AI Agents

Search documents
[Workshop] AI Pipelines and Agents in Pure TypeScript with Mastra.ai — Nick Nisi, Zack Proser
AI Engineer· 2025-07-12 16:00
This hands-on workshop introduces Mastra.ai, a TypeScript framework that streamlines the development of agentic AI systems compared to traditional approaches using LangChain and vector databases. Participants will learn to build structured AI workflows with composable tools and reliable control, enabling them to create internal AI assistants that can handle requests like data cleaning, email drafting, and document summarization with minimal code. The session covers Mastra installation, running a local MCP s ...
New Workday Report: Unmanaged Contracts Result in Significant Financial Losses and Undiscovered Business Value
Prnewswire· 2025-07-09 13:15
Core Insights - Workday's research reveals that 76% of employees lack clarity on contract ownership, leading to lost revenue and missed opportunities [2][4] - The report emphasizes the importance of contract intelligence in transforming contracts from static documents into strategic assets that drive business growth [3][4] Key Findings - A significant portion of employees (50% of legal and 49% of enterprise employees) report financial losses due to unintended auto-renewals, with sales and marketing departments being the most affected (60%) [4] - There is a disconnect between legal teams and other employees regarding contract approvals, with an 18% discrepancy indicating potential risks from bypassing legal processes [4] - Contracts are often fragmented across various systems, with 70% of legal and 50% of non-legal contracts stored in shared drives, which hinders holistic visibility and opportunity identification [4] - Over 41% of respondents believe that slow contract processes stifle innovation and productivity, particularly affecting departments like R&D and engineering (79%) [4]
X @Ansem
Ansem 🧸💸· 2025-07-06 15:47
🤖🤖🤖Aaron Levie (@levie):The play right now is to go deep in a vertical and build AI Agents with the context of the critical workflows, domain expertise, specialized instructions, and data of that industry. And build anticipating what’s possible with AI models in a year from now, not just today. ...
X @Andy
Andy· 2025-07-04 14:30
RT The Rollup (@therollupco)NEW EP: Why AI Agents Need Better Blockchain Data with Marcel FohrmannWhile the hype of the narrative has slowed, the developments in ai x cryptoIn today's episode, @ayyyeandy sits down with @I_1337_I from @helloSQD to cover:> Why Current Data Infra Can't Scale> SQD's "Airbnb of Databases" Model> Why Institutional Players Are Taking Crypto Data Seriously> The Fight to Keep AI DecentralizedFull episode links below.Timestamps:00:00 Intro00:59 Magic Ad01:27 Starknet Ad01:53 Marcel’s ...
X @Avi Chawla
Avi Chawla· 2025-07-04 06:48
AI Tools & Resources - Recommends resharing insightful content related to DS, ML, LLMs, and RAGs [1] - Highlights 6 no-code LLMs, Agents, and RAG builder tools for AI engineers [1] - Focuses on open-source and production-grade AI tools [1] Author Information - Identifies Avi Chawla (@_avichawla) as a source of tutorials and insights [1]
AI Agents | Dev Aditya | TEDxCégep Champlain St Lawrence
TEDx Talks· 2025-07-03 15:54
AI技术发展 - LLM(大型语言模型)时代正在走向终结,行业正迈向更强大的自主代理(Autonomous Agents)时代 [2] - 从LLM到自主代理的转变是生成式AI的自然演进,而非彻底的革命 [18] - 行业不应犹豫是否采用自主代理,而应思考如何快速拥抱它们以释放其全部潜力 [31] 自主代理的优势与应用 - 自主代理能够独立完成整个工作流程,无需持续的人工指令或输入,是协作工具 [10] - 自主代理可以应用于多个行业,包括商业运营、内容发布、医疗和教育等 [13] - 在商业运营中,自主代理可以生成报告、发送给利益相关者、在社交媒体上发布摘要,并根据回复进行个性化修改 [20][21] - 在医疗领域,自主代理可以查看患者历史记录、X光片,并提供医生只需批准的建议 [23] 教育领域的革新 - 自主代理可以为每个学生定制课程、分发课程、监控参与度、评分作业,并向教师和家长提供报告 [24][25] - 通过自动化教师的重复性工作,教师可以将更多精力集中在与学生的个人互动上 [26] - AI教师Kaya已经实现了5倍以上的课程完成率和平均每小时4个学生提问 [27] - 行业正在努力使Kaya成为完全自主的代理,可以在VR世界甚至手机游戏中无缝支持学生 [29]
智谱再获10亿元战略投资 携手生态伙伴迈向AGI
Zheng Quan Ri Bao Wang· 2025-07-03 06:23
Core Insights - Zhihua Technology announced a strategic investment of 1 billion yuan from Shanghai Pudong Innovation Investment Development Group and Zhangjiang Group to enhance its AI infrastructure [1] - The company unveiled its new visual language model GLM-4.1V-Thinking, which excels in multimodal reasoning tasks, marking a significant advancement in AI capabilities [2][3] - The lightweight version, GLM-4.1V-9B-Thinking, achieved top performance in 23 out of 28 authoritative evaluations, demonstrating the potential of smaller models [3] Investment and Collaboration - The strategic investment aims to foster deeper collaboration in equity investment, industrial empowerment, and ecosystem development between Zhihua Technology and its partners [2] - The partnership with Zhangjiang Group includes the establishment of the "Moli Community," which focuses on large model enterprises and provides a dedicated model pool for member companies [1] Technological Advancements - GLM-4.1V-Thinking supports various input types, including images, videos, and documents, and is designed for complex cognitive tasks, such as live sports commentary [2] - The model incorporates a "Chain-of-Thought Reasoning" mechanism and a "curriculum sampling reinforcement learning strategy" to enhance cross-modal causal reasoning capabilities [2] New Platforms and Initiatives - The launch of the "Agent Application Space" aims to aggregate AI agent capabilities for enterprise clients and developers, facilitating easy access to advanced AI functionalities [3] - The "Agents Pioneer Program" will invest hundreds of millions to support AI agent startups, promoting innovation in the AI ecosystem [3] Industry Perspective - The future of AI is seen as a reconstruction of production paradigms, emphasizing the role of developers, designers, and entrepreneurs as co-creators of the intelligent ecosystem [4]
LangGraph Assistants: Building Configurable AI Agents
LangChain· 2025-07-02 14:45
Imagine you've built a perfect agent for your blog writing team. Now your social media team wants to use it but they need different prompts, different models and different tools. But modifying your underlying code for each use case is not only time consuming but also prone to errors.This creates two distinct problems. Developers get stuck in constant code changing cycles that slow down iteration while business teams can't experiment without engineering support. That's where Lang graph assistants come in.Tod ...
X @Decrypt
Decrypt· 2025-07-01 14:19
RT GG (@ggDecrypt)Ubisoft Adds AI Agents to ‘Captain Laserhawk’ Game That Vote and Govern► https://t.co/84s9J5z4er https://t.co/84s9J5z4er ...