Gemini ahora CREA archivos por ti: PDFs, Excel, Word, Presentaciones y más
Google has updated Gemini to create downloadable files directly from chat, including PDFs, Word documents, spreadsheets, CSV files, and presentations, while also integrating with Google Drive. Though powerful, the feature is still in beta with notable limitations like duplicating files instead of editing originals and inconsistent PowerPoint support.
Summary
The video demonstrates a significant Gemini update that allows users to generate downloadable files—including PDFs, Word documents, Excel spreadsheets, CSV files, Google Slides presentations, and Markdown files—directly from the chat interface. The host argues this breaks down a previously confining barrier where Gemini could only respond in text, forcing users to manually transfer information into their own documents and workflows.
The host walks through several practical examples: generating a Google Docs research report on AI-powered business ideas, converting that report into a Google Slides presentation, uploading invoices to create an organized Excel expense tracker, and using data from a Drive spreadsheet to generate a detailed PDF with pie and bar charts and spending recommendations. A Markdown file creation example is also shown for use in external tools like Cloud Code.
In a stress test, the host asks Gemini to simultaneously generate 10 files in different formats—PDF, Word, Excel, PowerPoint, Markdown, JSON, SQL, and code files—which Gemini successfully produces with a summary of each file's contents. Some code formats downloaded as TXT files for security reasons, requiring a manual extension change.
Despite the capability, the host highlights several current limitations: Gemini sometimes fails to generate PDFs from Google Sheets without switching to Pro mode, it tends to duplicate documents instead of editing existing ones when asked to make changes, and it cannot always deliver a downloadable PowerPoint file directly, instead offering a workaround via VBA code. The host concludes that while the feature is still in beta and imperfect, it signals Google's broader vision of making Gemini an intelligence layer across the entire Google Workspace ecosystem.
Key Insights
- The host argues that Gemini's file creation update is more significant than it appears because it breaks down a core limitation: previously Gemini was confined to the chat, requiring users to manually copy and transfer information into documents, spreadsheets, or presentations themselves.
- The host demonstrates that Gemini can locate an existing file in Google Drive, analyze its contents, and use that data to generate a new file—in this case finding an expense spreadsheet and producing a PDF with charts and spending recommendations—showing cross-file intelligence within the ecosystem.
- In a batch generation test, Gemini successfully created 10 files simultaneously across very different formats—PDF, Word, Excel, PowerPoint, Markdown, JSON, Python, and JavaScript—and provided a summary of each file's contents directly in the chat.
- The host identifies a key current flaw: when asked to edit an existing Google Doc, Gemini does not modify the original file but instead creates a duplicate document with the change applied, which significantly limits the editing experience.
- When pushed to deliver a downloadable PowerPoint file, Gemini told the host it could not send one directly and instead offered a workaround—generating a visual presentation within Gemini and providing VBA code to copy into PowerPoint—which the host acknowledges is not equivalent to native file delivery.
Topics
Transcript
[0:00] Google has just taken a significant step with Gemini, and pay attention to this because Gemini can now create downloadable files directly from the chat, including PDFs, Word documents, spreadsheets, CSV files, presentations, and even create documents and sheets directly within Google Drive. At first glance, it might seem like a small update, like, "Okay, now it exports files," but I really think this is much more important than it appears because [0:31] it starts to break down a barrier that Gemini has had until now. Until now, Gemini felt very confined within the chat itself. You'd ask it something, it would answer, maybe it would help you draft, research, or summarize, but then you had to manually take…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Migue Baena IA
Cómo aprender por tu cuenta y volverte imparable con IA
This tutorial demonstrates how to use Gemini Notebook (formerly Notebook LM) to self-teach any skill by curating personal learning sources and converting them into multiple study formats. The four-step process involves selecting quality materials, studying them through different media, teaching the content to others, and integrating learning into daily routines.
Tienes que probar esto antes de crear tus videos con IA 🎬
A new AI video creation tool called 3D Builder within Topw Film Studio allows creators to pre-visualize and plan movie scenes by building interactive 3D environments, positioning characters and objects, controlling camera movements, and reviewing animations before final video generation.
No elijas entre Claude y Codex: úsalos juntos 🤝🏻
The video proposes using Claude and Codex together rather than choosing one over the other to maximize their respective strengths. Claude handles problem analysis and task delegation while Codex executes code generation, allowing users to work around individual API rate limits and leverage complementary capabilities.
Cómo usar Claude mejor que el 99% de la gente
A comprehensive guide to using Claude AI effectively, covering account setup with context import, model selection and reasoning levels, proper prompting techniques, projects and skills for organizing work, and advanced features like Cowork for delegated tasks and Code for building applications.
El archivo de GitHub que deberías de conocer 👀
Anthropic has published a detailed GitHub repository containing a 275,000+ character PRD with nearly 8,000 lines of instructions for one of their models, including specifications on what to do, avoid, and how to use tools. The key value lies not in copying the content but in studying its structure and learning how it organizes rules and defines tool usage for prompt engineering applications.