AI Engineering Cheatsheets
Decision-ready reference tables for the most common AI engineering problems: pick the technique, model, and architecture, then follow the recommendation.
- Source repo
- louisfb01/ai-engineering-cheatsheets
- Stars
- ★ 359
- Last updated
- 14d ago
- FA score
- Insufficient evidence
At a glance
- Works with
- Universal · cross-platform
- You'll need
- Typical use
- An AI engineer choosing a RAG setup, memory pattern, or eval method for production who wants a quick side-by-side comparison.
- Main limitation
- License is unknown, leaving commercial use and redistribution terms unclear.
- Source review
- Insufficient evidence 8 safety controls not found
What does this agent do, and when should you use it?
This is a free Markdown reference repository by Louis-Francois Bouchard that provides decision-ready guidance for the most common AI engineering problems. It ships three cheatsheets: the AI Engineering Playbook (AI_Engineering_Playbook.md), the Agent Architecture and Operations Guide (Agent_Architecture_Guide.md), and the Anti-Slop AI Writing Guide (Anti_Slop_AI_Writing_Guide.md). The usage model is simple: open a cheatsheet, find your situation in the decision table, and follow the recommendation. The material comes from Towards AI courses, and a companion book, AI Engineering For Production, is planned before the end of 2026. Model and tool preferences are explicitly dated snapshots — August 2026 for the playbook and agent guide, October 2026 for the Anti-Slop guide — to be validated on your own workload. The repository contains no executable code and its license is unknown; it is structured documentation, not software.
The repository delivers three Markdown documents. AI_Engineering_Playbook.md uses decision tables to help you pick the right AI technique, model, effort level, modality workflow, prompting strategy, RAG setup, memory pattern, eval method, and production config. Agent_Architecture_Guide.md helps you decide between workflow, single agent, and multi-agent, then covers operations with curated context, evidence stores, phased review, portable skills, feedback loops, and safe scheduling. Anti_Slop_AI_Writing_Guide.md distills what 6,750 judged drafts reveal about AI tells: the six kinds of slop, before/after rules, a two-generation phrase list, a copy-paste prompt, pick/review/rewrite prompts, a 60-second check, and format checks. The flow is: open the sheet, locate your situation in the decision tables, follow the recommended approach.
- An AI engineer choosing a RAG setup, memory pattern, or eval method for production who wants a quick side-by-side comparison.
- A team lead deciding between workflow, single agent, and multi-agent architectures who needs a clear tradeoff guide.
- A content writer using AI who wants to identify and remove AI-sounding phrasing with ready-made prompts and checklists.
- A learner moving from prompting to production RAG who wants the frameworks behind Towards AI's paid courses.
- An engineering manager assessing agent operations practices like context curation, evidence stores, and safe scheduling.
How do you install or deploy this agent?
No software installation or dependencies are required. Clone or browse the repository:
git clone https://github.com/louisfb01/ai-engineering-cheatsheets.gitOr read directly on GitHub. The documents are Markdown files (AI_Engineering_Playbook.md, Agent_Architecture_Guide.md, Anti_Slop_AI_Writing_Guide.md) openable in any Markdown viewer. The license is unknown, so confirm redistribution terms before commercial use.
How do you use this agent?
Three-step usage:
- Open the cheatsheet relevant to your problem (Playbook / Agent Architecture Guide / Anti-Slop Guide).
- Find your situation in the decision tables.
- Follow the recommended approach.
The Anti-Slop guide has a dedicated flow: 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. A companion video, the Free Agents Webinar on YouTube, deep-dives into workflows vs. agents.
What are this agent's strengths and limitations?
- Decision-table format gives a context-specific recommendation instead of generic best-practice prose.
- Covers the full AI engineering chain: prompting, RAG, evaluation, agent architecture, and operations.
- Anti-Slop guide is data-backed by 6,750 judged drafts, with copy-paste prompts and before/after examples.
- Same frameworks as Towards AI's paid courses, available here for free.
- License is unknown, leaving commercial use and redistribution terms unclear.
- Model and tool preferences are dated snapshots (Aug/Oct 2026) and require revalidation on your workload.
- Pure documentation — no executable code or automation, so implementation is entirely manual.
- Deeper material (full lessons, code, projects) sits behind paid courses and a forthcoming book.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| AI Engineering Cheatsheets This agent | Insufficient evidence | — | ★ 359 | 14d ago | — | — |
| AI Agent Engineering Textbook | 55 · Major gaps | FrameworkFree | ★ 651 | 12d ago | HTML | — |
| AI System Design Guide | 27 · Major gaps | Web appFree | ★ 4.2k | 3d ago | — | — |
| Hello-Agents | 54 · Major gaps | Web appFree + model costs | ★ 86k | 22d ago | Python | OpenAI API |
How does FollowAgents rate this agent?
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- This review is based solely on the README; the three core cheatsheet files were not provided, so the scores do not reflect actual product quality and the review must be redone once the body files are available.
- License is unknown; confirm licensing terms before enterprise adoption.
- Publisher identity is unverified, and the README contains multiple promotional links (book, courses); distinguish reference content from marketing when using it.