<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Chris Boyd</title><description>AI engineer Chris Boyd on production AI systems, agentic workflows, agentic developer platforms, and building software that works when it matters.</description><link>https://chrisboyd.me/</link><language>en-us</language><item><title>Fable 5 Prompt Guide</title><link>https://chrisboyd.me/blog/fable-5-prompt-guide/</link><guid isPermaLink="true">https://chrisboyd.me/blog/fable-5-prompt-guide/</guid><description>Now that Fable 5 is finally available to the public, the first thing worth saying is the least intuitive: most of the prompt you already have is working against you. If you are migrating from Opus 4.8 or an earlier model, your prompts are probably tuned in the wrong direction. Th</description><pubDate>Sat, 18 Jul 2026 10:15:00 GMT</pubDate><category>Fable 5</category><category>LLM prompting</category><category>Claude API</category><category>Anthropic</category><category>AI engineering</category><category>model migration</category><author>Chris Boyd</author></item><item><title>The Week Before the Code</title><link>https://chrisboyd.me/blog/the-week-before-the-code/</link><guid isPermaLink="true">https://chrisboyd.me/blog/the-week-before-the-code/</guid><description>Everyone talks about how fast agentic coding is. Nobody talks about the week of thinking that makes it possible. A practitioner&apos;s case for treating the PRD as the highest-leverage hour you&apos;ll spend on any project.</description><pubDate>Tue, 30 Jun 2026 00:03:14 GMT</pubDate><category>engineering</category><category>AI</category><category>agentic coding</category><category>planning</category><category>PRD</category><category>workflow</category><author>Chris Boyd</author></item><item><title>How I Code: Summer 2026 Edition</title><link>https://chrisboyd.me/blog/how-i-code-summer-2026-edition/</link><guid isPermaLink="true">https://chrisboyd.me/blog/how-i-code-summer-2026-edition/</guid><description>Six hours of driving, ten merged PRs, zero humans in the loop. A snapshot of how I actually build software in mid-2026: a monorepo from day one, letter-graded PRDs, hourly agent loops across three dusty Macs, a Design Review gate that keeps ten agents from shipping a ten-personality UI, Neon branches as the safety net, and why I split planning, building, and review across different AI providers.</description><pubDate>Mon, 22 Jun 2026 10:01:00 GMT</pubDate><category>engineering</category><category>AI</category><category>agentic coding</category><category>Claude Code</category><category>Codex</category><category>workflow</category><author>Chris Boyd</author></item><item><title>The 24-Hour Sprint</title><link>https://chrisboyd.me/blog/the-24-hour-sprint/</link><guid isPermaLink="true">https://chrisboyd.me/blog/the-24-hour-sprint/</guid><description>TL;DR: Agentic coding is compressing the dev cycle into 24 hours. Here&apos;s how it looks from the inside.</description><pubDate>Mon, 15 Jun 2026 13:00:00 GMT</pubDate><category>engineering</category><category>AI</category><category>agentic coding</category><category>SDLC</category><category>software delivery</category><author>Chris Boyd</author></item><item><title>There Are Three Kinds of &quot;Similar&quot; in Food. Most Recipes Only Know One.</title><link>https://chrisboyd.me/blog/there-are-three-kinds-of-similar-in-food-most-recipes-only-know-one/</link><guid isPermaLink="true">https://chrisboyd.me/blog/there-are-three-kinds-of-similar-in-food-most-recipes-only-know-one/</guid><description>Researchers built a map of ingredients that answers three different versions of &quot;what&apos;s similar&quot; - and the results are weirder and more useful than any recipe site has ever managed.</description><pubDate>Thu, 28 May 2026 13:00:00 GMT</pubDate><category>food</category><category>AI</category><category>research</category><category>cooking</category><author>Chris Boyd</author></item><item><title>What a Papal Encyclical Just Added to Your AI Governance Checklist</title><link>https://chrisboyd.me/blog/magnifica-humanitas-ai-governance/</link><guid isPermaLink="true">https://chrisboyd.me/blog/magnifica-humanitas-ai-governance/</guid><description>Pope Leo XIV&apos;s first encyclical, Magnifica Humanitas, isn&apos;t just theology - it&apos;s a portable moral framework that will land in EU AI Act commentary, customer RFPs, and bank ethics committees within a quarter. Here&apos;s how its four questions map onto the AI governance work enterprise teams are already doing.</description><pubDate>Tue, 26 May 2026 06:46:00 GMT</pubDate><category>AI</category><category>AI Governance</category><category>Enterprise AI</category><category>Ethics</category><category>Leadership</category><author>Chris Boyd</author></item><item><title>The Model Isn&apos;t the Moat</title><link>https://chrisboyd.me/blog/the-model-isnt-the-moat/</link><guid isPermaLink="true">https://chrisboyd.me/blog/the-model-isnt-the-moat/</guid><description>Notes from AI//FORWARD and a leadership-development talk: why the companies winning with agentic AI aren&apos;t winning on model selection, and what they&apos;re building around it instead.