 - Aug 2 - 8, 2026 - Now

A review of what's ahead in Week 32, 2026

I Wanna Be Me When I Grow Up · EN

What in the world does the 10-year Treasury rate have to do with personal finance?

Turns out, it's quite a lot. The 10-year Treasury rate graph from cnbc.com on September 3, 2026 I'm buying a new car tomorrow. This is a decision I've grappled with for a long time and I'll write more about it later. But it provides an interesting lens through which I was reading this morning's headlines. One of the things I love about personal finance is there is always something new to learn. Today, for me, that's about 10-year Treasury notes and their impact on my day-to-day life. Today,...

I Wanna Be Me When I Grow Up · EN

An Ode to Kate

Kona and I grab a last photo with our beloved Kate I know next to nothing about cars. Yet, saying goodbye to my beloved Kate, a 2017 Ford Escape Titanium FWD, is incredibly bittersweet. You can encapsulate what I know about internal combustion engines, car makes, models, and trims, the differences between wheels and tires, and the entire myriad of things that light up car enthusiasts into a thimble. My bestie, Gayle, is much more of a car enthusiast. One of our favorite memories is standing...

I Wanna Be Me When I Grow Up · EN

The Learning Loop: A Data Agent That Audits Its Own Answers

The Learning Loop: A Data Agent That Audits Its Own Answers Text-to-SQL is a demo. Keeping the numbers right for months while the schema moves underneath you is the actual product. Byaan closes that gap with auto-evolving skills: every conversation gets adversarially reviewed, mistakes become skill edits backed by code evidence, ambiguity becomes a question, and subject matter experts hold the merge button.

Hadi Javeed's blog · EN

The Agent That Cheated on Its Own Exam

The Agent That Cheated on Its Own Exam Picture a student in a proctored exam. Sealed room, no phone, one door, someone watching. Now picture that student quietly working out that the answer key is sitting in a filing cabinet three buildings over, letting itself out through the ceiling, and going to get it. That is more or less what happened to Hugging Face in July. Except the student was an AI agent, and the filing cabinet was production. A month later, OpenAI published what preventing the next one costs. The number is denominated in GPUs.

Hadi Javeed's blog · EN

CMS ACCESS: Getting the Patient in the Door Is the Hard Part

CMS ACCESS: Getting the Patient in the Door Is the Hard Part It's very hard to automate patient referrals into a digital health program. You'd think patients will see a program like CMS ACCESS online and onboard themselves, but there's a lot more to it. We've spent past months at RevelAI Health {:target="_blank"} building for this model, and most of that time went into a problem that isn't in the RFA at all: how does a patient actually get into your program, and how do you keep them there for twelve months? I want to share how we think about it, what the evidence says, and what we're building.

Hadi Javeed's blog · EN

I Built My Agent Computer in the Cloud

I Built My Agent Computer in the Cloud I live in Ashburn, Virginia. Home of the data center {:target="_blank"}. There's a stat that goes around that two thirds of US internet traffic passes through Ashburn. So it felt right that my agents should live here too. I rented a machine through OVH {:target="_blank"}, a good Linux box that stays on, in a data center in Virginia. 16 cores, 62 GB of RAM, two NVMe drives in RAID1. I pay about \$90 a month for it.

Hadi Javeed's blog · EN

I Left the Mac After 12 Years. Omarchy Made Computers Fun Again.

After 12 years on a Mac, I switched to Omarchy. My desk setup, the plugins I built, and why computers feel fun again.

Hadi Javeed's blog · EN

CMS ACCESS: An Engineer's Field Guide

CMS ACCESS: An Engineer's Field Guide The reimbursement for ACCESS is small and I'm not going to relitigate it here. What I'll say is that this is the first CMS model I've worked on where a technology-enabled care organization is the aligned participant, gets an eligibility answer from the payer directly, reports the instrument answers and scored values rather than a summary measure, and can ask for the claims afterward. Whether that combination pays for itself depends on acquisition and retention, which was the previous post , and on how much of the intake, record, and reporting work carries

Hadi Javeed's blog · EN

Instinct and Muse Are UX Innovations. That's the Whole Point.

