Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Tool Calling
Understanding 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 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 readA Hand-Rolled LangChain Tool Loop for Comparing Live Stock Metrics
Build a small LangChain stock-comparison assistant step by step and learn the create, bind, invoke and execute loop that lets an LLM request live data instead of guessing.
7 min readBuilding AI Agents on Top of Your Existing .NET Services and APIs
C# teams can expose existing .NET services as governed tools for AI agents via function calling, with the context, security and observability rules needed.
9 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 readProgressive Tool Discovery for AI Agents at Scale
Big tool catalogs make AI agents pick worse tools and burn context. Progressive discovery with manifests and just-in-time schemas fixes tool calling at scale.
10 min readUnderstanding AI Agents Through the Brain-Finger Analogy
Learn how LLMs, tools, and tool executors interact by mapping agent architecture onto a food-ordering analogy, then build a minimal agent implementation.
7 min readUnderstanding Items vs Messages in OpenAI's Responses API
Explains how OpenAI's Responses API reorganizes model outputs into items instead of messages, and why that shift matters for tool-calling and agentic workflows.
8 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.