Uploaded February 2026 | Updated November 2026, 18 hours ago
Anthropic's latest Sonnet 4.6 release quietly introduced programmatic tool calling; a feature that lets AI agents write code instead of JSON to invoke tools, slashing token usage by up to 98% while improving accuracy. I break down why this "code mode" approach outperforms traditional tool calling, how companies like Cloudflare and Anthropic are already implementing it, and why this could become the new industry standard just like MCP did. If you're building AI agents, this might be the most important under-the-radar upgrade of the year.
platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling
anthropic.com/engineering/effective-context-engineering-for-ai-agents
claude.com/blog/improved-web-search-with-dynamic-filtering
anthropic.com/news/model-context-protocol
platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills
anthropic.com/engineering/advanced-tool-use
My Dictation App: whryte.com
Website: engineerprompt.ai
RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag
Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0
Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
Anthropic's latest Sonnet 4.6 release quietly introduced programmatic tool calling; a feature that lets AI agents write code instead of JSON to invoke tools, slashing token usage by up to 98% while improving accuracy. I break down why this "code mode" approach outperforms traditional tool calling, how companies like Cloudflare and Anthropic are already implementing it, and why this could become the new industry standard just like MCP did. If you're building AI agents, this might be the most important under-the-radar upgrade of the year.
platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling
anthropic.com/engineering/effective-context-engineering-for-ai-agents
claude.com/blog/improved-web-search-with-dynamic-filtering
anthropic.com/news/model-context-protocol
platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills
anthropic.com/engineering/advanced-tool-use
My Dictation App: whryte.com
Website: engineerprompt.ai
RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag
Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0
Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
![System 1 vs System 2 AI models: whats actually different?
A System 1 model like Jev takes one look: a single pass, no scratchpad. A System 2 model runs the same brain in a loop, writing notes and building on them step by step. I tested both on chains of questions that get longer each time. Jev falls off a cliff; Qwen 3.8 with thinking barely moves.
The rule: count the steps. If the answer is visible in one look, use System 1. If it needs results you dont have yet, use System 2.
Full breakdown and the experiment you can run yourself: [link to full video]
#AI #LLM #Jev #SystemOne #SystemTwo #AIModels #Shorts System 1 vs System 2 AI models: whats actually different?](https://i.ytimg.com/vi/8daNaFE-qOg/mqdefault.jpg)









