How to use Google’s new information agents
Google has unveiled new AI agents for Search, allowing users to create and manage personalized AI assistants that continuously monitor and synthesize information on topics of interest. These agents go beyond traditional search by offering proactive, ongoing updates and actionable insights, functioning similarly to an advanced evolution of Google Alerts.
At the 2026 Google I/O keynote, Google announced new agentic capabilities in Search, allowing users to create, customize, and manage multiple AI agents. These agents are designed to keep users updated on topics of interest continuously. This initiative is part of Google's broader strategy toward agentic AI systems that can proactively assist with ongoing tasks.
Unlike traditional search tools, Google's information agents operate 24/7 in the background without needing repeated prompts. They synthesize information from various sources, explain its relevance, compare perspectives, and offer actionable insights. This represents a significant evolution from simple notifications provided by services like Google Alerts.
For example, users can set up an agent to monitor the stock market for specific companies or economic trends, which would track activity, summarize reports, and alert users to major changes. Agents can also help with everyday tasks such as tracking flight prices, monitoring sports events, following breaking news, or keeping tabs on housing market trends.
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.