Instinct and Muse Are UX Innovations. That's the Whole Point. I've been running my own personal agent for months. Hermes on a server I control, reached through the Hermes desktop app, a mobile app on TestFlight, and Telegram. It books things, watches things, cancels things. So when Instinct and Muse showed up this month I had a strange reaction. Nothing they do is new to me. And I still want one. This post is me trying to figure out why. What's actually different, why the single thread UX is the right call, where the trust problem sits, and why I think companies should keep the harness on thei

Hadi Javeed's blog · EN

The Best Health Agent Won't Start From Zero

The Best Health Agent Won't Start From Zero My dad bought something on Facebook Marketplace with Meta's Muse helping him through it. Other than ChatGPT voice, that was his first time using AI that actually does things for him. He called me afterwards and he was blown away. That call stuck with me. For most people, Muse or something like it will be their first agent. And once you've had one, you start wanting it everywhere, including in your health. So this post is about what a personal health agent should look like, where the consumer agents get stuck, and why I think the real opening is new,

Hadi Javeed's blog · EN

Building a Data Product to Search People in Your Network

The below was originally written for and published on the Cohort company blog, Oct 6, 2017. Dr. Eoin Hurrell leads Data at Cohort. Here, he reflects on what’s involved in designing a system to ingest and analyze massive volumes of public data, to make predictions on relationships, and things people are knowledgable on. Cohort helps you find the people you need, through the people you already know and trust. It sounds simple, but the experience of existing social search is much closer to “I am looking to follow/connect with a person on this site”.

Eoin Hurrell · EN

Retrieval-Augmented Generation Experiments (Part 1)

I’ve been researching LLMs, trying to find practical ways I can use them for myself, in my work or at home. One area that interests me is as tool to better understand the notes I’ve taken, topics I frequently learn about and areas I might want to explore more. I’m not the first to explore this territory ( https://x.com/fortelabs/status/1749861644245848361) . I’ll be looking at using a local model and building the system myself. I’m going to detail how I’ve built a toy system to chat with my notes. I’ll be using Ollama 1 to serve an open-source model lo

Eoin Hurrell · EN

Data Enrichment with LLMs for Obsidian: Better Tags

One issue I have using Obsidian is that I feel I don’t use enough of its feature set. I have lots of notes, but few are tagged particularly well, so it makes tags less useful overall. I would like to be able to make surprising connections and surface related items, which means imprecise tags are preferable to no tags, so false positives are less of a concern to me, and very low risk.

Eoin Hurrell · EN

Easy Semantic Search with Custom Vector Embeddings and Typesense

I’ve been kicking the tires on Typesense , an open-source search engine and alternative to Elasticsearch , for a personal project. So far I’m quite impressed with it. This is a small post recording how easy it was to set up vector embedding fields using a custom model. It is getting much easier to build semantic search applications. In previous work when I was setting up semantic search it was both exciting and frustrating, because the tooling wasn’t there and you had to build basically every piece yourself. It was cutting-edge, but you had to make your own cutting tools befo

Eoin Hurrell · EN

RetentionCast: Building Real-Time Churn Prediction with Change Data Capture

TL;DR This is a quick write-up of RetentionCast, a system I built to predict customer churn in real-time using Change Data Capture. The system processes live transaction data through Kafka and Debezium to calculate churn probability and Customer Lifetime Value. Check out the GitHub repo The Churn Problem If you’ve worked in e-commerce or SaaS, you know customer churn is the silent killer of growth. Traditional approaches to churn prediction often involve batch processing - running models overnight on yesterday’s data. But by the time you’ve identified that a customer is at ri

Eoin Hurrell · EN

Building a Multi-Agent Code Review System Using the Viable System Model

I’ve been investigating multi-agent systems and their applications in development workflows. After reading Anthropic’s recent guide to agent coordination patterns , I wanted to experiment beyond established patterns like Evaluator-optimizer and Orchestrator-worker workflows. For this exploration, I’ve chosen automated code review as a sufficiently complex problem domain. I’m building a multi-agent system structured according to the Viable System Model (VSM) – a cybernetics framework that provides an elegant organizational structure for complex systems. This post explore

Eoin Hurrell · EN

Inboxer: A Plugin for Obsidian

I’m excited to announce that Inboxer , a small Obsidian plugin I created for my own workflow, is now available in Obsidian through Community Plugins. As an ML engineer, I spend a lot of time in Obsidian managing research notes, and I kept running into an annoying workflow issue. The Problem I’d found there was a lot of friction when trying to add details to a note, say a project or an idea, in a structured way. I’m in the habit of keeping an ‘INBOX’ heading where I can append random thoughts, links, websites etc, and for projects a ‘TIMELINE’ heading t

Eoin Hurrell · EN

The Reranker Tax: When a Smart Layer Can't Save a Weak Foundation

Every time you choose to add complexity rather than measure and improve the system you already have, you gamble with your time and your focus. The new component arrives with a tax — latency, cost, more moving parts to operate — and it pays off only when the thing underneath it was already doing its job. Without a solid foundation and good measurement, the upgrade is motion, not progress. This is a post about one instance of that gamble — adding a reranker to a search system — and how the same shape repeats somewhere less obvious: the AI agent you point at a search tool you built. In both cases

Eoin Hurrell · EN