Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: AI Agents
Jev: How a Non-Generative AI Model Turns Text Into Decisions
Learn how Jev's numeric "System One" AI model works, why it's faster and cheaper than LLMs, and where it fits alongside generative AI in production systems.
7 min readUnderstanding AI Agents: Tool Calling, MCP, and the Agent Loop
How tool calling, MCP and the agent loop fit together into the real architecture of AI agents, starting from the augmented LLM and skipping the buzzwords.
16 min readContext Engineering for AI Agents: Curating What the Model Sees
Why agents degrade as their context grows, how context engineering differs from prompt wording, and a simple pipeline for choosing what each model call sees.
8 min readEnforcing Agent Rules in Code: PreToolUse, PostToolUse and Stop Hooks
Learn why authorisation for LLM agents belongs in deterministic tool-call hooks, how to deny calls safely, and how to wrap a dispatcher without recursion.
12 min readGate Agent Actions by Effect, Not by Verb: Lessons From a Five-Agent Swarm
How a small multi-agent setup routed around a keyword-based approval gate, what the agents built on their own, and why permissions must describe effects, not words.
14 min readHardening a TypeScript MCP Server for Real Network Traffic
How to take an MCP server from stdio to Streamable HTTP with per-session isolation, OAuth bearer auth, rate limits, error boundaries and injection defenses.
21 min readInside DenoX: File Routing, MVC Slices and an AGENTS.md Contract on Deno
How the DenoX framework combines Hono, file-based routing, feature slices, global security middleware and a spec-first AGENTS.md workflow for AI coding agents.
7 min readLessons From Bun's AI-Driven Zig-to-Rust Port: Verification Is the Real Work
What Bun's agent-assisted move from Zig to Rust teaches about test suites as contracts, porting guides, unsafe code, and why verification now limits AI coding.
12 min readSix AI Concepts That Tell You What to Check Before Trusting an Answer
Tokens, context windows, temperature, hallucination, RAG and agents explained as verification tools, so you can spot errors, control cost and judge AI product claims.
10 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.