Urgent.News

600+ sources. One page. See who else covered it.

Editions

AI

You might soon be able to create Gemini Spark skills directly on your Android phone

Soon, you won't need access to a desktop to create or edit Gemini Spark skills.

You might soon be able to create Gemini Spark skills directly on your Android phone

Google's upcoming Android app for Gemini is set to revolutionize the way users manage their Gemini Spark skills, potentially streamlining the process entirely on mobile devices. According to hints found in the Google app v17.45.14 code, the new update will introduce a dedicated Skills page within the Gemini Android app. This update will feature two methods for creating skills: guided conversational setup and manual creation.

The ability to manage active, inactive, and recommended skills on mobile will eliminate the need for users to rely on desktop browsers for these tasks. Gemini Spark, Google's autonomous AI agent powered by Gemini technology, relies heavily on "Skills" to perform tasks in the background based on user preferences. While creating and managing these skills previously required a desktop connection, Google aims to bring full Skill management capabilities directly to the Gemini app on Android.

This development signifies a significant step towards simplifying the user experience for managing AI-driven tasks on mobile devices.

Written by urgent.news from Android Authority's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at androidauthority.com →

More in AI

Build a Privacy Filter Before Your AI Agent Remembers User Actions

AI agents are starting to remember more than chats. They can watch clicks, typed text, app switches, browser context, files, tool calls, and workflow history.

  • AI agents are increasingly remembering user actions like clicks and typed text.
  • Privacy filters process user activity before it becomes part of an agent's memory.

Building Roshni: A Real-Time, Multi-Agent Financial Voice AI for Bharat 🇮🇳

Building Roshni: An Ultra-Low Latency, Multi-Agent Financial Voice Assistant for Bharat 🇮🇳 How I built an end-to-end, multilingual financial voice AI using Murf Falcon, LiveKit Agents, Deepgram…

  • Roshni AI assists Indian citizens with financial queries in voice interactions.
  • Supports English, Hindi, and Hinglish languages with ultra-low latency.
  • Maintains user memories via SQLite for personalized financial advice.

A beginner's guide to the Qwen3.8-27b model by Qwen on Huggingface

This is a simplified guide to an AI model called Qwen3.8-27b maintained by Qwen . If you like these kinds of analysis, you should join AImodels.fyi or follow us on Twitter .

  • Qwen3.8-27B is a 27-billion-parameter AI model with built-in vision capabilities
  • Excels in software engineering, coding, and multimodal computer use tasks
  • Requires significant hardware resources for deployment