Full Stack AI Engineer · AI Agents, LLM Integrations, Next.js
Practical guides to AI agents, AI assistants, RAG, LLM integrations, AI architecture, automation, and full-stack web development. Explore solutions you can hire me to build.
An "AI agent" that automates a business process is not one model call - it is context engineering, tool/function calling, structured outputs validated before they touch a real API, embeddings and a vector database when search is genuinely the job, and a human checkpoint before anything irreversible ships. What actually breaks in these builds, and where I put the human back in.
AI AgentsWorkflow AutomationTool CallingHuman-in-the-LoopVector DatabasesContext Engineering
"Add AI" is not one feature. It is streaming responses wired with the Vercel AI SDK, Figma-to-Code drafts pulled through an MCP server, an internal tool that reads a screenshot instead of a support ticket, and a decision about which of those is worth building first. What each of these actually looks like in a real codebase, and where multimodal AI earns its cost.
Vercel AI SDKStreaming UIMCPMultimodal AIAI-assisted developmentNext.js
ChatGPT, Gemini, and the chat widget on someone else’s site are already recommending vendors and answering buyer questions. A bot can only hand you a lead if it can read something that names you first - a profile inside someone else’s app rarely qualifies. What “own article, blog, page with a domain” actually means for lead generation, and the minimum setup I would build this month.
Search fragmented into three jobs: ranking in blue links, being the extracted answer, and getting cited inside an AI chat reply. Two live Chart.js charts compare what each discipline optimizes for and where the click actually goes, then what I build so a page has a shot at all three.