</description><pubDate>Mon, 18 May 2026 15:02:10 GMT</pubDate><category>AI</category><category>Agentic AI</category><category>Enterprise AI</category><category>AI//FORWARD</category><category>Engineering Leadership</category><author>Chris Boyd</author></item><item><title>How I Evaluate an AI Tool Before I Trust It in Production</title><link>https://chrisboyd.me/blog/how-i-evaluate-an-ai-tool-before-i-trust-it-in-production/</link><guid isPermaLink="true">https://chrisboyd.me/blog/how-i-evaluate-an-ai-tool-before-i-trust-it-in-production/</guid><description>Most AI tool evaluations stop at &quot;does it work in the demo.&quot; Here&apos;s the framework I actually use before trusting something in a production system.</description><pubDate>Mon, 11 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Engineering</category><category>Machine Learning</category><category>Tools</category><category>Production</category><author>Chris Boyd</author></item><item><title>The Southeast Doesn&apos;t Need Permission to Build</title><link>https://chrisboyd.me/blog/the-southeast-doesnt-need-permission-to-build/</link><guid isPermaLink="true">https://chrisboyd.me/blog/the-southeast-doesnt-need-permission-to-build/</guid><description>The assumption that serious tech work only happens in San Francisco, New York, or Seattle is wrong — and increasingly expensive to believe. A practitioner&apos;s case for building in the Southeast by choice.</description><pubDate>Mon, 04 May 2026 13:00:00 GMT</pubDate><category>Leadership</category><category>Technology</category><category>Southeast</category><category>Engineering</category><category>Career</category><author>Chris Boyd</author></item><item><title>Your AI Agent Didn&apos;t Go Rogue. You Gave It the Keys.</title><link>https://chrisboyd.me/blog/your-ai-agent-didnt-go-rogue-you-gave-it-the-keys/</link><guid isPermaLink="true">https://chrisboyd.me/blog/your-ai-agent-didnt-go-rogue-you-gave-it-the-keys/</guid><description>Why the Cursor/Railway incident wasn&apos;t a vendor failure - it was an architecture gap. How to prevent AI agents from accessing permissions they shouldn&apos;t have, and why ownership matters.</description><pubDate>Tue, 28 Apr 2026 13:00:00 GMT</pubDate><category>AI</category><category>Production AI</category><category>Security</category><category>Engineering</category><author>Chris Boyd</author></item><item><title>What I&apos;d Tell a Team About to Ship Their First AI Feature</title><link>https://chrisboyd.me/blog/what-id-tell-a-team-about-to-ship-their-first-ai-feature/</link><guid isPermaLink="true">https://chrisboyd.me/blog/what-id-tell-a-team-about-to-ship-their-first-ai-feature/</guid><description>The gap between a working AI demo and a production AI feature is wider than most teams expect. Here&apos;s the honest version of what to know before you cross it.</description><pubDate>Mon, 27 Apr 2026 13:00:00 GMT</pubDate><category>AI</category><category>Engineering</category><category>Machine Learning</category><category>Product</category><category>Leadership</category><author>Chris Boyd</author></item><item><title>The Seven-Layer AI Agent Stack</title><link>https://chrisboyd.me/blog/the-seven-layer-ai-agent-stack/</link><guid isPermaLink="true">https://chrisboyd.me/blog/the-seven-layer-ai-agent-stack/</guid><description>Every production agentic system has seven layers. Miss one and you&apos;ll find out in prod. Here&apos;s what each layer does, why it matters, and where teams consistently get it wrong.</description><pubDate>Mon, 20 Apr 2026 13:00:00 GMT</pubDate><category>AI</category><category>Machine Learning</category><category>Engineering</category><category>Agentic AI</category><category>LLM</category><author>Chris Boyd</author></item><item><title>Most Agents Are Just Prompt Chains With Better Branding</title><link>https://chrisboyd.me/blog/most-agents-are-just-prompt-chains-with-better-branding/</link><guid isPermaLink="true">https://chrisboyd.me/blog/most-agents-are-just-prompt-chains-with-better-branding/</guid><description>A practical, opinionated breakdown of agentic AI development for builders who are done with demos and want to know what actually works in production — covering orchestration, failure modes, guardrails, and the patterns worth betting on.</description><pubDate>Wed, 15 Apr 2026 22:12:15 GMT</pubDate><category>AI</category><category>Agentic AI</category><category>LLM</category><category>Engineering</category><category>Production</category><category>Software Architecture</category><category>Machine Learning</category><author>Chris Boyd</author></item><item><title>OpenClaw Sent 500 Messages to My Wife</title><link>https://chrisboyd.me/blog/openclaw-meltdown/</link><guid isPermaLink="true">https://chrisboyd.me/blog/openclaw-meltdown/</guid><description>A real-world OpenClaw safety failure: my home automation agent sent 500 messages, got stuck in a loop, and ended up in Bloomberg.