1
Building Food Metadata with LLM Juries
DoorDash用LLM陪审团与上下文优化，多模态AI精准构建食品元数据，工程实践亮点。
Article URL: https://careersatdoordash.com/blog/building-food-metadata-with-llm-juries-context-optimization-multimodal-ai/ Comments URL: https://news.…
2
Versiona acciones de correo en agentes LLM
用版本号锁定邮件动作，让LLM agent不再自由发挥，提升可预测性与可靠性。
Muchos equipos que integran LLMs con correo se obsesionan con el prompt y dejan medio borroso el contrato de ejecución. En mi experiencia, el fallo re…
3
A Small Node.js Wrapper for LLM API Retries, Timeouts, and Logging
一个小巧的Node.js包装器，优雅处理LLM API的重试、超时和日志，告别重复代码。
Most LLM API integrations start with a direct SDK call. That is fine for a demo. But once the call is inside a real product, I usually want three thin…
4
Why Snap CD: AI on a Leash
探讨AI agent在持续部署中的信任控制局限，提出渐进授权思路，打破“全有或全无”困境。
AI coding agents are showing up in infrastructure workflows. They can diagnose a failed terraform apply , summarise what changed across a dozen module…
5
Building Reliable LLM Applications in Python
用Python打造可预测、无幻觉的LLM应用工程实践，揭秘Anthropic Claude生产级部署要点
Introduction Calling an LLM API is easy. Building an application on top of one that is reliable — that fails predictably, doesn't hallucinate its way …
6
I Scored 10,000 Job Listings a Day With GPT-4. Here's What Broke
用GPT-4日处理万条职位列表，从47分钟/86美元到崩溃的全流程踩坑实录，生产级RAG的硬核教训。
The first time my scoring pipeline ran against a full day's batch, it took 47 minutes and cost $86. The second run took three hours because half the r…
7
How Shopify built an AI stack that doesn't care which models survive
Shopify构建了一套模型无关的AI堆栈，通过统一调度引擎自动切换大模型，实现工作流零中断与降本增效。
Shopify built an LLM proxy that gives every engineer access to multiple AI providers — with automatic failover when any one of them goes down, changes…
8
Why Most AI Projects Never Reach Production
快速将AI模型部署为可交互的在线应用，无需操心基础设施，一键分享给团队测试，缩短项目从实验到投产的周期。
They Don't Have an AI Problem. They Have an Engineering Problem. Artificial Intelligence has never been more accessible. In just a few months, we've g…
9
Your Team Doesn’t Need a Better AI Model This Week
别追逐最新AI模型，先解决工程基础——持久化工作流和编排税才是团队真正痛点
The real upgrade is your workflow contract: permissions, durability, and handoffs. The Hook: the bottleneck moved, and most teams missed it The fastes…
10
How we built an internal data analytics agent
GitHub团队亲述如何用AI打造内部数据分析代理，揭秘工程实践与效率提升
Qubot, our internal Copilot-powered analytics agent, allows any GitHub employee to ask questions about our data in plain language. Here's what we lear…
11
The engineering practices Claude Code and Codex use to improve AI agents
Claude Code与Codex的工程实践揭秘，教你如何系统性提升AI代理的性能与可靠性。
Article URL: https://www.andrewjesson.com/blog/the-engineering-practices-claude-code-and-codex-use-to-improve-ai-agents/ Comments URL: https://news.yc…
12
Search Autocomplete Systems — Complete Guide
揭秘Google搜索自动补全系统如何承受每秒千万级请求与100毫秒硬性延迟
Section 1 — Problem Definition An autocomplete system predicts and suggests query completions as a user types, character by character. The goal is to …
13
Ask HN: Are you using Spec Driven Development?
规范驱动开发是否让LLM编码代理更高效？开发者分享用OpenSpec等工具的实战困惑，核心矛盾在于能否放弃理解代码本身。
Developers working with LLMs in a professional environment, is Spec Driven Development really the way forward with LLM coding agents? Over the past fe…
14
Before You Build an AI Agent, Read This
在团队急于部署AI代理前，这份理性指南能帮你避开常见陷阱，从战略到工程一次理清。
You're leading a team — or an entire organization — that is under real pressure to adopt AI agents. Your board is asking about it. Your competitors ar…
15
4 Signs You Need a Multi-Agent AI System: A Visual Guide
一张图帮你快速识别是否需要升级到多智能体AI系统，告别单Agent瓶颈。
Article URL: https://aidoses.substack.com/p/4-signs-you-need-a-multi-agent-ai Comments URL: https://news.ycombinator.com/item?id=48494419 Points: 2 # …
16
We Used Agentic AI to Fix Kong Gateway's Flakiest Tests
用智能体AI自动化修复Kong Gateway最难搞定的不稳定测试，工程实践干货。
Article URL: https://konghq.com/blog/engineering/how-we-used-agentic-ai-to-fix-kong-gateways-flakiest-tests Comments URL: https://news.ycombinator.com…
17
What "done" means when you're shipping AI features
当“功能完成”不再是终点：AI特性交付如何重新定义“done”？
Article URL: https://jeffgothelf.com/blog/what-done-means-when-youre-shipping-ai-features/ Comments URL: https://news.ycombinator.com/item?id=48460711…
18
Designing an AI-Native Technical Screen
AI原生技术面试如何设计？从思维模式到评估体系，挑战传统筛选逻辑。
Article URL: https://i0exception.substack.com/p/designing-an-ai-native-technical Comments URL: https://news.ycombinator.com/item?id=48456390 Points: 1…
19
AI Doesn't Write Good Software: The Environment Does
AI写代码效率高但质量未必好，真正决定软件优劣的是开发环境与工程实践
Article URL: https://adrianferrera.dev/en/blog/ai-does-not-write-good-code Comments URL: https://news.ycombinator.com/item?id=48444459 Points: 2 # Com…
20
The ways we contain Claude across products
Anthropic披露Claude产品中从零信任到高权限的工程实践，平衡效率与安全。
Article URL: https://www.anthropic.com/engineering/how-we-contain-claude Comments URL: https://news.ycombinator.com/item?id=48392082 Points: 223 # Com…