AI builder, learning in public. Lessons, experiments, and a growing garden of notes on agentic engineering and beyond.https://jonroosevelt.com/https://jonroosevelt.com/blog/agent-stack-layers/https://jonroosevelt.com/blog/agent-stack-layers/I kept writing skills. New skill for code review. New skill for deployment. New skill for browser automation. Each one added a capability, and each one stayed a capability — a one-off that I had to coMon, 02 Mar 2026 00:00:00 GMThttps://jonroosevelt.com/blog/agentic-engineering-part-1-skills-that-ship-code/https://jonroosevelt.com/blog/agentic-engineering-part-1-skills-that-ship-code/Three months ago, I was letting my AI agent write code directly on the production server. No branches, no CI, no tests between "idea" and "live in production." If the agent broke something at 2 AM, thWed, 25 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/agentic-engineering-part-2-adversarial-code-review/https://jonroosevelt.com/blog/agentic-engineering-part-2-adversarial-code-review/Unit tests tell you if the code you wrote works. They don't tell you about the code you forgot to write. After shipping an alternate phone numbers feature that passed all 17 unit tests, a review agentWed, 25 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/agentic-engineering-part-3-architectural-trace/https://jonroosevelt.com/blog/agentic-engineering-part-3-architectural-trace/BugBot finds bugs in code that's already written. But what about the bugs that exist because the architecture is wrong — where the code does exactly what it says, but "what it says" is inconsistent acWed, 25 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/agentic-engineering-part-4-the-full-stack/https://jonroosevelt.com/blog/agentic-engineering-part-4-the-full-stack/Over the past three posts, I've covered the individual pieces: DevFlow for CI/CD enforcement, BugBot for adversarial review, and ArchReview for architectural tracing. But skills don't live in isolatioWed, 25 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/ai-patient-chatbot-urgent-care/https://jonroosevelt.com/blog/ai-patient-chatbot-urgent-care/When patients call or message an urgent care clinic, they're usually asking the same questions: "What are your hours?" "Do you take my insurance?" "How long is the wait right now?" These repetitive inSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/ai-urgent-care-trends/https://jonroosevelt.com/blog/ai-urgent-care-trends/Urgent care operates in a constant state of tension. Providers spend more time documenting visits than examining patients. Front desk staff juggle phone calls, check-ins, and insurance verification whSun, 25 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/architecting-modular-ai-agents/https://jonroosevelt.com/blog/architecting-modular-ai-agents/Learn how to architect AI agent systems with a modular, skill-based approach and implement real-time communication using Server-Sent Events (SSE).Sat, 05 Apr 2025 00:00:00 GMThttps://jonroosevelt.com/blog/azure-ai-evaluation-apim-integration/https://jonroosevelt.com/blog/azure-ai-evaluation-apim-integration/Learn how to implement robust evaluation for AI agents using Azure AI Evaluation SDK when working with Azure API Management (APIM), overcoming authentication and integration challenges.Wed, 02 Apr 2025 00:00:00 GMThttps://jonroosevelt.com/blog/bugbot-adversarial-loop-part-1/https://jonroosevelt.com/blog/bugbot-adversarial-loop-part-1/Every code review I've ever done was a single pass. You open the diff, read through it, maybe catch a few things, leave some comments, approve. The problem is bugs don't care about your review flow. TSat, 21 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/bugbot-angle-diversity-lessons-part-2/https://jonroosevelt.com/blog/bugbot-angle-diversity-lessons-part-2/After running BugBot across several real codebases, the result that surprised me most wasn't the bugs it found. It was which iteration found them. The same files, reviewed from a different angle in a Sat, 21 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/building-aoa-agent-lovable-n8n/https://jonroosevelt.com/blog/building-aoa-agent-lovable-n8n/I used to spend 6+ hours writing Analysis of Alternatives reports. Last week, I built an AI agent that does it in minutes - and you can too, without writing complex code.Sat, 31 May 2025 00:00:00 GMThttps://jonroosevelt.com/blog/building-on-pai/https://jonroosevelt.com/blog/building-on-pai/I'd been building my AI infrastructure for months before I found a name for it. I had a CLAUDE.md with operating modes, a folder of skills, a deploy script that pushed everything to multiple machines.Tue, 03 Mar 2026 00:00:00 GMThttps://jonroosevelt.com/blog/burden-of-being/https://jonroosevelt.com/blog/burden-of-being/When someone asks you what makes life meaningful, the reflexive answer is usually something about happiness, fulfillment, or pleasure. But Jordan Peterson argues we're asking the wrong question. The bSun, 25 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/claude-code-session-isolation-hooks/https://jonroosevelt.com/blog/claude-code-session-isolation-hooks/I run multiple Claude Code sessions in the same project all the time. One session