NEW Google AI Super Gems Update is INSANE!
Google has integrated its Opal visual workflow builder directly into Gemini as 'Supergems,' allowing users to build multi-step AI workflows using plain English with no coding required. The update consolidates what previously required multiple separate tools into a single platform. As of December 2025, the feature is rolling out first to US users via the 'Gems from Labs' section in the Gemini Gems manager.
Summary
The video introduces Google's Supergems update, framing it as a significant evolution of the existing Gems feature inside Gemini. The presenter begins by explaining what Gems originally were: custom AI personas built inside Gemini with a name, behavioral instructions, and optionally uploaded files. These allowed users to avoid re-prompting from scratch each session, functioning like saved AI experts for tasks like writing, coding, or coaching.
The core of the update involves Google integrating a tool called Opal — previously a separate, limited-access experiment inside Google Labs — directly into Gemini. Opal is described as a visual, natural language workflow builder that lets users construct multi-step AI workflows by simply describing what they want in plain English. Unlike a standard Gemini prompt that returns a single answer, Opal chains multiple prompts, model calls, and tools together so each step's output feeds into the next, creating reusable automated systems.
The presenter walks through how Supergems work in practice: users open the workflow builder inside the Gems manager, type a description of the desired workflow, and Gemini auto-generates the steps, system prompts, and a visual flowchart layout. Users can edit each component in real time, test it immediately in a preview mode, and publish it via a shareable link for team use. An advanced option redirects to the full Opal builder at opal.google.com for deeper configuration. Notably, existing Opal workflows automatically migrated into the Gems from Labs section without any manual transfer.
The presenter highlights that this consolidation eliminates the need to juggle separate tools like Zapier, Make.com, and Gemini simultaneously, reducing context-switching and centralizing the build, run, and share process within a single platform. Opal also handles hosting, so no server setup is required.
Practical use cases discussed include content creation pipelines (topic → research → draft → social captions), team onboarding guides, and structured research briefs. The presenter notes that the feature is still experimental, with a staged rollout beginning in the US in December 2025, and cautions that it will continue to evolve. The broader strategic point made is that Google appears to be consolidating all its experimental AI features — Opal, Notebook LM, and others — into Gemini as a unified AI workspace.
Key Insights
- The presenter explains that Supergems are the result of Google taking Opal — a previously separate, limited-access visual workflow builder from Google Labs — and embedding it directly inside Gemini as of December 2025, making multi-step workflow creation accessible without coding or API setup.
- The presenter describes how Opal's chaining mechanism works: rather than returning a single answer like a standard prompt, it links multiple prompts, model calls, and tools so that each step's output becomes the next step's input, enabling genuinely automated multi-stage processes.
- The presenter argues that the key practical shift Supergems represents is moving from AI as a single-answer tool to AI as a system builder — workflows are designed once, reused indefinitely, and can be shared with a team via a simple link without complex permissions.
- The presenter notes that existing Opal workflows automatically migrated into the new Gems from Labs section inside Gemini without any manual transfer required, and that Opal handles hosting so users do not need to set up servers to deploy their mini apps.
- The presenter characterizes Google's broader strategy as gradually pulling all experimental AI features — including Opal and Notebook LM — into Gemini to make it a single central AI workspace for chat, research, building, and automation, replacing the need for a stack of separate tools.
Topics
Transcript
[0:00] New Google AI Supergems update is insane. You're spending hours every week doing the same tasks over and over, writing prompts from scratch every single time, switching between five different tools to get one thing done, and wondering why AI still feels so manual. Here's what's changing everything. Google just dropped something that most people haven't even heard about yet. And by the end of this video, you'll know exactly how to use it. Hey, I'm the digital avatar of Julian Goldie. I help people learn AI tools and build smarter workflows. And today we're breaking down Google's Supergems update because this one is actually a big deal. Let's start from [0:31] the beginning so this all makes sense.…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Google AI Studio Just Got A Huge Security Upgrade
Google is reportedly developing a new "Security Check" mode for AI Studio that would apply secure coding practices to AI-generated applications. The feature aims to automate security verification during app development, addressing common vulnerabilities like exposed keys, weak authentication, and data access issues before deployment.
New Gemini Skills Update Is WILD!
Google has launched Gemini Skills, a new feature allowing users to save custom instructions once and reuse them repeatedly by typing a slash command, replacing the discontinued Gems feature. Skills can include reference files, be combined together, and are built on an open file format (skill.md) that allows portability across different AI tools.
NEW Codex CLI Update Is ABSURD!
OpenAI's new Codex CLI update transforms terminal-based programming assistance by enabling multiple AI agents to work simultaneously on different tasks, visible in a full-screen control center interface. The update includes features like Agent View, work trees, voice control, and parallel task execution, fundamentally changing how AI assistance operates from sequential Q&A to autonomous team-based work management.
NEW Hermes Cloud + Agent OS is Crazy! 🤯
Hermes Cloud combined with Agent OS enables users to deploy AI agents in the cloud 24/7 using free models without API keys or local setup complexity. The system provides persistent memory, sandbox isolation, and integration with custom workflows like content research, competitor analysis, and news monitoring.
Manus 2.0 Just Changed AI Agents Forever
Manas 2.0 represents a fundamental architectural overhaul that enables users to create games, websites, videos, and automations through simple text requests, with the key innovation being editable components rather than fixed outputs. The platform uses a new Cascade engine that reduces token usage by 23% and improves task speed by 28%, while maintaining all project elements in one connected workspace.