Gemini 2.5 Computer Use
Introducing the Gemini 2.5 Computer Use model, a specialized agent model built on top of Gemini 2.5 Pro’s visual reasoning capabilities, designed to interact directly with user interfaces (UIs). It is exposed via a new computer-use tool in the Gemini API, with inputs that include the user’s request, a screenshot of the UI environment, and a history of recent actions. The model generates function calls corresponding to UI actions like clicking, typing, or selecting, and may request user confirmation for higher-risk tasks. After each action is executed, a new screenshot and URL are fed back into the model to continue the loop until the task completes or is halted. It is optimized primarily for web browser control and shows promise for mobile UI interaction, though it is not yet suited for desktop OS-level control. In benchmarks across web and mobile control tasks, Gemini 2.5 Computer Use outperforms leading alternatives, delivering high accuracy at lower latency.
Learn more
II-Agent
II-Agent is an open source intelligent assistant developed by Intelligent Internet, designed to enhance productivity across various domains such as research, content creation, data analysis, coding, automation, and problem-solving. It operates through a robust function-calling paradigm, driven by a powerful large language model (LLM), specifically Anthropic's Claude 3.7 Sonnet, and is supported by advanced planning, comprehensive execution capabilities, and intelligent context management. The agent's architecture includes a central reasoning and orchestration component that interfaces directly with the LLM, utilizing system prompting, interaction history management, and intelligent context management to maintain a coherent and efficient workflow. II-Agent's capabilities encompass multistep web search, source triangulation, structured note-taking, rapid summarization, blog and article drafting, lesson plan creation, creative prose, technical manuals, website creation, etc.
Learn more
OneAdvanced AI
OneAdvanced AI is a privacy-first, enterprise AI platform designed to embed intelligence directly into business workflows to boost productivity, streamline processes, and support complex decision-making while keeping data secure and compliant. It combines a private, UK-hosted large language model with sector and role-specific AI agents that automate routine tasks such as summarizing information, generating insights, and handling domain-specific workflows tailored to industries like healthcare, legal, education, housing, social care, and wholesale logistics. It includes intelligent chat interfaces for centralized interaction, agentic AI that orchestrates multiple agents to manage intricate processes, and embedded AI that brings conversational and contextual intelligence into existing applications. OneAdvanced also emphasizes custom privacy controls and data sovereignty, ensuring sensitive information remains secure and compliant.
Learn more
Runbear
Runbear is a no-code platform that enables teams to create AI agents integrated with popular communication and productivity tools like Slack, Teams, HubSpot, and more. It allows users to build custom AI assistants quickly, typically within 10 minutes, without requiring technical expertise. Runbear helps automate repetitive tasks, streamline internal communication, and manage AI agents tailored for different teams all from a single interface. The platform supports integrations with AI models like OpenAI, Claude, and Gemini, combined with content management systems such as Google Drive, Notion, and Confluence. Use cases include automating meeting preparation, summarizing Slack threads, analyzing Airtable data through natural language, and enabling AI to suggest answers in Slack channels. Customer testimonials highlight Runbear’s ease of use and the significant efficiency gains achieved by integrating AI directly into workflows.
Learn more
