agent Archives

Winsage

December 4, 2025

I get why some people are suddenly freaking out about AI agents in Windows 11 – I’m worried, too, but let’s not panic just yet

Windows 11 has updated its documentation regarding AI agents, specifically the 'Experimental Agentic Features' introduced in October 2025. The recent update coincided with the rollout of experimental features in preview version 26220.7262, including the Copilot Actions agent, which helps users manage files. Concerns have been raised about potential attack vectors related to these AI systems, but Microsoft claims to have built defenses against such threats. The AI agents operate within a separate 'agent workspace,' isolating them from the user's primary account to limit file access and reduce exploitation risks. Despite these measures, there are lingering uncertainties about the reliability and security of the AI agents, especially in light of past challenges with similar features.

Winsage

December 4, 2025

Announcing the Microsoft Store Awards 2025 winners

The Microsoft Store Awards recognized exceptional applications that enhance user experiences within the Windows ecosystem. AI Assistants category: - Winner: Perplexity by Perplexity AI - Features native voice dictation, multi-modal AI search, and deep desktop integration for rapid research. - Winner: ChatGPT by OpenAI - Provides instant answers, direct image and file uploads, and enterprise-level privacy controls. Business category: - Winner: Invoice Maker & Estimate Creator by Moon Technolabs Pvt. Ltd. - Streamlines finance tasks with customizable templates and real-time payment tracking. Computer-Using Agents (CUA) category: - Winner: Manus by Manus AI - Automates complex tasks within a secure sandbox and allows users to guide ongoing actions. Creativity category: - Winner: n-Track Studio by n-Track S.r.I. - Transforms devices into recording studios with support for unlimited tracks and advanced effects. Developer Tools category: - Winner: ngrok by ngrok - Facilitates secure tunneling and remote access with automatic updates and compatibility with Windows Defender. Education category: - Winner: Scratch 3 by Scratch Foundation - Empowers students in computational thinking through engaging projects and block coding. Game category: - Winner: Castle Craft by Clever Apps Pte Ltd - Offers an immersive gaming experience with dynamic resource merging and family-friendly design. Music category: - Winner: Moises Live by Moises Systems, Inc - Leverages real-time AI audio separation technology for remixing and practice. Productivity category: - Winner: Notion by Notion Labs Inc - Consolidates tasks and notes into a searchable workspace with automation features. Each winner will receive a Store Award Winner badge in the Microsoft Store.

Winsage

December 1, 2025

Microsoft confirms that its new AI agent in Windows 11 hallucinates like every other chatbot and poses security risks to users

Microsoft has introduced agentic AI capabilities for Windows 11 through the 26220.7262 update, aligning with the trend of using large language models to enhance user experiences. The company has warned about potential risks associated with these new features, including the possibility of "hallucinations" and "novel security risks," specifically highlighting a vulnerability known as cross-prompt injection (XPIA). This flaw could allow malicious content to override agent instructions, leading to unintended actions like data exfiltration or malware installation. Microsoft’s move to integrate these AI features reflects a response to competitive pressures in the tech industry, despite the known flaws and security vulnerabilities associated with them.

Winsage

December 1, 2025

As Windows 11 turns into an AI OS, Microsoft Copilot boss does not understand how AI is underwhelming

Mustafa Suleyman, Microsoft's AI CEO, noted user frustration with the aggressive integration of AI into Windows 11, despite the company's efforts to enhance user experience with features like Copilot, which operates on models similar to ChatGPT. Windows 11 includes various AI functionalities, such as Copilot Voice and Copilot Vision, and aims to transform the OS into an "agentic OS" with features like Copilot Actions in Microsoft Edge. Users have expressed dissatisfaction with AI being present in applications like Notepad and File Explorer, perceiving it as intrusive rather than beneficial. Microsoft 365 applications have also integrated Copilot functionalities, but concerns about safety and privacy persist. User feedback indicates a desire for more thoughtful AI integration, as many feel that AI is being applied to problems that do not exist, leading to stress and uncertainty regarding the operating system's control.

Winsage

December 1, 2025

Microsoft Warns: Windows 11 Agentic Features May Hallucinate

Windows 11 will introduce "Experimental agentic features" with the installation of Build 26220.7262, which users must manually enable. These features are in an experimental phase and may affect device performance. Microsoft warns of potential security vulnerabilities, particularly from emerging attack techniques like cross-prompt injection, which can lead to harmful commands being executed. The agents operate within an "Agentic Workspace" with scoped, auditable accounts, but unlike Windows Sandbox, they persist across sessions, increasing the attack surface. By default, agents have read and write access to common folders, which presents additional vulnerabilities. Microsoft is working on improving security measures, including more granular permissions and defenses against prompt injection.

