BugNature @BugNature1

"Context Engineering for Multi-Agent Systems: Move beyond prompting to build a Context Engine, a transparent architecture of context and reasoning" — at amzn.to/448dSiA v/ @PacktDataML 𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷: 🔵Develop memory models to retain short-term and cross-session context 🟣Craft semantic blueprints and drive multi-agent orchestration with MCP 🟠Implement high-fidelity RAG pipelines with verifiable citations 🟡Apply safeguards against prompt injection and data poisoning 🔵Enforce moderation and policy-driven control in AI workflows 🟣Repurpose the Context Engine across legal, marketing, and beyond 🟠Deploy a scalable, observable Context Engine in production

Agent Skills 设计哲学和实战进化 前半段是真实场景演示，看我日常怎么用 Agent + Skills 完成实际工作；后半段是设计哲学和迭代方法论，把踩过的坑和悟出来的经验都讲透。 四个核心观点： 1）从提示词到 Skills：起步没有门槛。把你已有的好用提示词、好的实践、甚至模糊的想法，直接用 /skill-creator 变成 Skill。关键是动手。 2）别做万能 Skill：Skill 要原子化，每个只做一件事。然后用 Skill 或者 AGENTS.md 编排成工作流，让 Agent 灵活执行。我的素材收集和写作流程就是这么串起来的。 3）Skills 像随身小刀，越用越顺手：自己常用、遇到问题当场改、给 Agent 高质量对比样例让它自己优化、用 git 做版本管理留后悔药。 4）站在 Agent 角度设计：多存中间文件、先分析再执行、写清验证标准、用子 Agent 并行、脚本优先于 MCP。这些小细节决定 Skill 能不能真正跑通。 baoyu-skills 已全部开源：github.com/JimLiu/baoyu-s…

宝玉 @dotey

3 months ago

感谢大家支持，从第一次发布 baoyu-skills ，到现在 2 个多月时间已经 10K+ stars 了。 skills.sh 上的数据： 193.7K total installs，当前最受欢迎的 skill 排名在 170 github.com/jimliu/baoyu-s…

keyboard_arrow_left Previous keyboard_arrow_right Next

65 171 1K 350K 1K

"Python in Excel Step-by-Step" by @DaveOnData Get it here: amzn.to/3URAwqx #DataScience #DataAnalysis #DataScientist #DataAnalyst

🐍📺 Simulating Real-World Processes in Python With SimPy [Video] —realpython.com/courses/simula… #python

Essential Python Libraries!

MCP vs. Skills for AI agents, clearly explained! People treat MCP and Skills like they're the same thing. They're not. Conflating them is one of the most common mistakes I see when people start building AI agents seriously. So let's break both down from scratch. Before MCP existed, connecting an AI model to an external tool meant writing custom integration code every single time. 10 models, 100 tools? That's 1,000 unique connectors to build and maintain. The AI tooling ecosystem was a tangled mess of one-off glue code. MCP (Model Context Protocol) fixes this with a shared communication standard. Every tool becomes a "server" that exposes what it can do. Every AI agent becomes a "client" that knows how to ask. They talk through structured JSON messages over a clean, well-defined interface. Build a GitHub MCP server once, and it works with Claude, ChatGPT, Cursor, or any other agent that speaks MCP. That's the core value: write the integration once, use it everywhere. But here's where most explanations stop short. MCP solves the *connection* problem. It does not solve the *usage* problem. You can hand an agent 50 perfectly wired MCP tools and it'll still underperform if it doesn't know when to call which tool, in what order, and with what context. That's the gap Skills fill. A Skill is a portable bundle of procedural knowledge. Think of a SKILL. md file that tells an agent not just "here are your tools" but "here's how to use them for this specific task." A writing skill bundles tone guidelines and output templates. A code review skill bundles patterns to check and rules to follow. MCP gives the agent hands. Skills give it muscle memory. Together, they form the full capability stack for a production AI agent: - MCP handles tool connectivity (the wiring layer) - Skills handle task execution (the knowledge layer) - The agent orchestrates both using its context and reasoning This is why advanced agent setups increasingly ship both: MCP servers for integrations and SKILL. md files for domain expertise. If you're building with agents, I have shared a repository of 85k+ skills that you can use with any agent, link in the next tweet!

