Smitha Kolan

I used the new Gemini CLI and gave it only the YouTube link of a tech tutorial, and it set up the entire project for me, perfectly. This is a massive win for productivity and builders everywhere. Check it out here: github.com/google-gemini/…

$GOOG 🚀

Happy Friday!

Hit 1K on X 🤠

Learn how to build anything with Gemini 3! New Episode of the Agent Factory just dropped where we show you how to build webapps, multi-modal agents and even an entire agentic workforce. There’s truly no limit to what is possible with Gemini 3. Huge thanks to our guest @bhancock_ai and my co-host @vladkol! Full episode is live now. youtube.com/watch?v=hj0nTL…

Gemini 3 Pro just launched, and it’s unreal. The model has: • Advanced high-level reasoning • Complex instruction following • Agentic operations + autonomous code execution • Multimodal understanding across long contexts (text, image, audio, video) So I built an AI agent powered by Gemini 3 Pro + Google Search to help me brainstorm viral demo ideas! Full demo 👇

@steren @Waymo Waiting for @Waymo to come to Canada 🇨🇦

🏆 Achievement unlocked: @Waymo to work

Just about to give my first keynote at @Google in Bangalore on Building AI Agents! There’s 500 people here in total! Wish me luck 🍀!

@rseroter @GoogleCloudTech @Google Congratulations @rseroter! 🚀

My job just changed. I’m still leading Developer Relations and Docs for @GoogleCloudTech, but now I’m also leading the @google Open Source Program Office, Developer Relations for key dev tech (e.g. Go, Flutter, Firebase) and our global dev ecosystem team. What an amazing group!

Got a cool gift from @GoogleDeepMind! 💛💛💛

@heyshipz Joe Hisaishi

name a famous Japanese person without using google

@deedydas Congratulations @Dheemanthredy!

Two 23 year old Indians just dropped the #2 open-weight AI voice model in the world, trained purely on free credits! Maya1 is #20 globally, better than even Google's best. 3B params, runs on one GPU and does 20+ emotions with < 100ms latency You can just do things.

@barkmeta This looks AI generated

Sold all of my Crypto. Bought a farm in the middle of nowhere. Woke up at 6am, fed the chickens, and didn’t check a single chart. Feeling calm for the first time in 5 years. You guys keep chasing nonsense. I’m chasing peace.

Let’s go! 🚀🚀🚀

Finally updated my profile picture after 5 years. This was taken at the Google office in SF

Loved chatting about agents for data scientists and data engineers with @LuciaBlick

This was great to film! Highly recommend watching 👀

Caught the salmon run in Canada today! It felt like an impossible task placed on these salmon, to jump against the current but they were relentless. Truly inspiring ❤️

Here is Gemini CLI’s September 15th weekly update for v0.6.0 - 🎉 Higher limits for Google AI Pro and Ultra subscribers: we’re psyched to finally announce that Google AI Pro and AI Ultra subscribers now get access to significantly higher 2.5 quota limits for Gemini CLI! - Announcement: blog.google/technology/dev… - 🎉Gemini CLI Databases and BigQuery Extensions: Connect Gemini CLI to all of your cloud data with Gemini CLI. - Announcement and how to get started with each of the below extensions: cloud.google.com/blog/products/… - AlloyDB: Interact, manage and observe AlloyDB for PostgresSQL databases - BigQuery: Connect and query your BigQuery datasets or utilize a sub-agent for contextual insights - Cloud SQL: Interact, manage and observe Cloud SQL for PostgreSQL, Cloud SQL for MySQL and Cloud SQL for SQL Server databases. - Dataplex: Discover, manage, and govern data and AI artifacts - Firestore: Interact with Firestore databases, collections and documents Looker: Query data, run Looks and create dashboards - MySQL: Interact with MySQL databases - Postgres: Interact with PostgreSQL databases - Spanner: Interact with Spanner databases - SQL Server: Interact with SQL Server databases - MCP Toolbox: Configure and load custom tools for more than 30+ data sources - ‼️The Three-Day Drop: [██████████] 101% .......... - JSON Output Mode: Have Gemini CLI output JSON with --output-format json when invoked headlessly for easy parsing and post-processing. Includes response, stats and errors. (jerop) - Keybinding Triggered Approvals: When you use shortcuts (shift+y or shift+tab) to activate YOLO/auto-edit modes any pending confirmation dialogs will now approve. (bulkypanda) - Chat Sharing: Convert the current conversation to a Markdown or JSON file with /chat share <file.md|file.json> (rramkumar1) - Prompt Search: Search your prompt history using ctrl+r. (Aisha630) - Input Undo/Redo: Recover accidentally deleted text in the input prompt using ctrl+z (undo) and ctrl+shift+z (redo). (masiafrest) - Loop Detection Confirmation: When loops are detected you are now presented with a dialog to disable detection for the current session. (SandyTao520) - Direct to Google Cloud Telemetry: Directly send telemetry to Google Cloud for a simpler and more streamlined setup. (jerop) - Visual Mode Indicator Revamp: ‘shell’, 'accept edits' and 'yolo' modes now have colors to match their impact / usage. Input box now also updates. (miguelsolorio) github.com/google-gemini/… 🧵

Big news for devs! 🚀 Google AI Pro & Ultra subscribers now get a higher daily quota for Gemini CLI & Code Assist. Build more with Gemini 2.5 Pro/Flash in your IDE/terminal. blog.google/technology/dev… #Gemini #GoogleAI @GoogleDevs