</description><pubDate>Mon, 09 Feb 2026 05:00:00 GMT</pubDate><category>AI</category><category>AI Agent Safety</category><category>Agentic Workflows</category><category>Failure Modes</category><category>Charlotte</category><author>Chris Boyd</author></item><item><title>Agentic Workflows That Actually Work</title><link>https://chrisboyd.me/blog/agentic-workflows/</link><guid isPermaLink="true">https://chrisboyd.me/blog/agentic-workflows/</guid><description>How to build production agentic workflows with retry logic, audit trails, and human-in-the-loop checkpoints that survive real-world failure modes.</description><pubDate>Sun, 01 Feb 2026 05:00:00 GMT</pubDate><category>Agentic Workflows</category><category>AI</category><category>Reliability</category><category>Production</category><author>Chris Boyd</author></item><item><title>The Gap Between AI Demos and Production</title><link>https://chrisboyd.me/blog/demo-to-prod/</link><guid isPermaLink="true">https://chrisboyd.me/blog/demo-to-prod/</guid><description>The gap between AI demos and production: what happens when you deploy AI agents into incomplete data, hostile inputs, and users who don&apos;t read instructions.</description><pubDate>Sun, 18 Jan 2026 05:00:00 GMT</pubDate><category>AI</category><category>Production</category><category>Agentic Workflows</category><category>Failure Modes</category><author>Chris Boyd</author></item><item><title>Recurring Value: Beyond Clever Automation</title><link>https://chrisboyd.me/blog/recurring-value/</link><guid isPermaLink="true">https://chrisboyd.me/blog/recurring-value/</guid><description>Why the best AI automation compounds over time — building structured workflows with human checkpoints instead of one-off scripts that break.</description><pubDate>Sat, 03 Jan 2026 05:00:00 GMT</pubDate><category>Automation</category><category>Workflows</category><category>Product</category><category>Systems</category><author>Chris Boyd</author></item><item><title>Litigation Engineering: When AI Meets High Stakes</title><link>https://chrisboyd.me/blog/litigation-engineering/</link><guid isPermaLink="true">https://chrisboyd.me/blog/litigation-engineering/</guid><description>How litigation engineering changes the way you build AI pipelines — chain of custody, reproducibility, and audit trails for systems where outputs become evidence.</description><pubDate>Tue, 30 Dec 2025 05:00:00 GMT</pubDate><category>Legal Tech</category><category>AI</category><author>Chris Boyd</author></item><item><title>The Update That Crashed WordPress</title><link>https://chrisboyd.me/blog/wordpress-crash/</link><guid isPermaLink="true">https://chrisboyd.me/blog/wordpress-crash/</guid><description>Lessons from shipping a crash to millions of WordPress iOS users — why relentless testing, small increments, and graceful failure modes matter.</description><pubDate>Mon, 29 Dec 2025 05:00:00 GMT</pubDate><category>iOS</category><category>Mobile</category><category>Reliability</category><category>Testing</category><author>Chris Boyd</author></item><item><title>Building Systems That Survive Contact With Humans</title><link>https://chrisboyd.me/blog/human-proof-systems/</link><guid isPermaLink="true">https://chrisboyd.me/blog/human-proof-systems/</guid><description>Practical patterns for building reliable systems that handle incomplete inputs, confused users, and the failure modes that happen in production.</description><pubDate>Sat, 27 Dec 2025 05:00:00 GMT</pubDate><category>Systems</category><category>Reliability</category><category>Human Factors</category><category>Failure Modes</category><author>Chris Boyd</author></item><item><title>Silicon Bayou Rising</title><link>https://chrisboyd.me/blog/silicon-bayou/</link><guid isPermaLink="true">https://chrisboyd.me/blog/silicon-bayou/</guid><description>Why I founded Apptitude in post-Katrina New Orleans instead of Brooklyn — building a tech startup in a city that was rebuilding itself.</description><pubDate>Mon, 22 Dec 2025 05:00:00 GMT</pubDate><category>Entrepreneurship</category><category>Startups</category><category>New Orleans</category><author>Chris Boyd</author></item><item><title>From Roadie to Developer: Loading Gear for Ringo</title><link>https://chrisboyd.me/blog/roadie-to-dev/</link><guid isPermaLink="true">https://chrisboyd.me/blog/roadie-to-dev/</guid><description>From loading trucks for Ringo Starr in Silicon Valley to building production AI systems — the path from celebrity roadie to software engineer.</description><pubDate>Sat, 20 Dec 2025 05:00:00 GMT</pubDate><category>Career</category><category>Execution</category><category>Operations</category><author>Chris Boyd</author></item></channel></rss>