- What's Up in AI
- Posts
- Let These Tools Work For You !
Let These Tools Work For You !
Stop losing your best AI conversations to the void
What's Up in AI
July 31, 2026
In partnership with
Welcome Back, AI Geeks!
This is Edition #28 of the Weekly Tool Deep Dive 🔍️
We're back with 3 tools that will fuel your productivity this week so you have more time for things you love!
Each tool comes with real use cases you can copy paste and examples of how people are automating the tedious stuff. No fluff, just execution.
What It Is?
At this point, we all use AI for research, brainstorming, writing, building decks, etc.
And more often than not, you’ll find yourself spending hours searching for that one chat 3 months ago on the business idea you had on a random Tuesday at 2 am. But not anymore.
AI Toolbox is a Chrome extension that adds the organization layer that ChatGPT, Claude, Gemini, and Grok never built in.
It organises all your chats across tools into folders & subfolders.
You can search your entire chat history, export any conversation (or your whole history) in one click as PDF, Markdown, TXT, or JSON.
Use a single prompt library everywhere you chat.
Over 40,000 users across 150+ countries are already using & loving it.
💥 Why It's Hot Right Now
Nobody uses one AI anymore. Serious work now runs through two or three models at once, and the cost is that your best thinking ends up scattered across four separate chat histories with no shared search bar. AI Toolbox is the fix for "I want to use whichever model is best for the job without losing track of my own work." One extension, every platform, everything searchable in one place.
The Tool in Action
A consultant plans a launch across three AIs: timeline in ChatGPT, press release in Claude, concepts in Gemini. A week later the client asks about pricing and she can't remember where that chat lives. One search for "launch pricing" surfaces all three threads instantly, and she's back in the right conversation in five seconds.
⚡ How to Use It
Install AI Toolbox from the Chrome Web Store (it's free).
Open ChatGPT, Claude, Gemini, or Grok. The toolbox shows up automatically, no setup needed.
Hit the search icon or Cmd/Ctrl+Shift+F to search across all your chats at once.
Build folders and drop chats in as you go to keep projects from bleeding into each other.
Export any single chat, or your entire history, in one click when you need a clean copy. prompt here →
What It Is
Paste any YouTube link and Unfurl turns it into a structured chapter guide, a chat tutor that answers from the actual transcript, a do-it action plan with specific steps, and a shareable hand-illustrated infographic — all from one video.
💥 Why It's Hot Right Now
Free for your first guide, no card needed, and at $9/month after that it's honestly one of the cheapest productivity upgrades you can make.
Key Features:
Structured chapter guide with timestamps — The video gets broken into chapters with skill levels tagged and clickable timestamps so you can jump to exactly what matters without rewatching.
Transcript-grounded chat tutor — Ask questions and get answers pulled from what was actually said in the video — not guessed, cited back to the exact moment it was mentioned.
SMART action plan — Specific, measurable steps drawn from the video you can export and actually follow, not just a vague "key takeaways" list.
Real Example
A startup founder watches a two-hour YC talk on pricing strategy but can't retain all of it. She pastes the URL into Unfurl, skims the chapter guide to find the three sections relevant to her stage, asks the chat tutor two specific follow-up questions grounded in the transcript, and exports the action plan with five concrete pricing experiments to run this week. The infographic goes into her team's Notion doc. The video she watched on a Friday has actual follow-through by Monday.
⚡ How to Use It
Go to unfurl.sh and paste your first YouTube link — your first guide and action plan are completely free, no card required.
Read the chapter guide first to get the map before diving into details — it tells you where the valuable parts actually are.
Use the chat tutor for any concept you didn't fully follow — it cites the exact timestamp so you can go back if you need to hear it said.
Export the action plan as a PDF and drop it wherever you track tasks — Notion, your notes app, your to-do list — so it has a home.
For course playlists or multi-part series, use the multi-video guide feature to combine everything into one reference doc instead of five separate guides.
Share the infographic with your team or on social — it's the cleanest way to summarise something you found valuable without doing the summarising yourself.
1,000+ Proven ChatGPT Prompts That Help You Work 10X Faster
ChatGPT is insanely powerful.
But most people waste 90% of its potential by using it like Google.
These 1,000+ proven ChatGPT prompts fix that and help you work 10X faster.
Sign up for Superhuman AI and get:
1,000+ ready-to-use prompts to solve problems in minutes instead of hours—tested & used by 1M+ professionals
Superhuman AI newsletter (3 min daily) so you keep learning new AI tools & tutorials to stay ahead in your career—the prompts are just the beginning
What It Is
ByteDance built an AI video model and it immediately topped every benchmark on earth. Seedance 2.0 generates up to 2K video with native synchronized audio — dialogue, sound effects, ambient noise — all in one pass. No separate audio step, no stitching, no post-processing.
💥 Why It's Hot Right Now
Every other AI video tool makes you generate the clip first and figure out audio later. Seedance 2.0 uses a Dual-Branch architecture that generates video and audio at the same time, which is why the lip-sync actually looks right and the sound actually matches what's happening on screen. It launched in February 2026 and nothing else has touched it since.
Key Features:
Audio baked in from the start — Lip-sync in 8+ languages, sound effects, ambient audio — all generated alongside the video, not added after.
Up to 12 reference inputs — Feed it 9 images, 3 video clips, and 3 audio files at once. It uses all of them to direct the scene.
Multi-shot in one generation — Type "lens switch" in your prompt and the model cuts to a new angle mid-video while keeping the same characters and setting.
Real Example
A brand creator references a trending ad template by uploading the clip, adds product reference images, writes the scene description, and generates a 15-second video with English and Spanish voiceover simultaneously in one pass. Both versions are done. The shoot she was going to book for Thursday gets cancelled.
⚡ How to Use It
Start on ByteDance's Dreamina platform or through Artlist — sign up and use the free credits to test the basics before paying.
Do a simple text-to-video first before touching references, just to understand how the model interprets prompts.
When you need character or style consistency, upload your reference images — this is where Seedance 2.0 separates from every other tool.
Write prompts in short beats — describe what happens in each 2 to 3 seconds separately rather than dumping one long scene description.
Use the Fast variant to test ideas, switch to Standard only for the final render.
Set your aspect ratio before generating — 9:16 for Reels and TikTok, 16:9 for YouTube. Don't crop a finished video.
📣 Before You Bounce...
Hit reply and let us know:
🔥 "This was exactly what I needed - more tool breakdowns!"
👍 "Good stuff, keep these coming"
🤷 "Not my vibe, but appreciate the effort"
Know someone drowning in explanation requests? Share this with them - they'll thank you later.
We’ll be back soon with more spicy takes on What’s Happening in AI, so stay tuned & share our newsletter with a friend using this link!
Stay curious! 🤖
What's Up in AI Team