Tag
Hark previews Hark Handoff, a browser-use agent that can complete tasks like shopping and booking reservations by navigating websites without APIs, with claims of being faster and cheaper than rivals.
Gemini Spark can now use Google Chrome's auto browse feature to handle complex online errands, such as scheduling apartment viewings and researching flight options with user permission.
A benchmark of three AI agents on 12 multi-app tasks shows Kimi K3 tied the most expensive model GPT-5.6 Sol at a fraction of the cost, though all three failed cross-app reconcile tasks, highlighting the need for verification in production.
Sam Altman completed a complex weekend outing planning task with a single command via ChatGPT, including using chat history, generating plans, building a full-stack coordination website, booking, and drafting an email.
The article discusses efforts to build AI systems that can automate tedious and undesirable work tasks, freeing humans for more meaningful work.
Mechanly is a new Android-first tool that allows users to create personal apps and background tasks using the phone's browser sessions, notifications, and scheduling capabilities, inspired by OpenClaw.
Google's Gemini Intelligence features are rolling out to Samsung foldable devices, including task automation for over 40 apps.
Google announced three updates at Galaxy Unpacked 2026: expanded Gemini Intelligence task automation across 40+ apps, the Gemini Notebook app preinstalled on new Samsung foldables, and other AI-powered features for productivity.
OpenManus is a free open-source alternative to Manus, built by MetaGPT researchers in 3 hours, enabling end-to-end task execution via terminal with web browsing, tool use, and LLM support.
Anthropic announces that its Claude Cowork AI agent can now run tasks on mobile devices without requiring an active desktop session, enabling users to schedule and execute tasks overnight or away from their laptops.
OpenOPC is an open-source framework for building AI-native companies, featuring self-built, self-run, and self-grown capabilities for multi-agent collaboration and organizational memory.
A full-time SWE built an AI assistant that works via iMessage/SMS, activating a private AWS server per user to perform tasks like building apps, making websites, and planning vacations. It's free for testing.
Meituan's GN06 team officially launched AI browser Tabbit 1.0, which integrates multiple top large language models, supports automatic execution of complex tasks across software and web pages, and adds a memory function.
Tencent launches WorkBuddy, an AI agent that autonomously completes complex tasks instead of just answering questions, with a demo showing parallel agent execution.
Describes an AI tool that automates multi-tool workflows and executes tasks, waiting for user approval, instead of just providing instructions.
The author integrated an AI employee into Slack that autonomously executed and completed a weekly task, showcasing its high capability.
Introduces Teach VLM, a model that extracts step-by-step operational knowledge from mobile screen demonstrations, and the Teach-and-Repeat paradigm that uses this knowledge to guide GUI agents, achieving state-of-the-art performance on a new benchmark.
Most companies mistakenly automate tasks rather than decisions, missing out on significant ROI. By automating decisions that require human judgment, such as lead scoring and support triage, companies can save hours of senior time daily.
Kimi launched a new AI office product, Kimi Work, which inherits the capabilities of Kimi Code and Kimi Agent, enabling up to 300 agents to collaborate simultaneously on tasks, aiming to provide workers with a command-line-free automated office experience.
Arena Agent Mode enables autonomous AI agents to complete real-world tasks.