kiwistein

[kiwistein @cefikiwi]

@ShenSeanChen Best video I've watched so far about harness & loop

[Shen Sean Chen @ShenSeanChen]

You Can Learn AI Agent Harness & Loop Engineering In 19 Min, with LLM Ops, Eval, Tracing and RAG.

They went viral not because they're complicated but because they're simple building blocks, and once you see them you can prompt your way to building real systems.

🎬YouTube: https://t.co/6QZENmmeJr

Here's the whole thing in one picture.

An LLM is a powerful brain that knows everything about humanity and nothing about you or the software you're running.

The harness is the set of tools you put on that horse so it runs where you want.

Memory gives it context: who you are, what happened before, how to act.

The loop lets it call tools again and again, with guardrails so it knows when to stop.

Eval and LLM Ops trace every run, score it, and feed the fixes back in so the system keeps improving itself.

Master these four and you can read almost any AI agent repo or paper and actually know what's going on.

You Can Build Anything. You Can Learn Anything. 💪

Chapters:
Intro: the 4 AI agent buzzwords
What an AI agent run actually is
The memory system: procedural, semantic, episodic
What "harness" really means (the horse)
Storing and updating memory (databases, skills, summarizer agent)
Retrieval: RAG, SQL vs semantic search
Tool calling and why agents loop
Loop engineering and end-loop guardrails
A Claude Code hooks example
Eval and LLM Ops: why you need them
Tracing every run (Langfuse, LangSmith)
Evaluation: LLM as a judge
Diagnosing what broke
The gate: ship the fix or fix the bug
Zoom out: the full system

[cat @_catwu]

Here's a roundup of how Claude Code has changed engineering at inside Ramp, Rakuten, Brex, Wiz, Shopify, and Spotify 🧵

[kiwistein @cefikiwi]

@okx What are you building now 🧐

[Viking @vikingmute]

Stripe 已经开始在公司内部使用内部自研的一套全自动 AI agent 来写代码了，每周能独立完成并被 merge 超过 1300 个 pull request（全 AI 写，人工 review），这套系统叫 Minions
https://t.co/OB82okhncE

大体流程：
1 工程师在 Slack 里 at bot + 描述任务，或贴上 issue/ticket 链接

2 系统立即启动一个隔离的 devbox，和人类工程师一样的 AWS EC2 开发环境，预先加载了完整的 Stripe 代码库 + 开发服务

3 在 LLM 真正开始思考前，就通过内部工具 MCP + Toolshed（400+ 个工具）自动、确定性地拉取上下文：
* Slack 完整对话线程
* 相关 Jira/ticket 内容
* Sourcegraph 代码搜索结果
* 内部文档、设计文档

4 核心执行

5 代码修改 & 测试策略
* 本地跑 linter 和部分测试
* 改完代码 → git push → 触发完整 CI（Stripe 有 300 万+ 测试用例）
* CI 失败 → 最多允许 两次 CI 重试
* 超过两次就停止，不无限循环

6 CI 通过后，Minions 按 Stripe 标准 PR 模板自动创建 Pull Request 人类工程师 review → 批准 → merge

未来在大公司里面纯 AI 写代码也应该不远了，有严格的流程来管理对应的过程，有人类工程师最后 reivew 把关。

[kiwistein @cefikiwi]

@jiaowoka1ka1 还做吗