I just built a complete AI video generation system—and I'm giving away the entire thing for free. What's cool about this system is it automates the whole process. You type in a topic, and it generates a full video with voiceover, visuals, and sound effects. All the code is yours to download and customize. 👉 Watch here: https://youtu.be/QQNQc7cIbu0 Currently, it's trained to generate awesome AI Pokemon nature documentaries for Bulbasaur, Charmeleon, and Haunter! Check out the videos below! You can watch the full breakdown below! Here's what you'll learn: ✅ The complete tech stack: Kling 2.5 for video, Gemini for images, ElevenLabs for voice/SFX, and Claude Code to orchestrate everything ✅ My "Prompt Driven Development" process: How I iterate on each prompt until the output is perfect before moving to the next step ✅ The 7-step pipeline: From research to story generation to image creation to video generation to voice to sound effects to final assembly ✅ How to customize it: This isn't just for Pokemon—I'll show you how to adapt this system for any video topic you want ✅ The full source code: Everything I built, all the prompts, and the setup guide so you can run it yourself The best part? Once you understand this pattern, you can build AI video systems for any niche. Download the complete source code here: 👉 https://github.com/bhancockio/pokemon-ai-video-generator Can't wait to see what you build with this! Cheers, Brandon Hancock P.S. Want to see how you can convert this AI workflow into a real-world production application? In December, I'm dropping a brand new ShipKit template showing exactly how to transform this local video generation system into a full SaaS platform that anyone can use. If you want access to that (plus all our other production-ready templates for AI chat, AI workflows, RAG, and agents), check out ShipKit.ai—close to 300 developers are already using it.

Hi everyone 👋, I am curious if anyone used OpenAI Function Calling / tools feature? Here is a quick 5 min videos that explains it well: https://www.youtube.com/watch?v=Qor2VZoBib0 Basically the functions are normal functions in your code, you pass the unstructured input/request and your functions definitions/descriptions to the LLM, and the LLM comes back with suggestions on what functions (if any) in your own code that should be called to process the request as well as the structured arguments (!) you would pass to the functions. While AI frameworks are great for many use cases, this approach feels leaner and more transparent. In some cases, introducing a full AI framework into an existing production environment just isn’t practical — maybe your team works primarily in C#, Node.js, or PHP, and you simply want to sprinkle in some AI-driven decision-making without adding major dependencies or new infrastructure. I am curious what others think about it. Has anyone else tried using the OpenAI Functions Calling (or a similar feature from another AI provider API) on a project in production? If so, how did it work out for you in terms of reliability or performance?

Google has significantly enhanced the capabilities of its Google AI Studio, which links to a lot of its new frameworks. This is looking great, and it allows you to upload your project to GitHub once it's done. It might be suitable for a quick proof of concept or if you are getting started and want to work through ideas to apps. https://www.youtube.com/watch?v=Kb83qnQ0hQ8

I’m re-developing a sophisticated event management platform that I built using make.com & Twilio a few years ago and now trying to port it into a next.JS react tailwind typescript & Twilio stack. I have a lot of relational database experience and front-end ui/ux design experience, have led teams w/Jira, but very little JavaScript or actual webcoding experience. I’m looking for someone who is very comfortable developing in the new stack and has developed multi-repo apps? This first phase of the project will involve a lot of Twilio email and other channels designed to work together simultaneously for the same user as needed. Only one or two admin users will need to access the application UI online…all staff, guests, vendors, and other people involved in the event communicate over SMS + other channels with our app to interact/CRUD etc… A lot of intellectual property involved, the business logic, user stories and target audience are locked down. I want to work on this full-time, but I am on the verge of launching a completely different app in the music space, pulsing raising teenage son etc..so my time is limited right now. I imagine this will take a solid 2 to 3 months of part-time work to get to an MVP stage that can be shared with initial user base. Long-term (1 year? Or 2 months with ShipKit 😍) it is a three project ecosystem. This phase is just building out the communication/guest-entertainment/staff-management side which will also be the main point of entry for most users in the beginning. I’m looking for a partner for long term to put in work now for shares/equity in the application mrr profits when it launches, and I am confident this will be a very profitable and popular application when it does launch. We are breaking things (search interface, multi-agent multi-touch real-world interactions on behalf of Admin, text and voice AI flows to please, tease and um…make it eeees ier to get a LOT of really impt shit done in background & keep guests entertained upfront all without any apps required) on large scale, dinosaurs will fall and smaller mammals will chase.

There is excellent video content in the original language, and I am wondering if there is a process to convert to a different language while considering the cultural differences and generate suitable content?