GenFlow 2.0
GenFlow 2.0 is a next-generation AI agent system powered by Baidu Wenku’s proprietary Multi-Agent Parallel Architecture, orchestrating over 100 AI agents in parallel to reduce complex task processing from hours to under three minutes. It offers full transparency and user control throughout execution. Users can pause tasks at any stage, modify instructions on the fly, and edit intermediate results, ensuring human-AI collaboration remains dynamic and precise. To enhance reliability and accuracy, GenFlow 2.0 autonomously accesses vast knowledge bases, including Baidu Scholar’s 680 million peer-reviewed publications, Baidu Wenku’s 1.4 billion professional documents, and user-approved Netdisk files, leveraging retrieval-augmented generation and multi-agent cross-validation to minimize hallucinations. The platform supports a wide array of multimodal outputs, ranging from copywriting and visual design to slide generation, research reports, animations, and code.
Learn more
Waveloom
Waveloom is a developer platform that enables the visual construction and deployment of AI workflows, integrating services like GPT-4, Claude, and DALL-E without the need for infrastructure coding. Its drag-and-drop interface allows users to create complex AI workflows, connecting various services and transforming data seamlessly. Waveloom provides a unified SDK to access multiple AI models, including Claude 3.5, GPT-4, Gemini, Llama, DALL-E, Lora, Flux, Stable Diffusion, and Whisper, handling the underlying infrastructure to let developers focus on building applications. The platform offers real-time monitoring, enabling users to observe workflow execution, debug issues, optimize performance, and manage costs from a single dashboard. With a single function call, developers can run diverse processes, such as AI prompts and image generation, facilitating the creation of AI processing tasks involving large language models, image and video processing, voice synthesis, data storage, etc.
Learn more
Project Mariner
Project Mariner is a research prototype developed by Google DeepMind, built upon their advanced AI model, Gemini 2.0. It explores the future of human-agent interaction by automating tasks within a user's browser. Leveraging multimodal understanding, Project Mariner comprehends and reasons across various browser elements, including text, code, images, and forms. This enables it to navigate complex websites, automate repetitive tasks, and provide visual feedback to users. The system can interpret voice instructions and offers updates on task progress, ensuring users remain informed and in control. Additionally, Project Mariner can follow complex instructions by breaking them down into actionable steps, understanding relationships between web elements, and providing clear plans and actions to users. Currently, Project Mariner is in the testing phase with a select group of trusted users. Those interested in participating can join the waitlist for future testing opportunities.
Learn more
11.ai
11.ai is a voice-first AI assistant built on ElevenLabs Conversational AI that connects your voice to everyday workflows via the Model Context Protocol (MCP), enabling hands-free planning, research, project management, and team communication. By integrating out of the box with tools such as Perplexity for live web research, Linear for issue tracking, Slack for messaging, and Notion for knowledge management, and supporting custom MCP servers, 11.ai can interpret sequential voice commands, contextualize data, and take meaningful actions. It delivers real-time, low-latency interactions with multimodal support (voice and text), integrated retrieval-augmented generation, automatic language detection for seamless multilingual conversations, and enterprise-grade security (including HIPAA compliance).
Learn more