Mushfiq Sajib
@heysajib • 35,363 subscribers
🤖 AI enthusiast & educator | Talks about AI news, tips, and use cases | 65k+ followers on LinkedIn | DM for Collaboration or Email me: [email protected]
Videos
Most AI coding setups right now look something like this: one agent in a terminal, another in a browser tab, a chat window somewhere else, and you in the middle copy-pasting diffs like a very tired air traffic controller. JetBrains just launched something aimed right at that mess. It's called JetBrains Air, and it lives inside their IDEs. The short version: Air lets you direct multiple coding agents, run their tasks in parallel, and review their work without ever leaving your IDE. Here's what stood out to me: 👇 1. You pick the agents. Air isn't tied to a single agent or provider. You can use the ones you already like. That matters more than it sounds, because the "best" coding agent changes every few months, and nobody wants to rebuild their whole workflow each time. 2. Parallel work without losing track. You can run several agent sessions at once, even across different projects. Air shows you where your attention is needed, so you're not hopping between tabs to find out which agent is stuck. 3. You stay in control. You can follow what each agent is doing, give it input, inspect the changes, and review the output before accepting anything. Nothing lands in your codebase just because an agent felt confident. 4. The agents get IDE smarts too. This is the part I find most interesting. JetBrains IDEs already have great code navigation, refactoring, testing, and debugging. With Air, both you and your agents work with that context. So the agents aren't guessing blind inside a chat box, and when something needs a human, the real tools are right there. The bigger idea here is that agents become part of your development workflow instead of a separate chat you keep switching to. There's also a nice bonus. For a limited time, JetBrains is offering Junie Lite for free (fair use applies). It's their own coding agent paired with a highly efficient model. It isn't pitched as a frontier-level agent. Think of it as a solid, free baseline for trying out Air and running everyday tasks. Air works in any JetBrains IDE and is in early access right now. If you write code with agents, give it a try: #ad
Mushfiq Sajib40,469 次观看 • 23 天前
I run a daily AI newsletter with real subscribers. For two years I never had a proper explainer video for it. Not because I didn't want one. Because a decent one usually meant paying an editor or losing a week to editing software. Here's what changed: 👇 I gave Pexo my newsletter link and a couple of screenshots. Told it I wanted a 20 to 30 second explainer, simple and trustworthy, for people into AI tools and news. It didn't just start generating. It researched my actual site first, the dark purple brand, the robot illustrations, the tone. Then it proposed a full structure before making anything: a chaotic burst of AI headlines to open, a calm cut into the wordmark, three quick proof beats, then a clean close on the subscribe screen. It also asked me to confirm the format before producing. Vertical for social. Text on screen instead of a voiceover. Small thing, but it meant nothing got wasted on a version I didn't need. Once I saw the first cut, the opening felt slow. I said the first beat should be 3 seconds instead of 5. It didn't just trim the clip. It retimed the music drop and every caption after it so the whole thing still felt intentional instead of chopped. Final video: 23 seconds. Opens on the noise every AI newsletter promises to cut through. Settles into calm. Three quick proof points. Ends on subscribe. If you run something with no launch video, a product, a newsletter, a service, you don't need to learn editing software first. Give Pexo your link, tell it who it's for, and push back until it's right.
Mushfiq Sajib44,955 次观看 • 1 个月前
Here’s a better way to think about AI commercial creation: Don’t generate the final ad first. Generate the decisions that make the ad possible. GPT Image 2.5 is coming to CapCut through existing tools like Design Studio and AI Image. For an iPhone Duo concept, I used it to work through the shots, compositions and visual sequence. Then CapCut PC + Seedance 2.5 turned those decisions into a commercial. The rest is refinement. It’s less “AI made an ad for me” and more “AI helped me build the ad." #GPTImage25 #CapCutPC #AIVideo #Seedance25
Mushfiq Sajib43,467 次观看 • 1 个月前
I used to think the biggest promise of AI video was making production faster. Now I’m wondering if the bigger change is making pre-production accessible to more people. You can think through a scene spatially with GPT-6 Astra, establish camera and character movement, bring that scene into CapCut PC, generate with Seedance 2.5, and then keep refining the actual sequence. That creates an interesting possibility: What if creators who never had access to a traditional production team can start thinking like directors before they ever press “generate”? AI might not just be changing how we make footage. It might be changing who gets to plan a film. #GPT6Astra #CapCutPC #AIVideo #Seedance25
Mushfiq Sajib39,060 次观看 • 1 个月前
An AI video maker scales only when post-production keeps up. CapCut Seedance 2.5 1080p is now live. Batch-create the visual system with AI Image, turn the strongest assets into scenes with AI Video, then bring them into the CapCut PC project. Use Edit Pilot when selected clips need repeated conversational changes to length, pacing, captions or transitions rather than manual clip-by-clip work. AI Edit handles targeted visual corrections, AI Extend continues unfinished scenes, and the multi-track timeline completes dialogue, music, SFX, color and final delivery. #CapCutPC #AIVideoEditor #CapCutSeedance25 #Seedance251080p
Mushfiq Sajib36,678 次观看 • 2 个月前
没有更多内容可加载