AI engineer Chris Boyd on production AI systems, agentic workflows, litigation engineering, and building software that works when it matters.https://chrisboyd.me/en-ushttps://chrisboyd.me/blog/how-i-evaluate-an-ai-tool-before-i-trust-it-in-production/https://chrisboyd.me/blog/how-i-evaluate-an-ai-tool-before-i-trust-it-in-production/Most AI tool evaluations stop at "does it work in the demo." Here's the framework I actually use before trusting something in a production system.Mon, 11 May 2026 13:00:00 GMTAIEngineeringMachine LearningToolsProductionChris Boydhttps://chrisboyd.me/blog/the-southeast-doesnt-need-permission-to-build/https://chrisboyd.me/blog/the-southeast-doesnt-need-permission-to-build/The assumption that serious tech work only happens in San Francisco, New York, or Seattle is wrong — and increasingly expensive to believe. A practitioner's case for building in the Southeast by choice.Mon, 04 May 2026 13:00:00 GMTLeadershipTechnologySoutheastEngineeringCareerChris Boydhttps://chrisboyd.me/blog/your-ai-agent-didnt-go-rogue-you-gave-it-the-keys/https://chrisboyd.me/blog/your-ai-agent-didnt-go-rogue-you-gave-it-the-keys/Why the Cursor/Railway incident wasn't a vendor failure - it was an architecture gap. How to prevent AI agents from accessing permissions they shouldn't have, and why ownership matters.Tue, 28 Apr 2026 13:00:00 GMTAIProduction AISecurityEngineeringChris Boydhttps://chrisboyd.me/blog/what-id-tell-a-team-about-to-ship-their-first-ai-feature/https://chrisboyd.me/blog/what-id-tell-a-team-about-to-ship-their-first-ai-feature/The gap between a working AI demo and a production AI feature is wider than most teams expect. Here's the honest version of what to know before you cross it.Mon, 27 Apr 2026 13:00:00 GMTAIEngineeringMachine LearningProductLeadershipChris Boydhttps://chrisboyd.me/blog/the-seven-layer-ai-agent-stack/https://chrisboyd.me/blog/the-seven-layer-ai-agent-stack/Every production agentic system has seven layers. Miss one and you'll find out in prod. Here's what each layer does, why it matters, and where teams consistently get it wrong.Mon, 20 Apr 2026 13:00:00 GMTAIMachine LearningEngineeringAgentic AILLMChris Boydhttps://chrisboyd.me/blog/most-agents-are-just-prompt-chains-with-better-branding/https://chrisboyd.me/blog/most-agents-are-just-prompt-chains-with-better-branding/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.Wed, 15 Apr 2026 22:12:15 GMTAIAgentic AILLMEngineeringProductionSoftware ArchitectureMachine LearningChris Boydhttps://chrisboyd.me/blog/openclaw-meltdown/https://chrisboyd.me/blog/openclaw-meltdown/A real-world OpenClaw safety failure: my home automation agent sent 500 messages, got stuck in a loop, and ended up in Bloomberg.Mon, 09 Feb 2026 05:00:00 GMTAIAI Agent SafetyAgentic WorkflowsFailure ModesCharlotteChris Boydhttps://chrisboyd.me/blog/agentic-workflows/https://chrisboyd.me/blog/agentic-workflows/How to build production agentic workflows with retry logic, audit trails, and human-in-the-loop checkpoints that survive real-world failure modes.Sun, 01 Feb 2026 05:00:00 GMTAgentic WorkflowsAIReliabilityProductionChris Boydhttps://chrisboyd.me/blog/demo-to-prod/https://chrisboyd.me/blog/demo-to-prod/The gap between AI demos and production: what happens when you deploy AI agents into incomplete data, hostile inputs, and users who don't read instructions.Sun, 18 Jan 2026 05:00:00 GMTAIProductionAgentic WorkflowsFailure ModesChris Boydhttps://chrisboyd.me/blog/recurring-value/https://chrisboyd.me/blog/recurring-value/Why the best AI automation compounds over time — building structured workflows with human checkpoints instead of one-off scripts that break.Sat, 03 Jan 2026 05:00:00 GMTAutomationWorkflowsProductSystemsChris Boydhttps://chrisboyd.me/blog/litigation-engineering/https://chrisboyd.me/blog/litigation-engineering/How litigation engineering changes the way you build AI pipelines — chain of custody, reproducibility, and audit trails for systems where outputs become evidence.Tue, 30 Dec 2025 05:00:00 GMTLitigation EngineeringLegal TechAIChris Boydhttps://chrisboyd.me/blog/wordpress-crash/https://chrisboyd.me/blog/wordpress-crash/Lessons from shipping a crash to millions of WordPress iOS users — why relentless testing, small increments, and graceful failure modes matter.Mon, 29 Dec 2025 05:00:00 GMTiOSMobileReliabilityTestingChris Boydhttps://chrisboyd.me/blog/human-proof-systems/https://chrisboyd.me/blog/human-proof-systems/Practical patterns for building reliable systems that handle incomplete inputs, confused users, and the failure modes that happen in production.Sat, 27 Dec 2025 05:00:00 GMTSystemsReliabilityHuman FactorsFailure ModesChris Boydhttps://chrisboyd.me/blog/silicon-bayou/https://chrisboyd.me/blog/silicon-bayou/Why I founded Apptitude in post-Katrina New Orleans instead of Brooklyn — building a tech startup in a city that was rebuilding itself.Mon, 22 Dec 2025 05:00:00 GMTEntrepreneurshipStartupsNew OrleansChris Boydhttps://chrisboyd.me/blog/roadie-to-dev/https://chrisboyd.me/blog/roadie-to-dev/From loading trucks for Ringo Starr in Silicon Valley to building production AI systems — the path from celebrity roadie to software engineer.Sat, 20 Dec 2025 05:00:00 GMTCareerExecutionOperationsChris Boyd