New Google Slides Update is INSANE! 🤯
Google Slides now features Gemini AI that generates complete presentations from a single prompt by analyzing your existing files like Docs, Sheets, and PDFs. Unlike previous AI slide tools, the generated decks are fully editable and available to Business Standard/Plus and Enterprise users, with expanded usage limits through August 2026.
Summary
Google announced on June 30th a significant update to Google Slides integrating Gemini AI, with rollout beginning June 29th. This represents a major leap from previous AI capabilities that only helped with individual slide elements like bullet points or font suggestions. The new feature allows users to input a single prompt and receive an entire presentation including title slides, agendas, content slides, charts, and closing slides—all ready to edit immediately.
A key differentiator is that Gemini doesn't generate content from thin air. Instead, it analyzes a user's actual existing files including Google Docs, Sheets, PDFs, old presentations, emails, and chats to build contextually relevant presentations. This approach contrasts sharply with older AI slide tools that would guess at content. The speaker uses an analogy comparing it to allowing someone to walk through your house before describing it, versus asking a stranger to describe it without seeing it.
Every element Gemini creates is fully editable—text boxes, shapes, and charts are normal Google Slides objects that users can modify exactly as if they built them manually. The workflow is straightforward: users open Slides, click the Gemini icon, type their request, answer clarifying questions about tone and audience, approve an outline, and Gemini builds the complete deck while flagging additional relevant files from the user's drive. Users can also instruct Gemini to match the style of previous presentations.
The feature is currently available to Business Standard and Plus users, Enterprise Standard and Plus users, Google AI Pro, Google AI Ultra, and Education add-on subscribers. Through August 1st, 2026, these eligible plans include significantly higher usage limits. The speaker demonstrates two practical applications: creating an explainer deck about the AI Profit Boardroom community from coaching notes in under a minute, and building a proposal presentation from member results documentation. After generation, users can continue refining through conversational prompts like "Make this shorter" or "Use more images," allowing rapid iteration rather than starting over.
The speaker acknowledges limitations: Gemini may occasionally misrepresent facts or misjudge tone, requiring users to verify and adjust content. The feature is positioned as a tool to eliminate blank-page paralysis rather than replace human judgment entirely.
Key Insights
- Gemini analyzes users' existing files including Docs, Sheets, PDFs, old presentations, emails, and chats to build presentations from actual context rather than generating content from thin air
- Every slide element Gemini creates is fully editable as normal Google Slides objects, not flattened images or locked templates, allowing users to modify them exactly as if built manually
- The feature is available to Business Standard/Plus, Enterprise Standard/Plus, Google AI Pro, Google AI Ultra, and Education users, with significantly expanded usage limits through August 1st, 2026
- Users can iterate on generated decks through conversational prompts in a side panel, making targeted changes like 'Make this shorter' or 'Use more images' without starting over
- The AI tool generates complete, ready-to-send presentations in under a minute from source documents, eliminating the need for manual formatting and slide-by-slide construction
Topics
Transcript
[0:00] New Google Slides update is insane, and I mean that. Google just changed how presentations get made. And if you've ever sat there staring at a blank slide, this one's for you. Here's what happened. Google Slides now has a version of Gemini that doesn't just help you write one slide at a time. You type one prompt, and it builds you a whole deck. Title slide, agenda, content slides, charts, a closing slide all in one go. Not a rough draft, not a template you have to gut and rebuild, a real working presentation you can open right now and start editing. Let's back [0:30] up for a second because I want you to feel how big this…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Hermes Agent OS Makes AI Agents 10X Better
Julian Goldie presents Hermes Agent OS, a three-layer system architecture that transforms AI agents from one-time tools into persistent, context-aware systems. The system combines a brain (agent model), mission control (unified dashboard), and memory layer (Obsidian-based vault) to enable agents that retain context, automate workflows, and improve continuously.
This NEW AI AGENT is INSANE! 🤯
Macron V1 is a new open-source AI agent featuring four specialized experts that automatically switch between planning, coding, and generative UI capabilities. The system maintains 2 million tokens of context and performs competitively with leading closed-source AI models on major benchmarks.
NEW Qwythos-27B-v1 is INSANE!
Emperor AI released QwenchOS 27B, a 27-billion parameter open-source AI model that can process over 1 million words of context, understands images and screenshots, and runs on personal computers for free. The model represents a significant democratization of AI capabilities previously only available from major tech companies, featuring innovations like multi-token prediction for faster responses and an Apache 2.0 license enabling commercial use.
Agent OS Q&A: Setup, Loops + New AI Models
A Q&A session covering the Agent OS—a modular AI automation system where users can plug in various AI models and tools. The speaker demonstrates setup processes, discusses token optimization techniques, explains looping features in Claude Code, and addresses community questions about integrating multiple AI agents without overwhelming complexity.
Claude AI SEO Gets Me 2,680 Clicks a Day
The speaker demonstrates how to generate 2,680 clicks per day using an AI-powered SEO system that leverages social media content ranking on Google. The strategy involves using Google Search Console data to identify target keywords, then creating automated video content across multiple platforms to rank multiple times for the same keyword.