Winsage

December 1, 2025

Windows 11 trials AgentWorkspace agent amid privacy fears

Microsoft Corp is testing a new feature called AgentWorkspace on Windows 11, aimed at creating an “agentic operating system” where AI operates autonomously on behalf of the user. The tool allows AI agents to open applications, read files, organize documents, and navigate the interface, enhancing automated workflows. However, it raises privacy concerns due to the extensive permissions required, including access to sensitive directories like Desktop, Documents, Downloads, Pictures, and Videos. Microsoft claims the AI operates in a controlled space with strict logging and limitations, but critics highlight the reliance on user consent for access to private data.

Winsage

December 1, 2025

Microsoft says AI agents are “risky”, but it’s moving ahead with the plan on Windows 11

Microsoft is integrating AI agents into Windows 11, despite acknowledging risks such as hallucinations, unpredictable behavior, and vulnerabilities to cyber threats like Cross Prompt Injection (XPIA). The company plans to transform every Windows 11 PC into an AI-powered machine by introducing features like Copilot Voice, Copilot Vision, and Copilot Actions. The Windows 11 taskbar will feature a new "Ask Copilot" interface for users to interact with AI agents. These agents will operate under separate accounts with limited permissions, controlled folder access, and tamper-evident logs, but still have access to personal folders like Documents and Downloads. The Agent Workspace is a key feature that allows AI agents to perform tasks in a controlled environment, separate from the user's session. Agents can interact with applications and execute multi-step tasks while being monitored. Microsoft employs the Model Context Protocol (MCP) to regulate agent interactions with applications, ensuring security and proper permissions. Despite concerns over privacy and security, Microsoft believes that integrating AI is essential for keeping Windows competitive. The company has faced backlash over previous features like Recall, which raised privacy issues, and must work to rebuild trust with users. The experimental AI features are currently optional, and Microsoft aims to demonstrate their value to encourage acceptance.

AppWizard

November 30, 2025

Signal’s president warns AI agents are an existential threat to secure messaging apps

Meredith Whittaker, president of Signal, expresses strong concerns about the rise of AI agents, describing them as an “existential threat” to secure messaging platforms and app developers. AI agents require access to sensitive information, creating new vulnerabilities that can be exploited by cybercriminals. Whittaker points out the risk of prompt injection attacks, which can manipulate AI to execute harmful actions, leading to data breaches. She argues that unrestricted access to user communications by AI agents poses a significant risk to privacy and security, undermining the foundational security of the internet. Whittaker criticizes the reckless implementation of AI by Big Tech companies, suggesting it compromises cybersecurity in favor of rapid deployment and financial pressures.

Winsage

November 30, 2025

Microsoft Issues Warning To Windows 11 Users – This AI Feature Can Install Viruses

Microsoft is transitioning to Windows 11 with the introduction of an "agentic OS," featuring experimental components called Agent Workspace, currently available to select Windows Insiders. These agentic features will be disabled by default due to potential security risks, including cross-prompt injection (XPIA) that could allow unauthorized access to user files. When activated, agent accounts can access the user profile directory, which raises concerns about data exfiltration and malware installation. The AI applications, including Copilot, will have visibility into the entire display, prompting users to consider privacy implications. Agent workspaces are designed to provide scoped authorization and runtime isolation, allowing users to manage access to files while using their devices. However, initial user reactions have been mixed, with ongoing concerns about security and functionality.

Tech Optimizer

November 27, 2025

How Letta builds production-ready AI agents with Amazon Aurora PostgreSQL

AI agents benefit from persistent memory, enabling them to recall past interactions and maintain context, which enhances customer experience in scenarios like customer service. The Letta Developer Platform allows developers to create stateful agents with advanced context management features. It supports self-hosting within a virtual private cloud and uses Amazon Aurora PostgreSQL for long-term memory storage. Aurora PostgreSQL offers capabilities such as efficient similarity searches with the pgvector extension, sub-second query latency, and dynamic storage scaling. Letta operates as a persistent service, allowing agents to function independently and scale horizontally using Kubernetes. The platform supports multi-tenancy and includes enterprise features for security and monitoring. To set up an Aurora Serverless cluster for Letta, users must create a database on Amazon RDS, configure security group access, and install the pgvector extension. Letta connects to Aurora using a PostgreSQL connection string. After establishing the connection, users can create agents, send messages, and view agent states and conversation histories stored in Aurora. Letta organizes data in 42 tables, including those for agents, messages, and memory blocks. Users can explore the database schema and examine the structure of stored messages and embeddings. Finally, it is recommended to delete the Aurora cluster and associated resources after completing the integration to avoid charges.