Sitemap
Everything on the site.
91 links, kept up to date on their own as pages and posts are added.
Pages
- Home/
- About/aboutSenior Software Engineer and AI architect leading teams of AI coding agents: .NET 10, Next.js, Solr, SQL Server, Redis, k6, RAG, MCP and self-hosted LLMs.
- Connect your AI/aiThis portfolio is an MCP server. Connect Claude, Cursor or VS Code and ask your AI assistant about my experience, projects and writing.
- Bug log/bug-logBugs I have fixed: what people saw, why it happened, what changed and what it measured afterwards.
- Experience/experienceSenior Software Engineer at Revalsys Technologies: .NET R&D, multi-tenant RAG and MCP platforms, hybrid search, offline-first apps and large e-commerce builds.
- Fix a bug/fix-a-bugStuck on a bug, a slow API or an architecture question? Describe it and it becomes a triaged ticket on my phone.
- Knowledge graph/graphAn interactive map of my projects, R&D experiments, blog posts and the technologies that connect them.
- R&D Lab/labExperiments in load testing, AI code review, RAG, IoT predictive maintenance, encryption, messaging and gRPC.
- Hybrid Search Visualizer: BM25 vs Vector vs RRF/lab/hybrid-searchInteractive visualization comparing Okapi BM25 keyword search, dense vector kNN semantic search, and Reciprocal Rank Fusion (RRF) on Solr 9 and .NET.
- Projects/projectsIoT data platforms, developer tooling, video conferencing, RAG systems and e-commerce builds for Jockey, Speedo, Manyavar and more.
- System status/statusLive status of this site: Cloudflare, the Next.js front end, the .NET API and MongoDB, with response times, uptime and the last deploys.
- Topics/topicsBrowse posts by topic: software architecture, AI and RAG, DevOps and homelab, observability and performance.
- Work with me/work-with-mePerformance audits and load testing for .NET APIs, self-hosted AI assistants and agents, architecture reviews, and fixing stubborn bugs.
Case studies
- From 40 seconds to about 13: rebuilding a multi-tenant AI agent/projects/multi-tenant-ai-chatbotClients embed this RAG assistant, built on .NET 10, in their own products. It worked, but a data question took 30–40 seconds. An end-to-end audit ranked the fixes, the agent moved to Microsoft Agent Framework with MCP tools for data and docs, and most answers now arrive in about 13 seconds.
Writing
- When Vector Search Wasn't Enough: A Table of Contents per Document, Searched in Parallel/blog/rag-table-of-contents-parallel-retrieval · 18 Nov 2026
- My AI Dev Team Lives in Herdr: Claude Code as Tech Lead, Antigravity as Developers, Copilot and Codex as Reviewers/blog/herdr-ai-agent-team-claude-code-antigravity-copilot-codex · 14 Nov 2026
- Why I Call Myself an Agentic Developer: The Evidence, With Links/blog/why-i-am-an-agentic-developer · 13 Nov 2026
- One Lead, Three Agents: Building an On-Prem AI Email Assistant with Claude Code, Codex, Cursor and Antigravity/blog/building-ai-email-assistant-with-a-team-of-coding-agents · 12 Nov 2026
- Two Days, Not Two Sprints: Migrating Worker Services to .NET 10 with Skill Files and Coding Agents/blog/migrating-worker-services-to-dotnet-10-with-skills-and-coding-agents · 11 Nov 2026
- RTX 5090 vs DGX Spark for a Local AI Agent: Why Memory Bandwidth Won/blog/rtx-5090-vs-dgx-spark-local-llm-inference · 18 Oct 2026
- Memory, Reach and Habits: How I Use an Obsidian Vault, MCP and Skills to Ship Production-Grade Code/blog/ai-development-workflow-obsidian-mcp-skills · 26 Sept 2026
- Giving AI Assistants a Map of Your Codebase: An MCP Server for C# Code and SQL Server Schemas/blog/mcp-server-code-database-intelligence · 23 Sept 2026
- A Dynamic Background Service Manager in .NET 8: Start, Update and Stop Workers at Runtime/blog/dotnet-dynamic-background-service-manager · 23 Sept 2026
- How I Turned My MacBook into a Self-Hosted Vercel with Coolify, Cloudflare Tunnel & Terraform/blog/turning-my-macbook-into-a-self-hosted-paas · 23 Sept 2026
- Building a VMSS-Style Cluster from 10 Mini PCs: Why I'm Starting with Docker Swarm, Not K3s/blog/homelab-vmss-docker-swarm-vs-k3s · 24 Aug 2026
- Static Pages, Fresh Content: On-Demand ISR Between Next.js 16 and a .NET API/blog/nextjs-dotnet-on-demand-isr · 22 Aug 2026
- Hybrid Product Search on Solr 9: BM25 + Vectors + Reciprocal Rank Fusion in .NET/blog/hybrid-search-solr-bm25-vector-rrf · 14 Aug 2026
- Why Our RAG Chatbot Took 40 Seconds to Answer, and the Plan to Make It 70% Faster/blog/rag-chatbot-latency-audit · 17 Jul 2026
- Deep-Dive: .NET Core API Performance Tuning & Memory Optimization/blog/dotnet-performance-tuning-api-throughput · 20 May 2026
- Designing Repeatable Load Testing Suites with k6 and Grafana/blog/load-testing-microservices-k6-grafana · 15 Apr 2026
- Building an Advanced RAG Pipeline for Developer Knowledge Discovery/blog/building-rag-pipeline-internal-documentation · 10 Mar 2026
Topics
- Artificial Intelligence (10)
- DevOps (3)
- Software Architecture (3)
- Observability (1)
- Search & Vectors (1)
- .NET Core (8)
- LLMs (6)
- Claude Code (5)
- Performance (4)
- AI Agents (3)
- MCP (3)
- RAG (3)
- Skills (3)
- Background Services (2)
- Ollama (2)
- APIs (1)
- Async (1)
- C# (1)
- Caching (1)
- Cloudflare Tunnel (1)
- Codex (1)
- Concurrency (1)
- Coolify (1)
- Docker (1)
- Docker Swarm (1)
- Document AI (1)
- GC Optimization (1)
- GitHub Copilot (1)
- GPUs (1)
- Grafana (1)
- Herdr (1)
- Homelab (1)
- ISR (1)
- K3s (1)
- k6 (1)
- Kubernetes (1)
- LangChain (1)
- Load Testing (1)
- Migration (1)
- MongoDB (1)
- Next.js (1)
- Obsidian (1)
- ONNX (1)
- pgvector (1)
- Proxmox (1)
- Roslyn (1)
- RRF (1)
- Self-hosted AI (1)
- Self-Hosting (1)
- Semantic Kernel (1)
- Solr (1)
- SQL Server (1)
- Terraform (1)
- Vector DB (1)
- Vector Search (1)
- Webhooks (1)
Feeds and files for machines
- llms-full.txt, every post for AI assistants/llms-full.txt
- llms.txt, a summary for AI assistants/llms.txt
- RSS feed/rss.xml
- XML sitemap, for search engines/sitemap.xml