WebMCP in React: Exposing Client-Side State and Form Actions to Browser AI Agents
Turn React 19 web applications into agent-operable surfaces using the emerging W3C WebMCP standard, declarative form attributes, and idiomatic useWebMCPTool hooks.
Technical Journal
Deep dives into Open Knowledge Format (OKF), AI Agent orchestration, MACH architecture, and developer productivity.
Filter by Tag
Zero-Latency On-Device AI in React: Chrome Gemini Nano & Prompt API in Production
Building zero-latency, privacy-first React interfaces with Chrome built-in Gemini Nano APIs, window.LanguageModel, local PII sanitization, and resilient hybrid fallbacks.
Building MCP UI: Server-Driven Interactive Widgets for AI Agents
Architecting server-driven generative UI over Model Context Protocol (MCP) using structured JSON schemas, client-side sandboxed rendering, and bidirectional action loops.
Client-Side AI Governance: Architectural Patterns for Policy Enforcement, C2PA Provenance, and DLP in Next.js
A deep dive into embedding production AI governance inside Next.js frontends, covering client-side DLP, OWASP LLM output sanitization, EU AI Act C2PA provenance signing, and audit telemetry.
Evolving Google Open Knowledge Format to v0.2: Agentic Trust & Signals
How OKF v0.2 tackles agentic trust, provenance, trust tiers, staleness, and anti-hallucination Attested Computations in AI knowledge graphs.
Building Autonomous Multi-Agent Workflows with LangGraph and Next.js
Architecting stateful multi-agent LLM graphs with custom state channels, conditional routing, human-in-the-loop approval, and streaming responses in Next.js.
Demystifying Vector Embeddings & Similarity Math for Beginners
A plain-English guide explaining how modern AI represents human meaning as spatial coordinates, how cosine similarity works, and the normalize-then-dot trick used by vector databases.
Local-First Developer Workflows: Leveraging WebGPU and WebContainers for In-Browser LLM Fine-Tuning
A deep dive into running and adapting LLMs directly in the browser sandbox. We combine StackBlitz WebContainers with WebGPU and LoRA to build a zero-cost, private AI playground.
Standardizing AI Integrations with Model Context Protocol (MCP)
A hands-on guide to building and securing custom Model Context Protocol (MCP) servers to safely connect enterprise data to AI developer agents.
Building a Resilient Multi-Provider AI Routing Layer with Vercel AI SDK
How to build a production-grade LLM routing layer with failovers, fallback models, and structured Zod outputs using Vercel AI SDK.
Implementing Google's Open Knowledge Format (OKF) in Practice
How I structured this portfolio's documentation as a navigable markdown graph using Google's OKF spec, with real validation and automation.