Can AI coach soccer?

Happy Monday! No time for small talk — let’s get to it. 💪

⭐️ Today’s Feature

This link leads to one of the most interesting things I’ve seen in AI recently.

What’s cookin’? Google DeepMind has built TacticAI, an AI system designed to help soccer coaches understand and improve tactics. Created with Liverpool FC and now being expanded with Brazilian club Palmeiras, the system studies player positions from broadcast-style video and predicts how a play may unfold up to eight seconds in advance. It uses geometric deep learning to treat players like connected points on a moving map, then forecasts where they are likely to go next. For corner kicks, it can also suggest better player setups. In testing, soccer experts preferred TacticAI’s recommended arrangements over real match setups 90% of the time.

🤔 Hunter’s take: The bigger story is not just “AI helps sports teams win.” It’s that AI is getting better at understanding movement before it happens. Today, that means corner kicks. Tomorrow, it could mean robots, traffic systems, warehouses, or military planning. While the application for sports is cool, it may just be the test field.

The AI tool you tried last quarter waited for a prompt, hallucinated a number, then asked if you'd like a summary.

Viktor opened a PR at 2am, rebased it against main, ran your test suite, and posted a note in #eng: "Two flaky tests in payments service, both pre-existing. Recommended merging after fixing them." Then drafted the customer reply for the support ticket the bug created.

That's 619K autonomous actions per day across 20,000+ teams. Not chat replies. Real work shipped to GitHub, Stripe, Linear, Notion, and 3,000+ other tools, from inside Slack and Microsoft Teams.

You don't supervise him any more than you supervise a senior engineer.

SOC 2 certified. Your data never trains models.

"It's what you probably originally thought AI was going to be when you first heard of it in sci-fi movies." Tyler, CEO.

Get Started for Free

What’s cookin’? Instagram is testing a new feature called Your Algorithm that lets users directly adjust what the app thinks they are interested in. Instead of only shaping recommendations through likes, watches, shares, and scrolling habits, users will be able to see the topics Instagram has assigned to them and change those topics themselves. The feature is expanding beyond Reels and Explore to the main feed. Instagram also plans to let people make more natural requests in the future, including asking for certain moods, vibes, content types, or even people.

🤔 Hunter’s take: Social media has always learned from us, but rarely listened to us. This feature might put the user back in control of what they see, making feeds feel less like traps and more like, well, social media.

You may have realized by now that AI is only as good as your prompt.

That’s why we offer professional AI Prompt Packs: ready-to-use prompts that help you stop staring at the blinking cursor and start getting real value from your favorite chatbot.

Hi — I’m Hunter, a PhD candidate whose work has appeared in major academic journals and popular tech outlets. I founded FryAI to make staying ahead of AI clear, accessible, and fun.