AI Agent2026-05-17
Function Calling
Also known as: Function Calling / 関数呼び出し / ファンクションコーリング
OpenAI's term for LLM-to-function invocation — equivalent to Tool Use. Model emits a JSON call from a schema; host executes it.
Overview
Introduced by OpenAI in 2023, Function Calling is now universal across major LLMs. Developers describe functions via name, description, and JSON Schema; the model decides when to call.
MCP and Agent SDKs abstract Function Calling to standardise tool management across hosts and runtimes.
Related Columns
Software Development
Claude Code MCP Integration Guide — Accelerate Development with External Tool Integration
Model Context Protocol (MCP) is an open standard connecting Claude Code with external tools and data sources. Practical guide covering GitHub, Slack, Notion, AWS, GCP integration, custom MCP server creation, Hooks integration, and enterprise best practices for Tokyo development teams.
AI
NousResearch Hermes Complete Guide — Hermes 4.3 36B, Function Calling & Hermes Agent [2026]
Complete guide to NousResearch Hermes 4.3 36B (512K context) and the Hermes Agent framework. Covers Function Calling implementation, Ollama setup, hardware requirements, and benchmarks including RefusalBench dominance — updated for 2026.
Software Development
Claude Code Agent SDK — Custom AI Agent Development Guide | Python Implementation and Multi-Agent Architecture
Complete guide to custom AI agent development using Claude Code Agent SDK. Covers Python implementation, custom tool definition, Hook implementation, sub-agent utilization, multi-agent orchestration, and CI/CD integration patterns for enterprise applications.
Feel free to contact us
Contact Us