[Music] Thanks Alex for the introduction. That was a very impressive LLM generated summary of me. Uh I've never heard it before but uh nice.Um so um today I'm going to talk to you about something that has been keeping me up at night. Uh probably some of you too. So how to build enterprise aware agents.How to bring the brilliance of AI into the messy complex realities of uh how your business operated. So let's jump straight to the hottest question of the month for AI builders. Uh should I build workflows or ...

AG-UI Protocol Overview - AG-UI protocol has become the standard for building front-end Agentic apps where Agents are part of the interface [1] - AG-UI defines a common interface between Agents and the UI layer, remaining Agent framework agnostic [2] Key Features of AG-UI - AG-UI enables streaming token-level updates, showing tool progress in real time, sharing mutable state, and pausing for human input [2] - Developers can spin up a full-stack AG-UI app directly from CLI and visualize A2A interactions [2] - Pydantic AI is now AG-UI compatible [2] Development Efficiency - Building AG-UI frontends is now 10x faster with a plug-and-play interface [1][2] - A fully revamped contributor flow is available for developers [2] Agent Connectivity - MCP connects agents to tools, A2A connects agents to other agents, and AG-UI connects agents to users [2]

Agentic Apps Development - AG-UI protocol simplifies front-end Agentic app development, making it 10x easier [1] - AG-UI is becoming the standard for apps where Agents are part of the interface [1] Agent Communication Protocols - MCP connects agents to tools [1] - A2A connects agents to other agents [1]

Building front-end Agentic apps just got 10x easier (open-source)!If you're building apps where Agents are part of the interface, not just running in the background, AG-UI protocol has become the standard.For context:- MCP connects agents to tools- A2A connects agents to other agents- AG-UI connects agents to usersIt defines a common interface between Agents and the UI layer.AG-UI itself is Agent framework agnostic, and it lets you:- stream token-level updates- show tool progress in real time- share mutable ...

Summary of Conference Call Industry Overview - The conference focused on the U.S. AI industry and stock market changes, highlighting significant movements by major companies like NVIDIA and Microsoft [1][2] - The discussion emphasized the evolving landscape of AI, particularly the introduction of next-generation Internet concepts such as Agents Network and Agent Web [2][10] Key Companies and Developments NVIDIA - NVIDIA's NVLink Fusion product was a major highlight, showcasing advancements in AI chip architecture and model training capabilities [3][4] - NVLink has evolved from version 1.0 in 2016 to version 5.0, enhancing interconnectivity between different computing units [3] - The company is adapting to customer needs by offering customized solutions for AI and IoT applications, indicating a shift towards more tailored products [4][5] - NVIDIA's partnerships with companies like Boton and Marvell are expanding its market reach, particularly in customized chip solutions [5][6] - The anticipated launch of larger AI clusters (up to 500,000 cards) for model training is expected by the end of the third quarter [9] Microsoft - Microsoft's Build conference emphasized the concept of Agents as a core focus, with a shift towards a more integrated Internet experience [10][11] - The company is primarily targeting B2B markets, but its progress in AI model development is perceived as average compared to competitors like Google [11][12] - Microsoft’s token generation in the last quarter was about 1 million tokens, significantly lower than Google's performance [11] Google - Google’s IoT conference was noted for its comprehensive approach to AI, with a focus on its Gemini model and various cloud-based products [12][14] - The company is leading in AI commercialization, with a monthly token processing capacity significantly higher than Microsoft’s [15][17] - Google’s AI strategy includes a robust framework for developers and a strong emphasis on integrating AI into its existing products [14][15] OpenAI - OpenAI's acquisition of the design company IOU for $6.5 billion aims to enhance its hardware product offerings, indicating a strategic move towards the next generation of Internet [18][20] - The focus on hardware development is seen as crucial for maintaining competitive advantage in the evolving AI landscape [21][22] Additional Insights - The conference highlighted the competitive dynamics between major players in the AI space, with NVIDIA, Google, and OpenAI positioned as leaders [15][20] - The discussion also touched on the importance of product design and innovation, particularly in the context of hardware development in Silicon Valley [22] - Future trends in AI are expected to revolve around the integration of agents and the development of platforms that unify various AI applications [31] Conclusion - The AI industry is rapidly evolving, with significant advancements in technology and strategic partnerships among leading companies. The focus on customized solutions and the integration of AI into various sectors will likely shape the future landscape of the industry [31]

Consumer Software Industry Concerns - Consumer software CEOs are worried about agents taking over, leading to a paradigm shift away from web pages [1] - The rise of agents could make the traditional browser obsolete, reducing it to a glorified markup reader [6] Perplexity's Strategic Opportunities - Perplexity has the potential to replace Bloomberg in the financial information and data sector, a market worth $100 billion [4][5] - Focusing on a specific vertical and owning it is a good strategy for Perplexity, especially with unique data sources [10] Apple's Potential Acquisition of Perplexity - There is speculation that Apple might acquire or partner with Perplexity for distribution, given the Justice Department case against Google [9] - However, acquiring Perplexity may not solve Apple's AI challenges, as Apple has missed previous AI opportunities [10] Bloomberg's Weaknesses - Bloomberg's terminal is considered atrocious, terrible, and limited, presenting an opportunity for a better product [4] - Bloomberg's core usability and UI have not evolved, despite its messaging platform being valuable for trading [14]

Key Features of Stagehand - Bridges the gap between brittle traditional automation tools like Playwright and Selenium, and unpredictable full-agent solutions like OpenAI Operator [1][3] - Employs AI for navigating unfamiliar pages and code (Playwright) for executing known tasks [3] - Allows previewing AI actions before execution [3] - Caches repeatable actions to conserve tokens [3] - Compatible with SOTA computer use models with minimal code [3] - Available in both Python and TypeScript SDK [3] Stagehand Ecosystem - Includes an open-source MCP server [2] - Aims to provide a browser automation framework for Agents suitable for production environments [1]

RT Avi Chawla (@_avichawla)6 no-code LLMs, Agents, and RAG builder tools for AI engineers:(open-source and production-grade) ...

6 no-code LLMs, Agents, and RAG builder tools for AI engineers:(open-source and production-grade) ...

MCP Overview & Architecture - MCP (Micro Control Plane) is defined as a pluggable architecture for agents, contextualized within an enterprise cloud service [5][6] - Sentry's MCP server was initially built as a fun project and is biased towards Sentry's application monitoring services [4][5] - The industry views MCP as a potential solution for integrating services into various agents, enabling bug fixes and workflow enhancements within editors [7][8][25] Implementation & Challenges - Implementing MCP involves complexities around OAUTH 21%, requiring solutions like Cloudflare Shim for proxying OAUTH 2 API [16][17] - A key challenge is that MCP cannot simply sit on top of Open API; systems need to be designed around how agents and models react to provided context [19][20][21] - Current client support for native authentication is still evolving, with some clients like Cursor experiencing breakage [22] Security & Best Practices - Security is a major concern, particularly with the standard IO interface, and random MCP tools should not be allowed within organizations [27] - For B2B SaaS companies, focusing on OAUTH with remote environments is crucial for integrating services into agents [25] - Companies should avoid simply proxying Open API and exposing it as tools, as this yields poor results; intentional design and context provision are necessary [30] Agent-Centric Approach - The industry should focus on building agents, viewing MCP as a plug-in architecture to leverage the value of LLMs [39][40] - Exposing agents through the MCP architecture, particularly in B2B settings, is seen as a significant value unlock [42] - Optimizing for context in workflows and understanding data is crucial when designing agents, with a focus on providing structured information like Markdown for language models [31][50]