Technology & Development - React 获得了一种与 agents 交互的原生方式 [1] - 构建 agentic UIs 仍然非常困难 [1] - 需要将 agent 的输出流式传输到前端 [1] - 需要保持状态 [1]

Industry Trends - The industry is converging towards three open protocols that work across all frameworks for solving complex tasks [1] - The focus is shifting from selecting the "best" framework to utilizing protocols that offer interoperability [1] Frameworks & Tools - LangGraph, CrewAI, and Agno are mentioned as relevant frameworks or tools in the field [1]

We’re releasing a new LangChain Academy course, LangGraph Essentials, where you can learn the basics of LangGraph in less than an hour. LangGraph is a low-level orchestration framework designed specifically for building AI agents. It provides a durable runtime for agents with graph-based execution.LangGraph allows you to create flexible, agentic workflows with its modular components. It allows you to control execution, manage state, allow for human intervention when needed, and scale reliably. LangGraph add ...

Product & Solution - Pedi offers an enterprise-grade AI-powered incident management solution to help organizations transform critical operations [1] - The AI agent assists teams in understanding incidents through chat platforms like Slack or MS Teams, eliminating the need to navigate dashboards [2] - Langraph structures the AI agent with memory, decision-making, and fallbacks, parsing questions and devising plans to find answers [3] - Langraph provides full control over the agent's behavior, enabling debugging, error handling, and output analysis [4] Benefits & Impact - The AI agent saves engineers hours per week and reduces context switching [6] - Internal use of the AI agent provides learnings and a framework for developing more AI agents for customers [6] - Engineers use it for retrospectives, product managers use it to understand service stability, and executives use it to ask about incident and service health metrics [5] Technology & Architecture - Langraph helps maintain context throughout conversations, facilitating faster insights from incidents [3] - Langraph is flexible, open, well-documented, and integrates with Langchain and other observability tools [7] - Langraph enables the building of reliable and thoughtful AI agents that involve reasoning, data access, or coordination between steps [6][7]

Business Impact - Prosper Marketplace cut costs in its verification use case by over 90% using Langraph [9] - The cost per verification decreased from tens of dollars to cents [9] - The company moved from reviewing a sample of calls monthly to reviewing 100% of calls within minutes [10] Technological Implementation - Prosper Marketplace uses Langraph to automate QA verification process for customer calls [2] - The company needed a solution with complete ownership and control over data and deployment due to strict data compliance requirements [5] - Langraph's checkpoint system and interrupts simplified development, enabling focused optimizations and human-in-the-loop workflows [6][7] - Langraph allows quick adaptation and reuse of agents across different use cases, saving engineering time [10] Langraph Advantages - Langraph's checkpoint system makes development easier by allowing focused optimizations [6] - Interrupts facilitate building collaborative co-pilot style agents with natural language feedback [7][8] - Langchain team provides templates and examples to quickly get started with complex agents [11]

[Music] I'm Isis Julian and I'm a senior software engineer at Morning Star and I work on the intelligence engine. Morning Star is a global leader in providing investment research data and analysis and we pride ourselves in empowering investor success by serving transparent, accessible, and reliable investment information. So, with AI gaining increasing popularity nearing the end of 2022 and early 2023, with a scrappy team of just five engineers, we were able to launch our first ever AI research assistant na ...

