Google just added Learn Mode and Custom Instructions to Gemini inside Google Colab. Instead of generating copy-paste code, Learn Mode breaks down concepts and guides developers step by step, while custom instructions live right inside the notebook to travel with shared files.
Google just open-sourced the Colab MCP Server, enabling any MCP-compatible AI agent to programmatically control Google Colab notebooks straight from your terminal. Tools like Claude Code or Gemini CLI can now create cells, run Python scripts, and render visualizations live in the cloud. It basically turns Colab into an automated sandbox so agents no longer run risky, resource-heavy code on your local machine.
Google just integrated its Data Science Agent directly into Colab, powered by the Gemini 2.0 model family. Users can upload CSV, JSON, or text files up to 1GB and ask plain-English questions to clean messy datasets, build visualizations, or write SQL. It rolled out for free this week under Colab's standard compute limits.
Google just expanded its AI code assistance features to all Colab users, including those on the free tier in eligible regions. Users can generate Python code from plain English prompts and use an AI chatbot to explain and fix runtime errors. Why it matters: Bringing free AI pair programming to over 10 million active Colab users levels the playing field for students and researchers worldwide.
Google just announced that Colab is adding AI coding features powered by its new Codey models. Users will soon get natural language code generation, smart autocomplete, and a built-in coding chatbot right in their notebooks. It rolls out first to U.S. paid subscribers before expanding to free users and other regions.
Google just updated Bard with full programming support, tackling one of its most-requested features. The experimental AI can now generate, debug, and explain code across more than 20 languages like Python, C++, and Go, plus export directly to Google Colab. Google notes it's still experimental and prone to bugs, so you will definitely want to double-check its output.
