Google Simplifies File Search with RAG

Hi everyone,

Google’s new RAG tool for file search is getting a lot of attention for how easily it lets you find and work with documents. Their Vertex AI upgrade also makes running and scaling machine learning smoother for teams building AI into their workflows.

Meanwhile, Meta is going big with a massive investment in new U.S. data centers to power its next wave of AI growth. It’s a clear sign that the race to build the best AI infrastructure is only speeding up.

Let’s get right into it.

In this issue:

• 🤝 In Partnership: Download the audience guide free

• 🤿Deep Dive: Google’s new RAG Tool - File search

• 🤝 Powered by: Start your free fraud protection trial

• 🖼️AI Art: Examples of great and trending AI art

• 🤿Deep Dive: Google’s Vertex AI upgrade

• 🤝 Supported by: Get smarter every morning

• 🤿Deep Dive: Meta’s $600B data centers

🤝IN PARTNERSHIP WITH SPEEDEON

Where to find high-intent holiday shoppers

Let’s be real: most brands are targeting the same people this holiday season. “Shoppers 25–54 interested in gifts.” Sound familiar? That's why CPMs spike and conversion rates tank.

Speedeon’s Holiday Audience Guide breaks down the specific digital audience segments that actually perform—from early-bird deal hunters actively comparing prices to last-minute panic buyers with high purchase intent. These aren't demographic guesses.

And our behavioral audiences are built on actual shopping signals and real-world data —the same approach we use for clients like FanDuel and HelloFresh."

You'll get the exact audiences, when to deploy them, which platforms work best, and what kind of performance to expect.

Download the guide and get smarter about your holiday targeting before the holiday rush hits.

See the Holiday Audience Guide

🤿 DEEP DIVE

Google Adds File Search to Gemini API

Intelligence: Google has launched the File Search Tool, a managed retrieval-augmented generation (RAG) system built into the Gemini API, offering simplified pricing and full-stack integration for enterprise-grade document search.

• Pricing is $0.15 per 1M tokens for initial file indexing; storage and query-time embeddings are free.

• File Search handles storage, chunking, embedding, retrieval, and context injection end-to-end within the generateContent API.

• It uses Gemini’s latest embedding model for semantic vector search and supports formats like PDF, DOCX, TXT, JSON, and common code files.

• Responses include built-in citations showing which document passages informed the output.

• A demo app is available in Google AI Studio, requiring a paid API key.

🤝POWERED BY CHARGEFLOW

Stop post-purchase fraud before it drains your eCommerce business.

Running an eCommerce brand is hard enough, fraud shouldn't make it harder.

Post-purchase fraud, or "digital shoplifting," slips past checkout tools and costs DTC brands millions in disputes, wasted shipping, and lost revenue.

Chargeflow Prevent is the first AI-powered solution that stops fraud after payment but before fulfillment, cutting disputes by up to 90% with less than 0,1% false positives.

Stop Fraud in Its Tracks

🖼️ AI ART

Examples of great and trending AI art

🤿 DEEP DIVE

Google Cloud Expands Vertex AI Agent Builder

Intelligence: Google Cloud has rolled out major upgrades to its Vertex AI Agent Builder, adding new tools for building, scaling, and governing production-grade agents—alongside free access options and real-world adoption across industries.

• The Agent Development Kit (ADK) has over 7 million downloads and powers agents for Gemini Enterprise and other Google products.

• New build features include configurable context layers to reduce token usage, a plugin framework with self-healing tools, Go SDK support, one-command deploy via ADK CLI, and starter assets in Agent Garden.

• Agent Engine managed services now offer observability dashboards, traces for agent actions, and a debugging playground.

• A new Evaluation Layer includes a User Simulator for testing agent behavior, with simplified access via Gmail sign-up and free tiers for Cloud accounts.

• Governance tools include native agent identities as IAM principals, Model Armor for prompt injection defense, and integration with AI Protection in Security Command Center.

• Real-world use cases include Color Health’s breast cancer screening assistant, PayPal’s Agent Payment Protocol AP2, and Geotab’s enterprise-wide ADK adoption.

🤝SUPPORTED BY MORNING BREW

All the stories worth knowing—all in one place.

Business. Tech. Finance. Culture. If it’s worth knowing, it’s in the Brew.

Morning Brew’s free daily newsletter keeps 4+ million readers in the loop with stories that are smart, quick, and actually fun to read. You’ll learn something new every morning — and maybe even flex your brain with one of our crosswords or quizzes while you’re at it.

Get the news that makes you think, laugh, and maybe even brag about how informed you are.

Try it for free

🤿 DEEP DIVE

Meta Plans $600B U.S. Data Center Expansion

Intelligence: Meta has announced a $600 billion investment in U.S. data centers to support its AI growth and job creation goals, amid growing concerns over infrastructure strain and environmental impact.

• Meta has already invested $52B in U.S. data centers since 2010, generating $60B in economic activity across 15 states, with new builds in Idaho, Texas, and Alabama.

• Expansion includes a $27B Louisiana project via a special purpose vehicle and $30B raised through bond sales.

• Big Tech peers plan $380B in 2025 capital spending, mostly for data centers, placing Meta’s move in a broader AI infrastructure race.

• Economist Jason Furman notes that while AI-related investment is just 4% of GDP, it drove 92% of U.S. GDP growth in early 2025 though growth may slow without low energy and interest rates.

• Utilities have requested $29B in rate hikes to meet rising electricity and water demand; officials in Iowa and Arizona have flagged resource concerns.

• Power availability is a growing bottleneck, with grid upgrades potentially delaying projects up to six years and critics warning of long-term costs to local communities.

ℹ️ ABOUT US

The Intelligent Worker helps you to be more productive at work with AI, automation, no-code, and other technologies.

We like real, practical, and tangible use-cases and hate hand-wavy, theoretical, and abstract concepts that don’t drive real-world outcomes.

Our mission is to empower individuals, boost their productivity, and future-proof their careers.

We read all your comments - please provide your feedback!