Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Spend your time on innovation and not the boring bits. Let Gemini in Android Studio handle the heavy lifting → How Agent Mode assists your data layer: 📄 Ingests custom API documentation 🛠️ Generates thin Retrofit data sources 📐 Adheres strictly to project interfaces

Android Developers

2,055,766 subscribers

27,510 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

4 Comments

Costa1 month ago

@AndroidStudio wew lad @ tomcolvin (you even on this hellsite? i dunno)

Raphael gwar gwar1 month ago

@AndroidStudio

Caprini Dev1 month ago

@AndroidStudio Lo de "ingiere documentación de API personalizada" es la parte que más curiosidad me da. ¿Alguien lo ha probado con una API interna rara, no con Retrofit de libro? Ahí se nota si el modo agente entiende de verdad el contrato o solo rellena huecos con lo que ya sabía.

Caner Kaşeler1 month ago

@AndroidStudio Is there a way to define SKILL set for Gemini?

Related Videos

introducing annotation mode in AI Studio refining your app should be as easy as pointing at what you want to change: simply highlight any component, button or text in your app and Gemini will handle the heavy lifting

introducing annotation mode in AI Studio refining your app should be as easy as pointing at what you want to change: simply highlight any component, button or text in your app and Gemini will handle the heavy lifting

Google AI Studio

122,518 views • 11 months ago

Connect your agents directly to Chrome DevTools. 🛠️ The new Chrome DevTools MCP server allows agents to inspect the DOM and debug console errors in real-time using Gemini CLI or any compatible agent. Check out the documentation on GitHub →

Connect your agents directly to Chrome DevTools. 🛠️ The new Chrome DevTools MCP server allows agents to inspect the DOM and debug console errors in real-time using Gemini CLI or any compatible agent. Check out the documentation on GitHub →

Google for Developers

22,793 views • 9 months ago

Turn messy project folders into structured spreadsheets in seconds. 📁 ➡️ 📊 Just select your sources in Google Drive and prompt Gemini to extract the data, calculate key metrics, and build your Sheet, all without leaving your workflow. See how it works at

Turn messy project folders into structured spreadsheets in seconds. 📁 ➡️ 📊 Just select your sources in Google Drive and prompt Gemini to extract the data, calculate key metrics, and build your Sheet, all without leaving your workflow. See how it works at

Google Workspace

31,881 views • 25 days ago

🚀 CabalSpy v3 — Multi-Chain KOL Data CabalSpy provides the deepest real-time KOL data layer on Solana, BNB and Base. KOL Widget, API & WebSocket delivering actionable multi-chain KOL intellegence. Integrate our API today and bring KOL intellegence to your platform.

🚀 CabalSpy v3 — Multi-Chain KOL Data CabalSpy provides the deepest real-time KOL data layer on Solana, BNB and Base. KOL Widget, API & WebSocket delivering actionable multi-chain KOL intellegence. Integrate our API today and bring KOL intellegence to your platform.

CabalSpy

22,993 views • 10 months ago

Today, is launching Aim, the first background agent purpose-built for marketers. For months, we've been obsessed with one problem: dashboards tell you what's happening, but not how to act on the data. Aim is the agent harness designed specifically for marketing. Aim is trained from scratch on Profound's proprietary data, grounded in our research, and understands how marketers get work done. Aim analyzes your AI Search data, Prompt Volumes, competitive insights, and Knowledge Base to surface the opportunities worth acting on. It finds the anomalies that matter so you can spend your time on what moves the needle. Every Project comes with a data-backed brief and recommended tasks. From there, you can: • Chat with Aim to refine the plan • Deploy the custom Agent in one click • Track progress automatically Aim is your newest teammate keeping you moving in the right direction, working 24/7.

Today, is launching Aim, the first background agent purpose-built for marketers. For months, we've been obsessed with one problem: dashboards tell you what's happening, but not how to act on the data. Aim is the agent harness designed specifically for marketing. Aim is trained from scratch on Profound's proprietary data, grounded in our research, and understands how marketers get work done. Aim analyzes your AI Search data, Prompt Volumes, competitive insights, and Knowledge Base to surface the opportunities worth acting on. It finds the anomalies that matter so you can spend your time on what moves the needle. Every Project comes with a data-backed brief and recommended tasks. From there, you can: • Chat with Aim to refine the plan • Deploy the custom Agent in one click • Track progress automatically Aim is your newest teammate keeping you moving in the right direction, working 24/7.

