The AI Insider . YouTuber . Blogs . Latest Tech

Je vous conseille de bouffer du matt pocock matin midi et soir. Je pense legit que c'est le meilleur architecte IA actuel. Ses skills sont excellents, ses vidéos sont excellentes tout ce qu'il fait est EXCELLENT. ZERO SLOP dans mes projets mes repos sont cleeaannnnnnn github.com/mattpocock/ski…

A candidate interviewing for an L5 role at Google gets asked: “How would you design a web crawler that keeps 5 billion pages fresh?” And says, “I will add more crawler workers and increase throughput.” Another candidate gets the same question and walks through crawl budget, URL frontier, page-change frequency, politeness limits, conditional fetches, deduplication, and index freshness. One sounds like they know crawling. The other sounds like they understand search infrastructure. Same question. Same 45 minutes. Very different understanding of system design. Hence, different results in interviews.

As an AI Agent Engineer. Please learn: * Tool/function calling design * Agent planning / workflow orchestration * Memory / context management * State machines / multi-step execution * Retry / fallback / recovery logic * Agent evals / reliability testing * Cost / latency optimization * Human-in-the-loop patterns Most agent failures are orchestration failures, not model failures.

6 LLM Knowledge Base terms you need to know in 2026: (Most teams are missing at least 3, their AI agents pay the price) 𝟭. 𝗟𝗟𝗠 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗕𝗮𝘀𝗲 A system where an LLM ingests your raw content, compiles a structured wiki, and answers questions by navigating its own index. Karpathy built one for himself. The hard part? Building one that works for your entire team. 𝟮. 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗜𝗻𝗴𝗲𝘀𝘁𝗶𝗼𝗻 Auto-pulls knowledge from every tool where real work happens. Slack, CRM, meetings, docs, without anyone babysitting the pipeline. A personal KB pulls from the web. A team KB has to pull from the inside. 𝟯. 𝗦𝗼𝘂𝗿𝗰𝗲 𝗧𝗿𝘂𝘀𝘁 Not all content is equal. Source Trust tells agents (and humans) what's a verified company decision vs. someone's opinion in a Slack thread. Without it, every doc carries the same weight, which means none of them really do. 𝟰. 𝗙𝗿𝗲𝘀𝗵𝗻𝗲𝘀𝘀 𝗠𝗼𝗻𝗶𝘁𝗼𝗿𝗶𝗻𝗴 Actively re-checks what the KB thinks it knows. When two sources contradict each other, it flags the conflict and demotes the staler one. It doesn't wait for someone to notice, because that's exactly the maintenance work humans defer indefinitely. 𝟱. 𝗦𝗲𝗹𝗳-𝗠𝗮𝗶𝗻𝘁𝗮𝗶𝗻𝗶𝗻𝗴 Docs update themselves as work happens. A decision on a call lands in the right doc automatically. A roadmap change propagates everywhere it needs to go. No copy-pasting. No "someone should update this." 𝟲. 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗗𝗿𝗶𝗳𝘁 The slow, invisible gap that opens between what your docs say and what's actually true. A decision gets reversed. A process changes. A feature ships. The doc stays the same. Nobody notices, until your AI agent confidently gives someone the wrong answer. Knowledge Drift is the disease. Everything else on this list is the cure. Which am I missing?

If I wanted to land a $200k AI engineer job in 90 days, I wouldn’t go back to school for a degree. I’d master these 10 GitHub repos. 1. awesome-llm-apps Production-grade AI guide. RAG, agents, multimodal apps, with full code. 106k+ stars. Repo → github.com/Shubhamsaboo/a… 2. LangChain Core framework. Used in production by Klarna, Replit, Elastic, and most AI startups by 2026. Repo → github.com/langchain-ai/l… 3. LangGraph Orchestration layer powering production agents. A must-have skill in senior AI engineer job descriptions. Repo → github.com/langchain-ai/l… 4. CrewAI Multi-agent coordination. The go-to framework for Fortune 500 teams. Repo → github.com/crewAIInc/crew… 5. Ollama Run any open-source LLM on your own machine. The fastest way to learn how models work. Repo → github.com/ollama/ollama 6. awesome-mcp-servers MCP is the standard adopted by all major AI labs by 2026. Master it to outpace 99% of engineers. Repo → github.com/punkpeye/aweso… 7. Qdrant Vector database for large-scale production RAG. Embeddings and semantic search are essential AI job skills. Repo → github.com/qdrant/qdrant 8. AI-Agents-for-Beginners Microsoft’s free 12-course program teaching agent building. Real code, real exercises, real interview prep. Repo → github.com/microsoft/ai-a… 9. system-design-primer Production-grade AI is system design. The repo FAANG engineers use for interview prep. Repo → github.com/donnemartin/sy… 10. awesome-claude-code Usage guide for this tool, now used internally by FAANG, OpenAI, Anthropic, and most YC startups. Repo →

