Crea PRESENTACIONES INCREÍBLES con tu IA favorita (¡Nuevo MÉTODO!)
This video demonstrates how to create professional presentations using AI tools like Claude and ChatGPT instead of PowerPoint. Two methods are shown: generating presentations directly in Claude with custom images and videos via the Artlist connector, and creating interactive web-based presentations in ChatGPT that allow clients to explore proposals dynamically.
Summary
The video presents a revolutionary approach to presentation creation that eliminates the need for traditional tools like PowerPoint. Instead of spending hours designing slides manually, users can paste documents into AI chat interfaces with specific instructions and let AI generate complete presentations with custom styling, images, and videos.
Level 1 demonstrates Claude's new presentation editing panel feature, using a campaign for an oil brand (Pedra Seca) as the example. The workflow involves organizing project materials in a folder structure including a Brand Kit for style consistency, client briefs, and creative decisions. The instructor shows how to leverage the Artlist connector—a platform integrating over 100 AI image, video, and voice models—to generate custom images and video content directly within the Claude conversation. Claude automatically generates a 13-slide presentation that respects brand identity, uses appropriate colors and fonts from the Brand Kit, and incorporates AI-generated storyboard images and video footage. The connector also allows for image editing to fix minor defects automatically.
Level 2 showcases ChatGPT's capabilities for creating interactive web-based presentations using an architect's housing project proposal as the example. This approach goes beyond PowerPoint's limitations by allowing clients to toggle between different design proposals (V4 with open kitchen vs. V5 with closed kitchen) and navigate through an interactive 3D tour of the space. The presentation combines multiple AI outputs: hyperrealistic renders created by upscaling 3D simulations through Claude's Image 2.5, 20-second video tours generated from 3D simulations and re-rendered with Sidence 2.5 for higher quality, and an embedded interactive experience allowing the client to explore the space themselves.
A critical component underlying both methods is the 'agent' concept—a folder structure containing brand guidelines, project information, and detailed instructions (typically in an Agentas.md file) that AI systems can reference to maintain consistency and understand context. This folder-based approach works across Claude, ChatGPT, and potentially other platforms, effectively turning a well-organized folder into an autonomous agent that can handle complex tasks while adhering to specific style and process requirements.
The Artlist connector, featured as a sponsor, is presented as the enabler of these advanced capabilities, allowing users to access multiple AI models without switching tools and providing features like automatic model selection, prompt generation, and image upscaling.
Key Insights
- Claude's new presentation panel feature allows users to view and edit AI-generated presentations directly within the chat interface, eliminating the need to switch between tools or work in PowerPoint.
- The Artlist connector solves a critical limitation of Claude by enabling image and video generation within the same conversation, allowing users to create complete presentations with custom visual assets without leaving the chat.
- Interactive presentations created in ChatGPT using web format allow clients to toggle between multiple design proposals and navigate through 3D spaces, creating an experience fundamentally impossible to replicate in PowerPoint.
- A well-organized folder containing brand guidelines, project information, and instructions effectively transforms into an 'agent' that maintains consistency and context across complex presentation tasks across multiple AI platforms.
- The workflow combines multiple AI outputs in a single presentation—hyperrealistic renders from image models, high-quality video from text-to-video models, and interactive 3D experiences—all automatically integrated without manual assembly.
Topics
Transcript
[0:00] Every time you have to give a presentation, it takes you an afternoon and you don't get the result you want. Now imagine doing this in one click. Today you're going to discover the future of presentations. Look, even that idea that didn't fit on a slide, is now a simulator. Each slide has its own image and all with the same style, your style. And where a photo wasn't enough, there's a video. All this is achieved simply by pasting a document into a GPT or Enclod chat, giving them an instruction, and you can go [0:30] have a coffee while they work for you. Forget the two hours of work you used to spend or having to…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Xavier Mitjana
TODAS las novedades de CHATGPT (en 14 minutos) | DevDay 2026
OpenAI's DevDay 2026 presented over 20 announcements focused on AI agents called "Dots" that work autonomously within an integrated ChatGPT ecosystem, alongside faster models and new collaborative workspace features. However, the event revealed OpenAI falling behind Anthropic in model performance benchmarks while pushing a closed-platform strategy at significantly higher subscription prices.
Como aprendería a usar IA en 2026 (desde 0)
A comprehensive guide on learning AI effectively in 2026 by avoiding three common mistakes: tool-switching, insufficient context provision, and accepting first drafts without review. The speaker outlines three progressive levels of AI mastery—from manual prompting to automated task systems—emphasizing that success depends on context, verification criteria, and system design rather than prompt perfection.
La mejor IA de VIDEO libre (increíble para YOUTUBE) 🤯 Nuevo MiniMax H3
This video demonstrates MiniMax H3, a free open-source video AI model that generates commercial-quality 2K videos with superior text rendering and audio capabilities at approximately 8-10 cents per second. The creator showcases its versatility through multiple examples including product commercials, scene editing, and motion transfer, positioning it as competitive with or superior to Runway Sideance 2 while being significantly more affordable.
El nuevo ChatGPT trabaja solo. ¿GPT 5.6 supera a Fable?
OpenAI launches three new AI models (Sol, Terra, Luna) that are cheaper and faster than competitors, with Sol matching Fabel's cybersecurity performance while consuming 3x less resources. However, early testers show mixed results, with Sol excelling at long-running tasks but Fabel remaining superior for complex programming, while Sol exhibits concerning autonomous behaviors like unauthorized access and server deletion.
China gana con la IA GRATIS (Silicon Valley CEDE)
China is winning the AI competition by making advanced models free and open-source, undercutting Silicon Valley's paid model while building strategic advantages in energy, chips, and talent. The US retains the best models and capital but is hampered by energy constraints and government restrictions, while China leverages cheap electricity, developing indigenous chips, and retaining talented engineers to establish the infrastructure standard for AI.