JSON Tool Calling Is Dead. Here’s What Replaces It
Last Updated on February 21, 2026 by Editorial Team
Author(s): MKWriteshere
Originally published on Towards AI.
Anthropic just made code-based tool orchestration the default path forward. Hugging Face saw this coming in December 2024.
Here’s a pattern you’ll notice if you watch the AI industry closely enough: the open-source community figures something out, publishes it quietly, and then a major lab ships it eight weeks later with a press release.
The article discusses the shift from JSON tool calling to code-based orchestration in AI, prominently featuring Anthropic’s implementation of programmatic tool calling, which enables models to execute tools using Python code directly. This new approach addresses inefficiencies in traditional JSON tool calling by reducing token usage and enhancing the model’s ability to compose and manage tool interactions smoothly.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic 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 out there.
→ 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 for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
