<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>PaulBrower.Codes</title>
    <link>https://paulbrower.codes/</link>
    <description>Recent content on PaulBrower.Codes</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 20 Jul 2026 09:00:00 -0700</lastBuildDate>
    
	<atom:link href="https://paulbrower.codes/index.xml" rel="self" type="application/rss+xml" />
    
    
    <item>
      <title>On The Crypto Podcast</title>
      <link>https://paulbrower.codes/posts/on-the-crypto-podcast/</link>
      <pubDate>Mon, 20 Jul 2026 09:00:00 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/on-the-crypto-podcast/</guid>
      <description>I enjoyed sitting down with Roy Coughlan on The Crypto Podcast to talk about Casa, Bitcoin self-custody, multisig security, and the ways AI is changing the threat model for people protecting their wealth. You can listen or watch the episode through the player below, or open it directly on Apple Podcasts.
 </description>
    </item>
    
    <item>
      <title>A ladder for coding agents</title>
      <link>https://paulbrower.codes/posts/a-ladder-for-coding-agents/</link>
      <pubDate>Sat, 18 Jul 2026 09:00:00 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/a-ladder-for-coding-agents/</guid>
      <description>Most AI coding setups choose a model before the task produces any evidence.
A router takes a prompt and selects a model. For a straightforward task, it can choose something cheap. For a difficult task, it can send the work to an expensive model. That is better than sending every task to the same expensive model.
The choice still happens too soon. A task that looks routine can need a careful repair.</description>
    </item>
    
    <item>
      <title>Agentic Engineering, Part 3: Team Adoption, Leverage, and the New Engineering Bar</title>
      <link>https://paulbrower.codes/posts/team-adoption-leverage-and-the-new-engineering-bar/</link>
      <pubDate>Wed, 17 Jun 2026 09:00:00 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/team-adoption-leverage-and-the-new-engineering-bar/</guid>
      <description>This is Part 3 of a three-part series on building an AI development harness. Part 1 covered the harness as a concept. Part 2 covered feedback loops, hooks, and verification.
Part 1 was about one engineer and one harness. Part 2 was about making that harness produce evidence instead of asking for trust. This post is about the team. The moment more than one person depends on the harness, it stops being a personal productivity trick and turns into shared infrastructure, which changes who maintains it and how much the work of improving it is worth.</description>
    </item>
    
    <item>
      <title>Agentic Engineering, Part 2: Feedback Loops, Hooks, and Verification</title>
      <link>https://paulbrower.codes/posts/feedback-loops-hooks-and-verification/</link>
      <pubDate>Thu, 04 Jun 2026 09:00:00 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/feedback-loops-hooks-and-verification/</guid>
      <description>This is Part 2 of a three-part series on building an AI development harness. Part 1 covered the harness as a concept. Part 3 will cover team adoption and the new engineering bar.
In Part 1, I argued that the system around the agent matters more than the agent itself. This post is about the part of that system that does the most work: the feedback loops. Without them, the agent is writing code in a vacuum.</description>
    </item>
    
    <item>
      <title>Agentic Engineering, Part 1: Building your AI harness</title>
      <link>https://paulbrower.codes/posts/agentic-engineering-part-1-building-your-ai-harness/</link>
      <pubDate>Fri, 22 May 2026 09:00:00 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/agentic-engineering-part-1-building-your-ai-harness/</guid>
      <description>This is Part 1 of a three-part series on building an AI development harness. Part 2 covers feedback loops, hooks, and verification. Part 3 covers team adoption and the new engineering bar.
For the last year or so, most of the AI development conversation I&amp;rsquo;ve heard has been about models and coding assistants. Which model is smartest. Which IDE has the best autocomplete. Which prompt got the best result. That focus is too narrow.</description>
    </item>
    
    <item>
      <title>About</title>
      <link>https://paulbrower.codes/about/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://paulbrower.codes/about/</guid>
      <description>I&amp;rsquo;m Paul — an engineering leader and hands-on architect based in Boulder, CO, with 18+ years building secure mobile, backend, and crypto systems.
Today I&amp;rsquo;m Director of Engineering at Casa, leading a 12-person team and driving AI-first development workflows across engineering and product. Before that I spent six years there as a Staff Engineer, architecting Android key-management systems and on-chain Ethereum multi-signature designs for Casa&amp;rsquo;s non-custodial Bitcoin and Ethereum security products.</description>
    </item>
    