Dylan Babbs

79,962 views • 3 months ago

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Akshay 🚀

65,672 views • 10 months ago

You have not seen charts like this (or the ones that will come). AI Charts brings markets to life. Zoom, scroll, and explore price ranges in motion across any timeframe. The embedded AI layer does the heavy lifting, tag key events directly on the chart, then let the tools reshape the view around what matters to you. Ranges, technicals, sentiment, and raw data all transform dynamically. Your chart, built around your use case.

You have not seen charts like this (or the ones that will come). AI Charts brings markets to life. Zoom, scroll, and explore price ranges in motion across any timeframe. The embedded AI layer does the heavy lifting, tag key events directly on the chart, then let the tools reshape the view around what matters to you. Ranges, technicals, sentiment, and raw data all transform dynamically. Your chart, built around your use case.

SPECTRE AI

12,480 views • 7 months ago

See Google’s Gemini 2.5 Pro in action with the Box AI API! We put it to the test on complex invoice calculations and analyzing 10-K financial documents. Leverage Gemini 2.5 Pro via the Box AI API for advanced document processing, data extraction, and Q&A in your applications.

See Google’s Gemini 2.5 Pro in action with the Box AI API! We put it to the test on complex invoice calculations and analyzing 10-K financial documents. Leverage Gemini 2.5 Pro via the Box AI API for advanced document processing, data extraction, and Q&A in your applications.

Box

489,097 views • 1 year ago

Seal is now live on Sui Mainnet! Web3 finally has a native way to handle data privacy and access control. Define who can access your data and when. Encrypt it. Enforce it onchain. Seal + Walrus unlock the secure data layer Web3 has been missing. Let’s dive in 👇

Seal is now live on Sui Mainnet! Web3 finally has a native way to handle data privacy and access control. Define who can access your data and when. Encrypt it. Enforce it onchain. Seal + Walrus unlock the secure data layer Web3 has been missing. Let’s dive in 👇

MystenLabs.sui

121,559 views • 1 year ago

You missed the subway and need an e-bike across NYC, gets you there. Real-time MTA + Citi Bike data in one API. Pay just cents via x402 or MPP Add to your agent and get around NYC your way

You missed the subway and need an e-bike across NYC, gets you there. Real-time MTA + Citi Bike data in one API. Pay just cents via x402 or MPP Add to your agent and get around NYC your way

Matt Murray

65,069 views • 5 months ago

Say goodbye to sequential bottlenecks. In the stable release of Android Studio Quail 2, you can run multiple agent tasks in parallel with Gemini! 💬🔄 Watch how you can initiate and manage multiple agent tasks simultaneously across your chats. Read more in the launch blog post:

Say goodbye to sequential bottlenecks. In the stable release of Android Studio Quail 2, you can run multiple agent tasks in parallel with Gemini! 💬🔄 Watch how you can initiate and manage multiple agent tasks simultaneously across your chats. Read more in the launch blog post:

Google for Developers

14,716 views • 2 months ago

Google just made your entire content creation workflow free and automated. No more manual research and 50 open tabs. No more paying for expensive content tools. Here’s the new play 👇 → Turn notes into podcasts, videos, and quizzes in 1 click. → Upload 300+ sources to build a custom AI knowledge base. → Deep Research: Automated web scanning with full citations. → Studio Mode: Generate slide decks and landing pages instantly. → Gemini 3 Power: Zero-hallucination outputs grounded in your data. Save this for your next project. Google is shipping quietly and fast. Want the full guide? DM me.

Google just made your entire content creation workflow free and automated. No more manual research and 50 open tabs. No more paying for expensive content tools. Here’s the new play 👇 → Turn notes into podcasts, videos, and quizzes in 1 click. → Upload 300+ sources to build a custom AI knowledge base. → Deep Research: Automated web scanning with full citations. → Studio Mode: Generate slide decks and landing pages instantly. → Gemini 3 Power: Zero-hallucination outputs grounded in your data. Save this for your next project. Google is shipping quietly and fast. Want the full guide? DM me.

Julian Goldie SEO

15,449 views • 9 months ago

Introducing CEO Mode: Be the CEO of Your Army of Agents Lot of talk here about commanding agent armies. With Rox, it’s real and already working at scale for the Global 2000. Powered by Rox Governance - the first agentic governance system for revenue. CEO Mode gives you secure, unified and real-time view across every part of your book of business. With CEO Mode, you can: - Protect sensitive data as confidential data is only accessible to the right people. - Empower every team member and leader to self-serve actions without bottlenecks. - Build custom apps and workflows with governed, secure access. Simply ask your agent a question, and CEO Mode orchestrates the work across your entire system in seconds. You can stay focused on what matters most: growing your business.