现在大家都在做 Agent，但一上复杂业务：架构怎么搭、记忆怎么管、多智能体怎么配合，往往越做越迷糊。 我最近看到一本开源书 Agentic Design Patterns，把智能体设计模式从入门讲到企业级，脉络清晰、拆解到位。 全书 21 章 + 7 个附录，按难度分四大部分；每章配套 Jupyter Notebook，边读边跑，理论和代码紧贴在一起。 GitHub：github.com/evoiz/Agentic-… 前半段打底：提示链、路由、并行、反思、工具调用、多智能体协作等核心模式，一次讲透“怎么设计”。 后半段落地：记忆管理、异常恢复、人机协作、安全护栏、性能评估等生产必修课，直接对准“怎么上线”。 附录还补齐框架对比和高级提示技巧，适合查漏补缺、随用随翻。 想把 Agent 从概念学到可落地的系统方法，这本开源书值得收藏，慢慢啃。

Andrej Karpathy: "90% of what AI twitter tells you to learn will be dead in 6 months" Here are 10 things senior AI engineers stopped wasting time on: 1. AutoGen / AG2: moved to community maintenance, releases stalled. dead for production 2. CrewAI: demos well, breaks in production. engineers building real systems already moved off it 3. Autonomous agent pitches: the AutoGPT / BabyAGI wave is dead in product form. the industry settled on supervised, bounded, evaluated agents 4. Agent app stores / marketplaces: promised since 2023, zero enterprise traction 5. SWE-bench leaderboard chasing: researchers proved nearly every public benchmark can be gamed without solving the underlying task 6. Microsoft Semantic Kernel: unless you're locked into Microsoft enterprise stack, it's not where the ecosystem is heading 7. DSPy: philosophical merit, niche audience. not a general agent framework 8. Horizontal "build any agent" platforms: Google Agentspace, AWS Bedrock Agents, Copilot Studio. confusing, slow-shipping, the math still favors building yourself 9. Per-seat SaaS pricing for agent products: market moved to outcome-based. per-seat is already dead 10. The framework that went viral on HN this week: wait 6 months. if it still matters, it'll be obvious what actually compounds instead: - context engineering - tool design - orchestrator-subagent pattern - eval discipline - the harness mindset (harness > model, always) - MCP as the protocol layer be few steps ahead than your competitors and outperform this market till it became mass-opinion study this.

After reading @AnthropicAI blog on Agentic AI. spent some time to create a mental model to understand how to design, and explain Agentic AI architecture Define a task/goal - what you want agent to do achieve? 1. Orchestration layer : it is your control panel 3. Agents layer: this layers made of agents (multi /specialised) 4. tools: your tools are made of this layer (web search, DB, APIs etc) 5. memory: this is the brain to store information - long or short term etc. 6. monitoring : This is the most crucial to monitor each and every step 7. Reliability & failure management: identify errors, retry, fallback, involve human 8. Governance and security: compliance, audit, auth etc.

System design concepts I’d master if I wanted to crush it. Bookmark this. 1.Consistent Hashing 2.Sharding 3.CAP Theorem 4.Quorum Consensus 5.Leader Election 6.Raft & Paxos 7.Gossip Protocol 8.Vector Clocks 9.Load Shedding 10.Circuit Breakers 11.Backpressure 12.Tail Latency Reduction 13.Bloom Filters 14.HyperLogLog 15.Reservoir Sampling 16.Split-Brain Resolution Follow @asmah2107 to uplift your system design game.

Curated system design diagrams and concepts for interviews github.com/ashishps1/awes…

Job 👨🏻‍💻 Position: Data Science / Sr. Data Scientist Skills: NBFC, Credit Risk and Financial data handling, with Credit Bureau Data and Collections data handling skills, Python, PySpark and SQL must. Location: Gurgaon Package: 20-35 LPA DM me for direct interviews

Agentic system design concepts I'd master if I wanted to build AI that doesn't blow up in prod. Bookmark this. 1. Agent Circuit Breaker 2. Blast Radius Limiter 3. Orchestrator vs Choreography 4. Tool Invocation Timeout 5. Confidence Threshold Gate 6. Context Window Checkpointing 7. Idempotent Tool Calls 8. Dead Letter Queue for Agents 9. LLM Gateway Pattern 10. Semantic Caching 11. Human Escalation Protocol 12. Multi-Agent State Sync 13. Replanning Loop 14. Canary Agent Deployment 15. Agentic Observability Tracing

I gave my OS a goal and let it research overnight. Woke up to 6 hours of autonomous research, structured, cited, saved to disk. Built a Personal OS Agent inspired by Karpathy's AutoResearch — but for ANY research topic, not just ML. Open-source 👇 github.com/simranjeet97/S…

Building a WhatsApp Bot using Andrej Karpathy LLM Wiki Idea and Gemini. Using this bot, Get info about Study Resources, Medium blogs, YouTube videos or GitHub repositories that are suitable to your query. Join this WhatsApp Community to use this Bot: chat.whatsapp.com/EhsiKqFWHTb0EN…

Curated list for reliable AI agents github.com/walkinglabs/aw…