慣性聚合 高效追蹤和閱讀你感興趣的部落格、新聞、科技資訊
閱讀原文 在慣性聚合中打開

推薦訂閱源

Google DeepMind News
Google DeepMind News
大猫的无限游戏
大猫的无限游戏
GbyAI
GbyAI
WordPress大学
WordPress大学
雷峰网
雷峰网
博客园_首页
L
LangChain Blog
Blog — PlanetScale
Blog — PlanetScale
Last Week in AI
Last Week in AI
博客园 - Franky
M
MIT News - Artificial intelligence
S
SegmentFault 最新的问题
博客园 - 【当耐特】
Jina AI
Jina AI
腾讯CDC
Y
Y Combinator Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
Stack Overflow Blog
Stack Overflow Blog
宝玉的分享
宝玉的分享
罗磊的独立博客

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python)
.NET 人工智慧架構實驗室:讓人工智慧運作與執行工具(第二階段)
Murat Süzen · 2026-05-20 · via DEV Community

在本專案的第一階段,我們使用 .NET 10 和 Google Vertex AI 建立了一個型態安全的「大腦」。在第二階段,我們成功為我們的 AI 基礎架構賦予了手足。透過連接 Microsoft Semantic Kernel,我們創建了一個自動代理,它能夠讀取實際的本地專案檔案、獨立思考,並偵測安全性漏洞或效能瓶頸。

這裡是我第二階段所達成的成就以及學到的關鍵技術教訓的簡要總結.

🛠️ 主要成就

自動工具執行:AI代理現在接收一個高層級目標(例如,“尋找架構模式和安全性漏洞”)。它可以自動運行原生C#插件,如ListProjectFiles和ReadCodeFile,來探索和分析工作空間,無需人工指導。

動態提供者路由:我實現了一個動態執行時管線。系統可以根據用戶選擇,隨時在 Gemini 2.5 Flash 和 Groq (Llama 3.3 / Llama 3.1) 之間切換,完全解耦業務邏輯與單一 AI 供應商。

Angular 19 網絡監控面板:使用 Angular Signals 和 Tailwind CSS v3 建立了一個現代化界面,用於視覺化代理的實時分析結果、複雜度分數和戰略建議日誌。

🧠 重要技術教訓學習

The .NET Scope Trap: Trying to resolve request-scoped Semantic Kernel instances directly from the root IServiceProvider container crashes the Kestrel server. I resolved this runtime boundary issue by shifting keyed service lookups to HttpContext.RequestServices to keep the kernel container safely isolated per HTTP request.

強制確定性JSON:小型模型如Llama 3.1 8B喜歡輸出對話文本或混亂的「思考鏈」而不是乾淨的數據。單獨依靠提示工程太脆弱了。我通過在API網關層級強制嚴格的ChatResponseFormat.Json設置來解決這個問題,機械地保證有效的JSON解析。

Token洩露濾鏡:強制LLM輸出剛性JSON有效載荷,同時以土耳其語解釋複雜的來源代碼可能會使token選擇矩陣混淆,洩露奇怪的字符(如俄羅斯或中文字母)。我不應浪費提示token,而是在客戶端Angular信號流中添加了一個簡單的白名單正則清除器來立即清理它們。

🖥️ 仪表板界面預覽

當 Llama 驅動的自動代理評估本地 C# 源代碼時,實時網頁控制面板的樣式如下:

🚀 下一站是什麼?(階段 3:企業記憶)

既然我們的型態安全大腦可以完美地執行工具並顯示結果,接下來的挑戰是上下文保留。將龐大的代碼庫塞進單個提示窗口非常昂貴,並降低模型準確性。

接下來,我們開始第三階段:企業記憶 (RAG)。我將整合 PostgreSQL/pgvector 至閘道,為我們的代理提供一個永恆記憶基礎,用於儲存專案歷史和工程標準.

🔗 探索程式碼

第二階段的完整藍圖、架構藍圖和逐步實現檔案都是開放原始碼。隨意探索、克隆或隨著實驗室演進而跟進:

👉 GitHub Repository: github.com/muratsuzen/dotnet-ai-lab