Turn complex PDFs into LLM-ready data with agentic document extraction! Traditional OCR tools extract text but lose critical information. Structure, order, and context are lost. This is the gap between pulling text and understanding documents. Documents come in different formats across industries. Invoices, contracts, forms, bills, receipts - each has unique layouts. Manual extraction doesn't scale when you need to process hundreds of documents with different formats. LandingAI's Agentic Document Extraction (ADE) solves this with a vision-first approach that preserves layout and context. Here's how it works in practice: the utility bills workflow for financial services. In KYC and onboarding, utility bills are common proof-of-address documents. But they come from hundreds of providers with different formats. The workflow uses a two-step process: 1. Parse - Converts PDFs or images into structured markdown with chunk metadata and bounding boxes. Preserves visual layout and context. 2. Extract - Applies a JSON schema to pull specific fields with field-level metadata and chunk references. You define fields to extract in a JSON schema: provider info, account details, billing summary, charges. The workflow processes batches from any provider and outputs structured JSON + CSV with grounding coordinates showing exactly where each field came from. This same approach works across any document type: invoices, insurance forms, tax documents, contracts, receipts, medical records. Define your schema once, process documents at scale. What you get: • Markdown extraction with grounding coordinates • Structured JSON matching your custom schema • Field-level metadata linking fields to source chunks Preserving visual context makes document processing scalable. Link to the workflow in the comments!

Git

Awesome ad

Data Profiling — Having that First Date with your Data: medium.com/codex/data-pro… —————— #BI #Analytics #DataScience #MachineLearning #Statistics #DataAnalytics #DataLiteracy #DataViz #VisualAnalytics #DataStorytelling #DataScientist #ExploratoryDataAnalysis

Grok is solid

Mario Nawfal @MarioNawfal

6 months ago

GROK ACES PSYCHOLOGICAL TESTING WHILE OTHER AI MODELS SPIRAL University of Luxembourg researchers just put major AI chatbots through 4 weeks of actual psychotherapy sessions and psychiatric diagnostic tests. While other models imploded, Grok emerged as the clear winner. The

958 1K 8K 13.1M 3K

Instead of switching between 10 tools and platforms to stay relevant, you can get it all in one app, ChatGPT. And as OpenAI turns into a supergiant, we'll start to see more expanded capabilities and learning pathways through this powerful AI tool, all in one window. forbes.com/sites/rachelwe…

NEW RELEASE coming soon from @PacktDataML. Get book price guarantee from Amazon here: amzn.to/4njfsVM ⬇️↓⬇️↓⬇️ "Learn Model Context Protocol with Python: Build agentic systems in Python with the new standard for AI capabilities", by @chris_noring

We believe it's important to give people the ability to fix things themselves if they prefer to do so You can find service manuals for all of our cars, buy parts, access info on diagnostic tools & more via service.tesla.com

Branden Flasch @brandenflasch

8 months ago

I don't think many people appreciate how awesome it is that @Tesla publishes all their service manuals online for free

78 128 2K 2.7M 128

This is pure AI made by Grok

This tool lets you create your python GUIs like Canva, Using Drag and Drop. Outputs clean editable python code.

Dask – Parallel Data Processing

50 #Algorithms Every Programmer Should Know: amzn.to/3Mi1hAk via @PacktDataML ————— #DataScientist #DataScience #Coding #Mathematics #MachineLearning #Statistics #ComputerScience #AI #Cryptography #ComputationalScience

Best LLM Courses- mltut.com/best-large-lan… @KirkDBorne @antgrasso @ronald_vanloon #MachineLearning #deeplearning #BigData #Datascience #ML #HealthTech #DataVisualization #ArtificialInteligence #SoftwareEngineering #GenAI #deeplearning #ChatGPT #OpenAI #python #AI #keras #SQL #Statistics #AgenticAI #AIAgent