handles a long-running task via a Ralph Wiggum loop (a self-referential iteration technique), while I open another sesMon, 16 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/claude-multi-account-load-balancer/https://jonroosevelt.com/blog/claude-multi-account-load-balancer/I hit my Claude Code rate limit three times last Tuesday. Each time, I had to stop what I was doing, log out, log into a different subscription, and pick up where I left off. The context was gone. TheThu, 23 Apr 2026 00:00:00 GMThttps://jonroosevelt.com/blog/context-files-making-agents-worse/https://jonroosevelt.com/blog/context-files-making-agents-worse/I had a 2,000-word CLAUDE.md in one of my repos. It covered architecture, directory structure, coding conventions, style rules — the works. Every time I ran Claude Code or Codex against the codebase, Thu, 26 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/defining-pii-masking-policies-with-aws-bedrock-guardrails/https://jonroosevelt.com/blog/defining-pii-masking-policies-with-aws-bedrock-guardrails/- Amazon Bedrock Guardrails are a robust feature within the Amazon Bedrock service designed to enhance the safety, compliance, and overall quality of interactions with AI models. Guardrails provide a Tue, 26 Nov 2024 00:00:00 GMThttps://jonroosevelt.com/blog/delayed-prescription-antibiotic-stewardship-urgent-care/https://jonroosevelt.com/blog/delayed-prescription-antibiotic-stewardship-urgent-care/Every urgent care provider knows the pressure. A parent brings in a child with an ear infection. The exam is ambiguous — it could be viral, could be bacterial. You know antibiotics probably won't helpSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/enterprise-rag-system/https://jonroosevelt.com/blog/enterprise-rag-system/This blog post details the technical architecture and innovations that make this system particularly effective for enterprise use cases.Thu, 06 Feb 2025 00:00:00 GMThttps://jonroosevelt.com/blog/fastapi-mcp-client/https://jonroosevelt.com/blog/fastapi-mcp-client/I've been working on a project to support SSE for MCP. Couldn't find any good example on the client in Python for supporting SSE with FastAPI MCP. So I wrote it up myself and thought I will share everMon, 14 Apr 2025 00:00:00 GMThttps://jonroosevelt.com/blog/field-level-ensemble-ocr-insurance-cards/https://jonroosevelt.com/blog/field-level-ensemble-ocr-insurance-cards/I've been running OCR on insurance cards at our urgent care clinics for a few months now. Patients hand over their card at check-in, staff snaps a photo, and our system extracts member IDs, group numbSun, 15 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/fine-tuning-microsoft-phi-2-for-sentiment-analysis/https://jonroosevelt.com/blog/fine-tuning-microsoft-phi-2-for-sentiment-analysis/Microsoft Phi-2 Fine Tuning - Learn how to adapt this powerful small language model for sentiment analysis of employee performance data using LoRA and quantization.Fri, 15 Nov 2024 00:00:00 GMThttps://jonroosevelt.com/blog/four-line-architecture-beat-complex-ai-frameworks/https://jonroosevelt.com/blog/four-line-architecture-beat-complex-ai-frameworks/Claude Code's entire architecture is fundamentally just one while loop. Not as a simplification—literally. While competitors build orchestration frameworks with task queues, agent hierarchies, and comSun, 25 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/git-driven-ai-config/https://jonroosevelt.com/blog/git-driven-ai-config/I had four machines. My AI assistant behaved differently on each one.Sun, 01 Mar 2026 00:00:00 GMThttps://jonroosevelt.com/blog/git-worktrees-broke-dedicated-machines-fixed-it/https://jonroosevelt.com/blog/git-worktrees-broke-dedicated-machines-fixed-it/I was in the middle of a refactor — removing dead code from a shared SDK module — when my edits vanished. No error. No warning. Just gone.Fri, 27 Mar 2026 00:00:00 GMThttps://jonroosevelt.com/blog/gpu-accelerated-rag/https://jonroosevelt.com/blog/gpu-accelerated-rag/Learn how to leverage GPU acceleration to significantly improve document processing speed in Retrieval-Augmented Generation (RAG) systems.Thu, 13 Mar 2025 00:00:00 GMThttps://jonroosevelt.com/blog/handling-skewed-data-in-apache-spark-performance-optimization/https://jonroosevelt.com/blog/handling-skewed-data-in-apache-spark-performance-optimization/Learn advanced techniques to tackle the performance challenges of processing skewed data distributions in Apache Spark, backed by a real-world case study with 5x performance improvement.Fri, 15 Nov 2024 00:00:00 GMThttps://jonroosevelt.com/blog/hybrid-scheduling-urgent-care/https://jonroosevelt.com/blog/hybrid-scheduling-urgent-care/The urgent care industry is undergoing a quiet revolution in how patients are seen. The traditional walk-in-only model — once the defining feature of urgent care — is giving way to hybrid scheduling sSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/implementing-gcc-paper-agent-memory/https://jonroosevelt.com/blog/implementing-gcc-paper-agent-memory/I run AI coding agents across multiple machines, multiple sessions, sometimes for days at a time. The biggest frustration isn't capability — it's amnesia. Every new session starts from zero. The