Introducing CEO Mode: Be the CEO of Your Army of Agents Lot of talk here about commanding agent armies. With Rox, it’s real and already working at scale for the Global 2000. Powered by Rox Governance - the first agentic governance system for revenue. CEO Mode gives you secure, unified and real-time view across every part of your book of business. With CEO Mode, you can: - Protect sensitive data as confidential data is only accessible to the right people. - Empower every team member and leader to self-serve actions without bottlenecks. - Build custom apps and workflows with governed, secure access. Simply ask your agent a question, and CEO Mode orchestrates the work across your entire system in seconds. You can stay focused on what matters most: growing your business.

Rox

324,265 views • 3 months ago

We’ve introduced a new security layer on MyOneApp to better protect your account. By linking your login to your Safaricom SIM, we ensure it’s always you accessing your services— keeping fraudsters out. When logging in for the first time: - Ensure your Safaricom line is set as your primary data line. - ⁠Use mobile data (not Wi-Fi). - ⁠Complete the quick authentication. After login, using my OneApp doesn’t consume your data. You may need to re-authenticate if you remove your SIM. Safety and Security are App’Graded on #MyOneApp.

We’ve introduced a new security layer on MyOneApp to better protect your account. By linking your login to your Safaricom SIM, we ensure it’s always you accessing your services— keeping fraudsters out. When logging in for the first time: - Ensure your Safaricom line is set as your primary data line. - ⁠Use mobile data (not Wi-Fi). - ⁠Complete the quick authentication. After login, using my OneApp doesn’t consume your data. You may need to re-authenticate if you remove your SIM. Safety and Security are App’Graded on #MyOneApp.

Safaricom PLC

109,432 views • 5 months ago

Made more improvements to the usage view in T3 Code. Much easier to see where your "spend" is and how different models behave based on your own data btw this measures all usage of Claude Code and Codex on your machines, not just usage within T3 Code :)

Made more improvements to the usage view in T3 Code. Much easier to see where your "spend" is and how different models behave based on your own data btw this measures all usage of Claude Code and Codex on your machines, not just usage within T3 Code :)

Theo - t3.gg

38,094 views • 3 days ago

Describe it. Watch it appear in SolidWorks. CADAI Assistant lets you describe the component you need in plain language—and delivers a fully editable SolidWorks model in seconds, built from your company’s data, design standards, and existing workflows. Spend less time on setup & more time on innovation.

Describe it. Watch it appear in SolidWorks. CADAI Assistant lets you describe the component you need in plain language—and delivers a fully editable SolidWorks model in seconds, built from your company’s data, design standards, and existing workflows. Spend less time on setup & more time on innovation.

CADAICO

11,734 views • 1 year ago

Podcasts are the largest source of untapped data on the internet. But searching audio is still broken. Today, we're launching a product to fix that. Meet the Particle Podcast Intelligence API. Track mentions or topics, get shareable clips, uncover ad intelligence, and get access to rich metadata. Tell your agent: "Go to 🛠️

Podcasts are the largest source of untapped data on the internet. But searching audio is still broken. Today, we're launching a product to fix that. Meet the Particle Podcast Intelligence API. Track mentions or topics, get shareable clips, uncover ad intelligence, and get access to rich metadata. Tell your agent: "Go to 🛠️

sara beykpour

612,552 views • 5 months ago

The depth of your research insights depends entirely on the precision of your prompts. In Episode 5 of Decoding Data Insights, Dr. Lyndon Walker sits down to demonstrate how to find sources, run advanced regressions and mediation analysis, and decode highly transparent, reproducible workflows with SciSpace Agent. Trusted by 9.6M+ researchers worldwide. Sign up for free and see how it works:

The depth of your research insights depends entirely on the precision of your prompts. In Episode 5 of Decoding Data Insights, Dr. Lyndon Walker sits down to demonstrate how to find sources, run advanced regressions and mediation analysis, and decode highly transparent, reproducible workflows with SciSpace Agent. Trusted by 9.6M+ researchers worldwide. Sign up for free and see how it works:

SciSpace

167,924 views • 3 months ago