推荐阅读：《AI 会取代人类思考吗？我们为什么仍要亲手写作和编程》 作者：Simon Späti 重新学习思考，警惕对 AI 的依赖。 每天关于 AI 的（吹捧的或无聊的）文章层出不穷。用它没问题，大家也都在用，但我们仍然需要打磨自己的手艺，并努力去思考。 就像 DHH（David Heinemeier Hansson，Ruby on Rails 框架创始人）所说： 精通某项技能比一直等着 AI 完成任务要有趣得多。 在我看来，AI 让我们不快乐的概率非常高。用，当然可以，但不能事事都用。我们可以用它来探索新知、梳理历史脉络，或者制作图表（比如用 Canva、Figma），但绝对不能用它来写作（或编程）。世界总需要有人贡献新的知识和见解，而 AI 无法自我训练。因此，文章、书籍和文字仍将被创作，当人人都依赖 AI，导致其发展停滞时，作家的价值反而会更加凸显。 从长远来看，这是一种损失——人们将停止思考和学习。时间会证明一切。我的浅见是，如果你在某个领域已是资深专家，你会比 AI 更懂。 Bsky 何时使用 AI 的指南 我从 ThePrimeagen 的一个视频中听到一个观点：这取决于你决策的影响有多长远。短期内，用 AI 自动补全代码没问题，但让它做架构设计这样重大的决策，绝对不行。 Image 这张图的横轴是时间，纵轴是错误数量。它表明，我们让 AI 参与的决策越是影响深远（比如系统架构），它产生的错误就可能越多。 如果我们用它来快速补全代码，或者写一个定义清晰的算法函数，那么出错的概率就小。在初始阶段，你可能会提升 20% 的效率；但到了后期，你失去的会更多。 这就像现实生活中，我等待决策的时间越长，掌握的信息就越多，做出的决定就越好。这正是 Shape Up 工作法所倡导的，决策周期最长为 6 周，不制定更长远的路线图和积压任务。使用 AI 也是同理，因为它的所有输出都是基于概率预测的。 Forrest Brazeal 的另一张图也很有启发性： Image 同时，也要牢记什么对你的应用场景最重要，正如 Thomas Ptacek 在《我的那些 AI 怀疑论朋友都疯了》一文中所展示的： Image 毫无灵魂 没人想读毫无灵魂的文字，即使它写得还不错，你又能从中得到什么呢？我认为这是一个巨大的陷阱，人们只有在时间流逝后才会意识到。当然，AI 能提供帮助，每个人在“某些”任务上都需要它们，但不应是写作本身。 归根结底，大语言模型 (LLM) 和 AI 需要引导，它们只是概率的产物。另见 亲手写作。 分心 我认为我们将比以往任何时候都更容易分心。我们甚至没有两秒钟的思考时间，Grammarly、Copilot 或 Cursor 就会跳出建议。于是，我们不再独立思考，只是随波逐流，渐渐失去了主导权。 这让我想起最近写的一篇文章《寻找心流》。更多关于“不要事事依赖 AI，否则你会停止思考和学习”的讨论，请见 AI 的使用 和 写作之难。 别误会 别误会，我自己也每天都用 AI，但用得更审慎。我关掉了 Grammarly 和 Copilot（很久以前就关了），这样我才有空间去思考和学习。偶尔用一两次没问题，但如果处处都用，你不仅会失去学习新技能的机会，也会失去其中的乐趣。 关于“人机协作智能”（LLM Collaborative Intelligence, LCI）的讨论很有趣。当然，它会带来很多好处，但我不确定这些 AI 产生的“洞见”能否与人类历经艰辛后感受、感知或体验到的洞见相提并论。所以，是的，我对此没有太多期望，也不希望它来创造新的见解。因为那是我工作中真正有趣的部分 :) 锻炼一项技能 事情永远不是“全有”或“全无”，而是在于度的把握。学习的问题在于，如果你频繁使用 AI，我认为你其实学不到太多东西。写作时只是复制粘贴，编程时只是不停地按 Tab 键。学习的过程消失了。如果这种情况持续下去，我们的大脑就不再习惯于学习，更严重的是，不再习惯于思考。就像记忆一样，我们现在还能记住几个手机号码？很少了。但在早期用电话的时代，我能记住很多，因为我每天都在训练这个能力。 这完全是一个熟能生巧的问题。我为自己总结出——虽然不一定适用于每个人——我发现自己不再学习或思考了。坦白说，也失去了乐趣。这主要是在我熟悉的领域。 在其他领域，比如创作一张图片（就像我为这篇文章做的那张 😆），或者用 HTML/CSS 更新我网站的首页，这些事因为不常做，AI 帮我省了很多时间。但我得说，除了学会了如何给 Claude Code 写提示词，我并没学到任何新东西。这始终是一种权衡，不是吗？:)

keyboard_arrow_left Previous keyboard_arrow_right Next