agentFri, 20 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/machiavelli-strategic-principles-modern-leaders/https://jonroosevelt.com/blog/machiavelli-strategic-principles-modern-leaders/Niccolo Machiavelli has been misunderstood for 500 years. His name has become synonymous with manipulation and ruthlessness, but his actual writings contain some of the most pragmatic leadership insigSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/patient-insurance-education-app/https://jonroosevelt.com/blog/patient-insurance-education-app/I got a 4-star Google review last week that bothered me more than it should have.Sat, 22 Nov 2025 00:00:00 GMThttps://jonroosevelt.com/blog/personal-ai-infrastructure/https://jonroosevelt.com/blog/personal-ai-infrastructure/The first real sign I had a system rather than a workflow was when I noticed the assistant failing gracefully.Sun, 01 Mar 2026 00:00:00 GMThttps://jonroosevelt.com/blog/production-rag-system-phi4-lightrag/https://jonroosevelt.com/blog/production-rag-system-phi4-lightrag/After spending months helping enterprises build AI systems, I noticed a pattern: everyone wanted powerful RAG capabilities, but few were comfortable shipping their proprietary data to external APIs. TWed, 08 Oct 2025 00:00:00 GMThttps://jonroosevelt.com/blog/rag-system-cost-savings/https://jonroosevelt.com/blog/rag-system-cost-savings/In October 2025, I deployed a production RAG system that would have cost $39,600 annually using OpenAI's APIs. My actual cost? $2,300 per year. That's 94% cost savings while maintaining comparable perSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/sacrifice-abraham-peterson-genesis-meaning/https://jonroosevelt.com/blog/sacrifice-abraham-peterson-genesis-meaning/The story of Abraham waiting 100 years for a son, only to be asked to sacrifice him, seems absurd on its face. Why would ancient cultures preserve such a psychologically brutal narrative? Dr. Jordan PSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/self-hosted-insurance-card-ocr/https://jonroosevelt.com/blog/self-hosted-insurance-card-ocr/Insurance card data entry is one of the most tedious bottlenecks in patient onboarding. Commercial OCR services charge per page and require sending patient data to third-party servers. I wanted to seeThu, 12 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/semantic-kernel-research-agent/https://jonroosevelt.com/blog/semantic-kernel-research-agent/Learn how to transform an open-source AI research agent into an enterprise-ready solution using Microsoft's Semantic Kernel framework with Azure OpenAI.Thu, 20 Mar 2025 00:00:00 GMThttps://jonroosevelt.com/blog/sentiment-analysis-azure-aws-custom-models-comparison/https://jonroosevelt.com/blog/sentiment-analysis-azure-aws-custom-models-comparison/A comprehensive comparison of sentiment analysis capabilities across Azure Cognitive Text Analytics, AWS Comprehend, and custom fine-tuned models like RoBERTa and Phi2.Fri, 15 Nov 2024 00:00:00 GMThttps://jonroosevelt.com/blog/six-task-system-para-ivy-lee-productivity/https://jonroosevelt.com/blog/six-task-system-para-ivy-lee-productivity/The best productivity system is the one you'll actually use. After years of experimenting with todo apps, kanban boards, and elaborate task managers, I found something that works: a hybrid of Tiago FoSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/synology-backup-agent-kernel-6-17-patch/https://jonroosevelt.com/blog/synology-backup-agent-kernel-6-17-patch/Synology Active Backup for Business is one of the best self-hosted backup solutions out there — agent-based, centralized, bare-metal restore capable. There's just one problem: the Linux agent only offSun, 15 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/terminal-design-philosophy-rethinking-multiplexers/https://jonroosevelt.com/blog/terminal-design-philosophy-rethinking-multiplexers/If you're a developer, you probably use tmux or screen. You might even consider it essential infrastructure. But according to Kovid Goyal, creator of the Kitty terminal emulator, terminal multiplexersSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/three-levels-of-why-primal-motivation-psychology/https://jonroosevelt.com/blog/three-levels-of-why-primal-motivation-psychology/Every January, millions of people set ambitious goals. By February, 80% have abandoned them. The conventional wisdom blames willpower, discipline, or commitment. But the real problem runs deeper: mostSat, 24 Jan 2026 00:00:00 GMThttps://jonroosevelt.com/blog/two-healthcare-sites-four-hundred-points/https://jonroosevelt.com/blog/two-healthcare-sites-four-hundred-points/When I checked our mobile Lighthouse scores last month, both of our clinic websites — arcs.health and covenant.clinic — were in rough shape. Not broken, but mediocre. The kind of scores that quietly cThu, 19 Feb 2026 00:00:00 GMThttps://jonroosevelt.com/blog/universal-algorithm-ai-execution-framework/https://jonroosevelt.com/blog/universal-algorithm-ai-execution-framework/What if one algorithm could handle everything—from fixing a typo to architecting a distributed system to building an entire company? Not a vague philosophy, but a precise, verifiable framework with meSat, 24 Jan 2026 00:00:00 GMT