You can now talk to your Gmail inbox, as seen at Google IO 2026
Google has unveiled "Gmail Live," a new conversational AI feature for Gmail that allows users to ask natural language questions to find information within their inboxes. This feature, powered by Gemini AI, aims to make finding specific details like flight information or appointment times much easier than traditional keyword searches.
Google has introduced "Gmail Live," a new conversational AI feature powered by Gemini AI, allowing users to interact with their Gmail inbox using natural language. This advancement, showcased at Google I/O 2026, aims to simplify the process of finding specific information without relying on keyword searches. Users can now ask questions about flight details, appointments, or event information, and Gmail Live will retrieve the relevant emails.
Before Gmail Live, users had to employ specific keywords or email addresses to search their inboxes, a method that often proved inefficient, especially when searching for broad terms. The new feature is designed to understand naturally phrased questions, respond to follow-up inquiries, and even adapt if the user interrupts.
Devanshi Bhandari, product lead for Gmail, demonstrated Gmail Live by asking about a child's school projects and travel plans. The AI successfully grasped nuanced requests and extracted granular details like hotel room numbers, even when not explicitly mentioned. This capability highlights Google's commitment to integrating practical AI solutions into its widely used products.
Gmail Live is an augmentation, not a replacement, for the traditional search function. This approach reflects Google's learning from past experiences, such as the backlash against an AI-only search in Google Photos, which was later made optional. The voice-powered Gmail Live will initially be available later this summer for Google AI Ultra subscribers.
In addition to Gmail Live, Google is enhancing Gmail with other features, including ready-to-send drafts, instant file access, and improved task management. The broader AI Inbox experience, which provides an overview of tasks and items in the inbox, will also expand to Google AI Pro and Plus subscribers.
Related articles
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
CUGA, IBM's open-source Agent Harness, simplifies building agentic applications by handling infrastructure, allowing developers to focus on tools and prompts. It offers pre-assembled components for planning, execution, and state management, significantly reducing development time. CUGA has topped agent benchmarks like AppWorld and WebArena.
OpenAI launches new initiative to help find and patch open source bugs
OpenAI has launched "Patch the Planet," a new initiative in partnership with cybersecurity firm Trail of Bits, to enhance the security of open-source projects. This program aims to assist maintainers in identifying and patching bugs, utilizing OpenAI's AI-powered security tools while reducing the burden on project teams.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
Baidu has released PP-OCRv6, an advanced optical character recognition (OCR) model supporting 50 languages. Available on Hugging Face, this version significantly improves accuracy and efficiency across various parameter sizes, from 1.5 million to 34.5 million, marking a substantial leap in multilingual OCR technology.
