AI 教程与实战
收录 AI 工具教程、提示词、安装部署、配置指南、开发实战与可复现步骤。
分类文章5603
当前页28 / 141
持续更新永久归档
分类文章
按发布时间从新到旧 · 每页 40 条
教程 / 实战普通
The Witness Was the Suspect: Why AI Audit Logs Can't Be Trusted
An AI agent does something it shouldn't. It leaks data, or wipes the wrong database, or makes a call...
信息来源:DEV Community
教程 / 实战普通
Backstage: a venue-scouting agent that knows “350 seats” isn’t a yes
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content* ...
信息来源:DEV Community
教程 / 实战普通
Integrating Claude Code with Auth0 APIs
Did you know that an AI agent with live access to your Auth0 tenant can catch bugs that no static...
信息来源:DEV Community · Claude
教程 / 实战普通
Mend: a missing button shouldn't retire a shirt
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community
教程 / 实战普通
We Gave AI Agents Real Tools — Then Realized “Just Ask Before Acting” Wasn’t Enough
Giving an AI agent tools feels like the moment it becomes truly useful. Now it can: read...
信息来源:DEV Community
教程 / 实战普通
Event-Driven AI at Cloud Scale: High-Throughput Stream Classification with Pub/Sub, Dataflow, and Jev
How to turn millions of events per hour into typed, confidence-scored decisions, without a...
信息来源:DEV Community
教程 / 实战普通
Whisper Keeps Correcting Nigerian Speech. Here's How I Measured It
What I Benchmarked I've been fine-tuning Whisper on Nigerian speech for a while, and I...
信息来源:DEV Community
教程 / 实战普通
My first-choice AI model said no to 5 of 6 room photos. The app still answered each one in about 4 seconds.
After a stroke, some people with aphasia understand everything but can't find the words. Hospital...
信息来源:DEV Community
教程 / 实战普通
Broadcast and Get Hit, Go Dark and Void $65M: I Built NAVI-SANCTION with Sanity to Break the Deadlock
How we built NAVI-SANCTION, an autonomous maritime war-risk arbitration engine using Sanity Content Lake and relational GROQ to resolve the lethal contradiction between SOLAS treaties, naval advisories, and Lloyd's insurance warranties.
信息来源:DEV Community
教程 / 实战普通
480 cases, 240 evil twins
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked a lab...
信息来源:DEV Community
教程 / 实战普通
My friend can't stop buying things at 2am. So I built an AI that can.
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
Delta: investigate, connect clues, change your mind
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange. What...
信息来源:DEV Community
教程 / 实战普通
"If it's not in front of me, it's gone": I fine-tuned a 4B model for my friend with ADHD
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend TL;DR. My friend...
信息来源:DEV Community
教程 / 实战普通
Padh Ke Batao: an AI that reads my grandfather's documents to him, on a laptop with no GPU
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
From the Word 'Risk' to Tighter Stops: Automating Quant Parameters via NLP Keyword Capture from LLM Outputs
From the Word 'Risk' to Tighter Stops: Automating Quant Parameters via NLP Keyword Capture...
信息来源:DEV Community
教程 / 实战普通
What survives /compact in Claude Code: the root CLAUDE.md came back 8 of 8 times, an invoked skill didn't through claude -p --resume
2 of 8 compactions dropped the body of a skill I had invoked earlier in the session, even though the...
信息来源:DEV Community · Claude
教程 / 实战普通
My judging engine passed 119 tests and had never once finished its own maths
I've done more than fifteen hackathons and won five, always on a team. For DOGFOOD 2026 I entered...
信息来源:DEV Community
教程 / 实战普通
Trama: Investigating Uncertainty with Sanity Context
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
信息来源:DEV Community
教程 / 实战普通
I gave my text-to-SQL agent a business glossary. One version helped a lot, one did nothing.
A text-to-SQL agent sees table and column names. It does not know that "revenue" in your company...
信息来源:DEV Community
教程 / 实战普通
Building an Un-Cheatable AI Mentor for Competitive Programming
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
Have your own Lake of Assets
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community
教程 / 实战普通
My friend's laptop is full of junk nobody dares delete. So I built him a local AI that explains what's safe.
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
The New System Design Question in 2026 Interviews: Design an LLM Chat Service
A ChatGPT-style chat service is showing up in system design loops. Walk through streaming, token rate limits, context, and GPU scheduling.
信息来源:DEV Community · ChatGPT
教程 / 实战普通
I built an auction for our FIFA draft night, and a local Gemma bids for the friend who can't be there
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
Everlogue: I Built a Book Catalog That Refuses to Trust Its Own Automation
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community
教程 / 实战普通
I built my friend a Gemma-powered mock interviewer that talks back, entirely in the browser
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
I Built a Recipe Book for My Dadi, Using AI That Never Leaves My Laptop
My dadi's best recipes have never been written down. Ask her how much salt goes in, and she says "ek...
信息来源:DEV Community
教程 / 实战普通
SECONDO: An Offline Baking Planner for My Friend's Café, Built on Gemma and TabPFN
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
Cresta 如何基于 Claude Agent SDK 打造智能体构建器 Conductor
Cresta 基于 Claude Agent SDK 打造了自然语言智能体构建器 Conductor,帮助团队将复杂业务上下文转化为可投产的客服体验智能体。Cresta 称在早期用例中,Conductor 将初始部署时间缩短约一半。Conductor 是自改进的元智能体,可将构建经验沉淀为可复用的 skill 供团队共享。
信息来源:Claude:Blog(网页) · Claude
教程 / 实战普通
HandNotes: teaching an open model to read my friend's handwriting, on his own laptop
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
NoPlanB: An AI Execution Engine to Cure Productive Procrastination
For the Hacktoberfest 2026 Weekend Challenge ("Build for a Friend"), I decided to tackle a problem...
信息来源:DEV Community
教程 / 实战普通
He Knew Every Line of Code But Couldn't Ask for Water. I Built AphasiaBridge with Thinking Machines' Tinker to Restore My Friend's Voice in 174ms
A submission for the Hacktoberfest Weekend Challenge: Build for a Friend. How I used Thinking Machines' Tinker and Gemma-2B to restore my friend Tariq's voice in 174ms.
信息来源:DEV Community
教程 / 实战普通
How Sanity Context & MCP Supercharged AI Customer Support in Basegent & Bucket Space
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real...
信息来源:DEV Community
教程 / 实战普通
Your AI Guardrails Are a Taxonomy Pretending to Be an Ontology
A guardrail that only knows categories can label a problem. It can't reason about one. ...
信息来源:DEV Community
教程 / 实战普通
Pinned — your Sanity apiVersion is a promise; this agent reads the fine print
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
信息来源:DEV Community
教程 / 实战普通
Echo Shelf: An AI Knowledge Lake That Connects What You Save to What Matters Now
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community
教程 / 实战普通
The Missing Middle: Why Agent Skills Need Package Managers, Not Just Prompts
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. It's Monday...
信息来源:DEV Community
教程 / 实战普通
California Black Stories: an AI fact-card workflow with a human approval gate
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community
教程 / 实战普通
Clockwrit — every hour has a citation (an agent that knows what time it is, legally)
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
信息来源:DEV Community
教程 / 实战普通
Bench Court: Case Western v. University of Washington, or how my lab protocols went on trial
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
信息来源:DEV Community