内容为 2026 年 8 月与 10 月的模型与工具快照，需在自己的负载上重新验证；仓库只有文档，不含可运行代码或脚本
README 未提供安装命令，直接打开对应 Markdown 速查表阅读即可 硬件要求按 README 说明
README 未说明，纯文档仓库，无需 GPU 或显存
一套按场景查表的 AI 工程决策速查手册，帮你快速选定技术、模型与 Agent 架构
面向 AI 工程常见问题的速查手册，用决策导向的参考帮你快速选定 Agent、LLM 应用等方案，少走选型弯路。
核心能力
- 用决策表按场景选技术、模型、RAG 与评估方法
- 区分工作流、单 Agent 与多 Agent 并给出运维要点
- 提供反 AI 味写作规则、改写提示词与 60 秒自检
- 覆盖提示策略、记忆模式与生产配置建议
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
暂无 release 数据（可能没有发版，或尚未同步）。
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
AI Engineering Cheatsheets
By Louis-Francois Bouchard (X, YouTube, other AI resources)
Goal: give you decision-ready references for the most common AI engineering problems. Open a cheatsheet, find your situation in the table, and follow the recommendation.
Model and tool preferences are snapshots: August 2026 for the playbook and agent guide, October 2026 for the Anti-Slop guide. Treat them as tested starting points, then validate them on your own workload.
New book: AI Engineering For Production takes these cheatsheets further, from prompting, RAG, and evaluation to reliable agents and the harnesses around them. It comes out before the end of 2026. Join the waitlist →
Cheatsheets
| Cheatsheet | What you get |
|---|---|
| AI Engineering Playbook | Pick the right AI technique, model, effort level, modality workflow, prompting strategy, RAG setup, memory pattern, eval method, and production config. |
| Agent Architecture and Operations Guide | Decide between workflow, single agent, and multi-agent, then operate it with curated context, evidence stores, phased review, portable skills, feedback loops, and safe scheduling. |
| Anti-Slop AI Writing Guide | Write with AI without sounding like AI: the six kinds of slop, what 6,750 judged drafts reveal about AI tells, rules with before/after examples, a two-generation phrase list, a copy-paste prompt, pick/review/rewrite prompts, a 60-second check, and format checks. |
How to use
- Open the cheatsheet relevant to your problem.
- Find your situation in the decision tables.
- Follow the recommended approach.
For the Anti-Slop guide, assemble the sources first, fill in the prompt template, generate a few drafts, pick the best, run the separate evidence-first review, rewrite once, and finish with the 60-second check.
Learn more
These cheatsheets come from the Towards AI courses. They cover the same frameworks in more depth, with full lessons, code, and hands-on projects.
- AI Engineering For Production - Our new book on making LLMs and agents reliable with prompting, RAG, evaluation, and harnesses. Coming before the end of 2026; join the waitlist to hear the date first.
- Full Stack AI Engineering - Prompting to production-grade RAG system. Position yourself for the roles, projects, and opportunities that AI is creating right now.
- AI for Business Professionals - Learn to get real benefits from LLMs for valuable tasks from experts that build AI for a living.
- Agentic AI Engineering - Your Path to Agentic AI for Production.
- Free Agents Webinar - Workflows vs. agents deep-dive (YouTube).