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: Agentic AI
Will Smarter Models Shrink the Agent Harness or Make It Matter More?
Why stronger LLMs may remove some orchestration code yet raise the stakes for permissions, evaluation and state, and how to decide which harness parts deserve investment.
7 min readChat Interface or Agent Loop? Deciding What Your AI Feature Needs
Learn how to tell a conversational chatbot from a goal-driven agent, what the agent loop adds, and how to decide which one your AI feature actually needs.
12 min readFrom Goal to Guarded Action: Loops, Verification and Permissions in AI Agents
Learn how AI agents turn a goal into tool calls through a plan-act-observe loop, and why verification, autonomy levels and permission layers decide if they are safe.
12 min readAgent = Model + Harness: Where Reliable AI Behavior Actually Comes From
Reliable AI agents come from the harness, not the LLM alone: where state, authority and verification belong, and which scaffolding fades as models improve.
16 min readDesigning Multi-Agent Systems on A2A: Nodes, Memory and Governance
A reference architecture for multi-agent systems built on the A2A protocol, covering agent modules, memory types, orchestration, security risks and a design checklist.
9 min readWhy AI Agents Burn Budget Without Finishing, and How to Stop Them
Learn why tool-calling agents keep looping when "done" is undefined, where the token spend goes, and which stop conditions beat simply raising step or budget caps.
7 min readDesigning Token-Efficient Tool Surfaces for Agentic MCP Servers
Learn how to collapse dozens of MCP tool definitions into a handful of domain-focused, action-routed tools without losing any underlying functionality.
19 min readLangGraph in Practice: State, Nodes, Edges, and Five Agent Patterns
Learn how to define LangGraph state with Annotation and reducers, wire nodes with edges, and implement all five core agentic workflow patterns in JavaScript.
10 min readDesigning Agentic AI Workspaces That Fit How Teams Actually Operate
Explains ten core principles for building agentic AI workspaces that combine context, knowledge, autonomy, tool access, and workflow automation into a unified system.
9 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.