Last updated on February 21, 2026 by Editorial Team
Author(s): MK write here
Originally published on Towards AI.
Anthropic has just made code-based tool orchestration the default path forward. Hugging Face sees it arriving in December 2024.
If you look closely at the AI industry there’s a pattern you’ll notice: The open-source community figures something out, quietly publishes it, and then a major lab ships it out with a press release eight weeks later.
The article discusses the shift from JSON tool calling to code-based orchestration in AI, highlighting Anthropic’s implementation of programmatic tool calling, which enables models to execute tools directly using Python code. This new approach addresses inefficiencies in traditional JSON tool calling by reducing token usage and enhancing the model’s ability to smoothly create and manage tool interactions.
Read the entire blog for free on Medium.
Published via Towards AI
We build enterprise-grade AI. We will also teach you how to master it.
15 Engineers. 100,000+ students. The AI Academy side teaches what actually avoids production.
Get started for free – no commitments:
→ 6-Day Agent AI Engineering Email Guide – One Practical Lesson Per Day
→ Agents Architecture Cheatsheet – 3 Years of Architecture Decisions in 6 Pages
Our courses:
→ AI Engineering Certification – 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course.
→ Agent Engineering Course – Hands-on with production agent architectures, memory, routing, and eval frameworks – built from real enterprise engagements.
→ AI for Work – Understand, evaluate, and apply AI to complex work tasks.
Comment: The content of the article represents the views of the contributing authors and not those of AI.