    <item>
      <title>Setting Bear Traps in the Dark Forest</title>
      <link>https://paulbrower.codes/posts/bear-traps-in-the-dark-forest/</link>
      <pubDate>Wed, 25 Jan 2023 00:00:00 +0000</pubDate>
      
      <guid>https://paulbrower.codes/posts/bear-traps-in-the-dark-forest/</guid>
      <description>Some background: Transactions to insecure contracts on the Ethereum blockchain can be front run by attentive parties via bots in order to steal funds. See https://www.paradigm.xyz/2020/08/ethereum-is-a-dark-forest for the canonical example. These bots are the monsters in the &amp;ldquo;Dark Forest&amp;rdquo;. This blog post details my attempt to subvert and co-opt these bots in attempt to get them to send me money, to &amp;ldquo;set bear traps in the Dark Forest&amp;rdquo;. We cannot introspect a front-running bots internal code, but we can manipulate and invoke it to see how it interacts with smart contracts we write to infer some of its behavior.</description>
    </item>
    
    <item>
      <title>Engineering Problems - Understanding Blockchain Technology</title>
      <link>https://paulbrower.codes/posts/engineering-problems/</link>
      <pubDate>Thu, 01 Dec 2022 16:18:19 -0700</pubDate>
      
      <guid>https://paulbrower.codes/posts/engineering-problems/</guid>
      <description>You needn’t look far to see the hate for blockchain technology. I run into it quite often in a place I used to love, Hacker News. I have had a hard time with this over the years. I often go there as a fellow skeptic to see smart people poke holes in the fluff of the goings-on of the world around us. It’s fun in the way a skeptic likes fun, at the expense of the hopeful.</description>
    </item>
    
    <item>
      <title>Celo Hackathon Project - Hello Celo</title>
      <link>https://paulbrower.codes/posts/hello-celo-hackathon/</link>
      <pubDate>Sun, 05 Dec 2021 01:00:00 +0000</pubDate>
      
      <guid>https://paulbrower.codes/posts/hello-celo-hackathon/</guid>
      <description>Hello Celo is a POC permissionless, uncensorable micro-blogging platform. It was an entry in the 2021 Celo Blockchain Hackathon. Some features:
 Standard micro-blogging features  create profile post updates with pictures follow people  uncensorable ( the location of content is posted to the blockchain and actual content is posted to IPFS ) easy onboarding ( uses meta-transactions in order to allow users with no balance to interact with the smart contract )  See the video below for the presentiation video:</description>
    </item>
    
    <item>
      <title>Ethereum File Hub</title>
      <link>https://paulbrower.codes/posts/ethereum-payment-channel/</link>
      <pubDate>Sat, 25 Aug 2018 14:56:47 -0600</pubDate>
      
      <guid>https://paulbrower.codes/posts/ethereum-payment-channel/</guid>
      <description>Ethereum File Hub is a Proof-of-Concept implementation of a payment channel used to purchase digital files between two parties who do not trust each other and does not require a third party. It was an entry in the EthDenver 2018 hackathon. You can read this blog post or watch pretty much the same content via the video:  
Background Currently, if you want to buy or sell some digital content on the internet you have to involve quite a few other parties.</description>
    </item>
    
    <item>
      <title>Permissionless Blockchain Programming</title>
      <link>https://paulbrower.codes/posts/permissionless-blockchain-programming/</link>
      <pubDate>Fri, 27 Jul 2018 14:56:47 -0600</pubDate>
      
      <guid>https://paulbrower.codes/posts/permissionless-blockchain-programming/</guid>
      <description>Leverage the blockchain so your app needs neither permission nor forgiveness. This is my quick adventure into using NodeJS and the Ethereum blockchain to write an unstoppable app. TLDR; I built an app that takes the Gitcoin Bounties and creates an RSS Feed using NodeJS, Web3JS, AWS S3, and AWS Lambda
Anyone who has deployed an app to the Google Play Store or the Apple App Store or built something using the Twitter API or anything that requires permission to do can tell you that the rug can be pulled out from under you at any moment.</description>
    </item>
    
  </channel>
</rss>