In partnership with

Welcome Automaters!

So quick PSA: Claude Code is sliding into Slack, and no — this isn’t just “AI writes some code.”

This is Slack leveling up into a full-on command center, where you literally delegate engineering tasks in chat.

What actually changed?

Before, Claude in Slack was like that helpful intern, great for explanations, rewrites, and tiny fixes. But now? You tag @Claude in a thread, drop a bug report or feature request, and Claude spins up a full coding session: figuring out the right repo, solving the problem, posting progress updates, and dropping PR links — all in-thread.

Why it matters

The real battle isn’t happening inside VS Code anymore — it’s happening where teams argue about why something isn’t working.

Slack is turning into an agentic hub, and whoever becomes the default assistant there probably wins the AI-for-devs war.

Meanwhile… OpenAI just dropped a whole other plot twist

They casually made holiday shopping fully conversational.

ChatGPT + Instacart now lets you: plan meals, generate a full grocery list, and check out right there in chat

The big picture: AI is leaving the apps and moving directly into your flow, your team chats, your grocery runs and into the tiny decisions you make all day. 

We’re not just getting better models.  We’re getting models that can act. And speaking of models that can act….

Here's what we have for you today

🤖 Chrome’s New AI Features: How Google Keeps Agents Safe and Aligned

Chrome is about to level up… and I mean really level up. 

Think: booking tickets, shopping, comparing prices, filling forms, navigating pages, and clicking for you.

But let’s be real — an AI with “hands” and permissions can also… y’know… buy the wrong thing, leak your data, or wander into sketchy corners of the internet.

That’s exactly why Google dropped the playbook for keeping Chrome’s new agentic features from going rogue.

And honestly? It might be one of the nerdiest security stacks they’ve ever shared.

Here’s a quick look at the security features and how they actually work: 

  1. User Alignment Critic: Picture a Gemini-powered supervisor that checks the plan your AI agent comes up with and goes, “Hold up… does this actually serve the user’s goal?” If the answer’s “nope,” the plan gets sent back like an overcooked steak. Fun fact: the critic only sees metadata, never the real webpage, so yeah, it can’t snoop on your stuff.

  2. Agent Origin Sets: This is Google’s way of respecting personal space. Here sites get split into two categories: Read-only: for info surfaces. And Read-writable: for very controlled actions inside specific frames. These boundaries prevent the AI from accidentally leaking bits of data across sites. Essentially, the browser controls exactly what the AI sees, and what it can’t.

  3. Observer Model for URLs: Every navigation attempt is checked by this feature, so the AI can’t accidentally send you to sketchy, model-invented scam pages. 

  4. For sensitive stuff — like bank accounts, medical portals, password managers, messages, or purchases, the AI won’t touch a thing unless you approve. Chrome literally pauses and asks before it moves. 

Also important: The AI agents never see or access your actual passwords — that’s all handled through your regular password manager.

Plus, Google’s running a prompt-injection classifier to filter out malicious instructions and is actively letting researchers try to break the system before it ships.

Side note: Perplexity is doing similar work — they even open-sourced their own anti-injection detector.

The big picture?

We’re entering the era of AI that acts, not just answers, and the entire future of this space depends on whether these systems stay aligned, safe, and locked up where it counts.

Chrome’s pushing hard to get this right. Now, we just have to see if it actually works — and, most importantly, if the rest of the AI world can keep up.

PS: Just like yesterday, we asked our AI which model is most likely to snag #1 AI of the Year

The answer? 😂 You’ve gotta check it out for yourself — and remember, while you’re laughing, the AI is still learning!

Your competitors are already automating. Here's the data.

Retail and ecommerce teams using AI for customer service are resolving 40-60% more tickets without more staff, cutting cost-per-ticket by 30%+, and handling seasonal spikes 3x faster.

But here's what separates winners from everyone else: they started with the data, not the hype.

Gladly handles the predictable volume, FAQs, routing, returns, order status, while your team focuses on customers who need a human touch. The result? Better experiences. Lower costs. Real competitive advantage. Ready to see what's possible for your business?

🧱 Around The AI Block

🤖 AI Workout Of The Day: How ChatGPT, Gemini & DeepSeek Handle Video Summaries

Long YouTube videos are great, but who has time to watch them all?

We put ChatGPT, Gemini, and DeepSeek to the test to see which AI can take a full transcript and turn it into clear, digestible bullet points.

If you want quick takeaways without missing the key ideas, this showdown shows which model actually gets it.

Here’s How To Make This Prompt Work

  1. Provide Full Context: Include the complete transcript so the AI has all the info.

  2. Be Specific About Format: Ask for bullet points or numbered lists to keep the summary structured and scannable.

  3. Highlight Conciseness: Focus on main points, not minor details.

  4. Encourage Clarity: Each bullet should be self-explanatory, brief, and easy to understand. 

  5. Compare Across Models: Evaluate accuracy, clarity, organization, and whether the summary captures the essence of the video.

PS: The live side-by-side comparison of ChatGPT, Gemini, and DeepSeek is exclusive to premium subscribers. If you want in on this AI showdown, now’s the time to upgrade.

Prompts to try:

“Summarize the following YouTube video transcript into three key bullet points. Each bullet should clearly and concisely highlight the main ideas from the video. Focus on the most important insights or takeaways, avoiding minor details or unnecessary info. Make sure the points are easy to understand, even for someone who hasn’t watched the video. Capture the essence of the content in a structured, readable format. Maintain accuracy and clarity, keeping each bullet short and impactful.”

P.S. Each Workout of the Day (WoD) is powered by original prompts written by our team — no recycled or external templates here. That means lower risk of prompt injection or manipulation, and higher trust in what you’re creating.

Also…

Upgrade now to see this whole month’s prompt videos and more, or buy TODAY’S WOD for just $1.99

Is this your AI Workout of the Week (WoW)? Cast your vote!

Login or Subscribe to participate

That's all we've got for you today.

Did you like today's content? We'd love to hear from you! Please share your thoughts on our content below👇

What'd you think of today's email?

Login or Subscribe to participate

Your feedback means a lot to us and helps improve the quality of our newsletter.

logo

🚀 Want your daily AI workout?

Premium members get daily video prompts, premium newsletter, an no-ad experience - and more!

🔓 Unlock Full Access

Premium members get::

  • 👨🏻‍🏫 A 30% discount on the AI Education Library (a $600 value - and counting!)
  • 📽️ Get the daily AI WoD (a $29.99 value!)
  • ✅ Priority help with AI Troubleshooter
  • ✅ Thursday premium newsletter
  • ✅ No ad experience
  • ✅ and more....

Reply

or to participate

More From The Automated

No posts found