Company Overview - 11X is building digital workers, including Alice, an AI SDR, and Julian, an AI voice agent [1] - The company relocated from London to San Francisco and rebuilt its core product, Alice, from the ground up [2] Alice Rebuild & Vision - The rebuild of Alice was driven by the belief that agents are the future [3] - The new vision for Alice centers on seven agentic capabilities, including chat-based interaction, knowledge base training via document uploads, AI-driven lead sourcing, deep lead research, personalized emails, automatic handling of inbound messages, and self-learning [11][12][13] Development Process & Tech Stack - The rebuild of Alice 2 took only 3 months from the first commit to migrating the last business customer [3][14] - The company chose a vanilla tech stack and leveraged vendors like Langchain to move quickly [15][16][17] - Langchain was chosen as a key partner due to its AI dev tools, agent framework, cloud hosting, observability, Typescript support, and customer support [18][19] Agent Architecture Evolution - The company experimented with three different architectures for campaign creation: React, workflow, and multi-agent systems [21] - The final architecture was a multi-agent system with a supervisor and specialized sub-agents for research, positioning, LinkedIn messaging, and email writing [44][45][46] Results & Future Plans - Alice 2 went live in January and has sourced close to 2 million leads and sent close to 3 million messages [52] - Alice 2 has generated about 21,000 replies, with a reply rate of around 2%, on par with a human SDR [52] - Future plans include integrating Alice and Julian, implementing self-learning, and exploring new technologies like computer use, memory, and reinforcement learning [53][54]

Agent Adoption & Scalability - LinkedIn aims to scale agentic adoption within the organization to enable broader idea generation [2] - LinkedIn built the Hiring Assistant, its first production agent, to automate recruiter tasks and free up time for candidate interaction [3] - The Hiring Assistant follows an ambient agent pattern, operating in the background and notifying recruiters upon completion [4][5] - LinkedIn adopted a supervisor multi-agent architecture, with a supervisor agent coordinating sub-agents that interact with LinkedIn services [6] Technology Stack & Framework - LinkedIn standardized on Python for GenAI development, moving away from its traditional Java-centric approach [7][8] - The company built a service framework using Python, gRPC, Langchain, and Langraph to streamline the creation of production-ready Python services [9][19] - Over 20 teams have used this framework to create over 30 services supporting Generative AI product experiences [9][10] - Langchain and Langraph were chosen for their ease of use and sensible interfaces, enabling rapid development and integration with internal infrastructure [22][23] Infrastructure & Architecture - LinkedIn invested in a distributed architecture to support agentic communication modes [10] - The company modeled long-running asynchronous flows as a messaging problem, leveraging its existing messaging service for agent-to-agent and user-to-agent communication [26][27] - LinkedIn developed agentic memory with scoped and layered memory types (working, long-term, collective) [29][30] - LinkedIn implemented a centralized skill registry, allowing agents to discover and access skills developed by different teams [34][35]

[Music] I'm Paul Rasgitis and I'm the tech lead for AI products at Modern Treasury. Modern Treasury is the payment operations platform built for the instant economy. At Modern Treasury, our goal is to transform how teams track and move money.Recently, we launched Modern Treasury AI, a horizontal platform that includes chat, task management, monitoring, and an AI agent designed specifically for financial operations. The agent is just one part of this broader experience, but it plays a key role in how users i ...

AI Developer Tool Strategy at Uber - Uber's AI developer tool strategy focuses on products that directly improve developer workflow, such as writing tests and reviewing code [6] - The strategy emphasizes building crosscutting primitives, foundational AI technologies applicable across multiple solutions [7] - Intentional tech transfer is a cornerstone, identifying and spinning out reusable components to reduce barriers for future problem-solving [8][9] Key Products and Their Impact - Validator, an IDE experience, flags best practices violations and security issues, resulting in thousands of fixed interactions daily [11][16] - Autocover, a test generation tool, leverages domain expert agents and has increased developer platform coverage by approximately 10%, saving an estimated 21,000 developer hours [17][27][28] - Uber has built an internal custom GPT store where you can build chatbots that are steeped in Uber knowledge [29] Technical Learnings - Building super capable domain expert agents yields outsized results due to better context utilization and reduced hallucination [34] - Composing agents with deterministic sub-agents, like the lint agent in Validator, ensures reliable output [36] - Scaling development efforts is achieved by creating and reusing agents across multiple applications, such as the build system agent [37] Strategic Learnings - Encapsulation through well-defined abstractions like Langraph boosts collaboration and allows for horizontal scaling of development [39] - Graphs model interactions effectively, mirroring developer workflows and improving both AI and non-AI experiences [41]