In partnership with
Did you know that we have LinkedIn, Instagram and X accounts
that you can follow?
Hi {{first_name|everyone}},
YouTube's rolling out a way to just tell your feed what you want instead of hoping it figures that out from your watch history, so we're getting into what that actually looks like.
Beyond that, there's a handy MCP tool for shipping full-stack apps straight from your AI chat, a couple more useful finds, and a sculpture built entirely to mock AI slop.
Let's get right into it.
🤿 DEEP DIVE
YouTube Gets a Prompt Box
The recommendation algorithm is becoming something you can talk to.
Most recommendation feeds work the other way around.
You watch things. The platform watches what you watch. And eventually it decides what else you might want.
YouTube is adding a slightly different idea. Just tell it.
The company announced something called custom feeds, which lets you describe the kind of YouTube feed you want in plain language. Gemini then uses that request to build one for you.
And the useful bit is that you're not limited to something basic like "cooking videos."
YouTube says you could ask for video podcasts that fit a 30-minute train commute. Or "relaxing commentary videos to unwind with." You can also get much more detailed about what the feed should include, exclude, or prioritize.
Basically, instead of trying to teach the recommendation system what you want by watching enough stuff, you're giving it instructions directly.
It's less "pick a topic"
I think this is the part that makes the idea more interesting.
These aren't just folders for interests. The prompt can describe the purpose of the feed too.
That 30-minute commute example is a good one because the request isn't simply "give me podcasts." There's context attached. You want a particular type of video for a particular chunk of your day.
And because Gemini is handling the request, YouTube says those instructions can be lengthy and detailed.
Once the feed is created, it gets its own tab pinned at the top of the YouTube home page. You can make multiple feeds and jump into whichever one fits what you're looking for at that moment.
Your normal feed isn't going anywhere
There is one important distinction here.
YouTube isn't handing over the main recommendation feed itself. That's staying as the place for your usual recommendations.
Custom feeds sit alongside it.
So "build your own algorithm" is maybe a little generous. It's more like YouTube is letting you create a few purpose-built recommendation lanes inside YouTube, using normal language instead of settings and filters.
YouTube isn't alone here either. Bluesky, Threads, Instagram, X, and Spotify all introducing their own versions of customizable feeds, with several using AI.
YouTube's version starts rolling out across web and mobile next month.
The quick take
YouTube's new custom feeds are created from plain-language prompts.
Gemini builds the feed around what you want included, excluded, or prioritized.
Prompts can describe a purpose or mood, not just a topic.
Custom feeds get their own tabs and won't replace YouTube's main recommendation feed.
Support for multiple feeds starts rolling out on web and mobile next month.
🤝 FROM OUR FRIENDS
A quick share we thought you might find useful
Hire Ava, the AI BDR built for enterprise
Ava is the first AI BDR to run outbound end to end, and you decide whether she runs autonomously or on copilot.
She finds leads or ingests accounts from your CRM, enriches them, sends personalized emails on behalf of your reps, follows up, handles replies and books meetings. Website visitor de-anonymization, intent signals, and a parallel dialer come built in.
A small team can manage her centrally for thousands of reps who never log in. Everything syncs two-way with Salesforce and HubSpot.
Ava runs outbound for companies like DoorDash and Grammarly, and one customer deploys her across 1,000+ reps. Ava is SOC 2 Type II audited, SSO and GDPR ready. Ava is how revenue teams grow pipeline without growing headcount.
🔥 WHAT’S THE BUZZ
What people are building, sharing, and talking about
As AI takes on more of the actual coding, the work around it changes too. Less “write all the code,” more “know what should be built, catch the bad calls, and step in when things get messy.”
⚒ TOOL SNAPSHOTS
Futuristic tools within AI, no-code, and productivity
Build and ship a full-stack app without leaving your AI chat.
Why it’s useful: Handy if you want Claude or ChatGPT to handle the build while Floot takes care of the workspace, database, logins, hosting, and publishing setup.
🔍 Hookest
See how viral short-form videos actually open.
Why it’s useful: Useful for creators and marketers who want real examples from their niche or competitors instead of guessing what kind of hooks are working.
Give your AI more context about your life before you ask.
Why it’s useful: The idea, basically, is less repeating yourself. Cotton keeps track of personal context while Melody uses it to help you stay on top of commitments.
👀 ON OUR RADAR
One more thing we thought you'd like
Watch the full system run live on Sep 30. Walk away ready to do it yourself.
Most founders have LinkedIn traction with nothing to show for it in the CRM. On Sep 30, Maria Gharib (Mindstream) and Valerie Chapman (Ruth AI) walk through the exact system live.
From AI-assisted content creation to sequenced outreach to booked meeting. You'll leave with a process you can run the same day.
Eligible startups also get the LinkedIn-to-Leads Toolkit: ad credits, Apollo, Captions, and HubSpot's Prospecting Agent.
🤖 AI MADE THIS
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!
Did you like today's email?
What more do you want to see in this newsletter?
