How to use Google’s new AI agents to go beyond your standard searches
Google is launching new AI agents within Search, moving beyond traditional single-query responses. These agents will continuously monitor interests, synthesize information, and provide actionable insights, acting as an evolution of Google Alerts. The feature will be available this summer, initially for Google AI Pro and Ultra subscribers in the U.S.
At Google I/O 2026, Google unveiled new "agentic" capabilities in Search, allowing users to create and manage multiple AI agents. These agents move beyond answering single questions, instead assisting with ongoing tasks. This initiative reflects Google’s broader strategy toward agentic AI systems that can take initiative and operate continuously.
Unlike traditional search tools, Google’s AI agents work 24/7 in the background, keeping users informed without the need for repeated searches. They synthesize information from various sources, explain relevance, compare perspectives, and offer actionable insights. This represents a significant evolution from Google Alerts, offering more than just simple notifications.
For example, users tracking the stock market can set up an agent to monitor specific companies, share prices, or economic trends. The agent can then track market activity, summarize earnings reports, and alert users to major changes. Similarly, agents can assist with everyday tasks like tracking flight prices, monitoring sports events or news, and staying updated on housing or job market trends.
To use this feature, users access AI Mode in Search and enter a prompt, such as "Keep me updated on movie tickets for 'The Mandalorian and Grogu.'" The Google app will then send push notifications for relevant updates. Users can manage, refine, or disable these alerts within their AI Mode history.
Information agents will be rolled out this summer, initially for Google AI Pro and Ultra subscribers in the U.S. before expanding to other markets.
Alongside these agents, Google also introduced a revamped Search interface, featuring an "intelligent search box." This change, the most significant in over 25 years, is designed for longer, more conversational queries and includes an AI-powered query suggestion system for nuanced searches.
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.
