The engineering best practices you can drop straight into Claude

2024-09-10 · Source: Towards AI Newsletter · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Towards AI has released a public GitHub repository containing "AI Engineering Cheatsheets," which are markdown files designed to assist AI engineers in building LLM systems. These cheatsheets distill years of internal best practices and lessons learned from Towards AI's experience, offering decision-ready references for common AI engineering problems. The content is derived directly from the Towards AI Academy courses, providing frameworks and recommendations that can be used during development or fed directly into large language models like Claude to provide context. The repository is freely accessible and aims to streamline the building process for AI engineers.

Key takeaway

For NLP Engineers building LLM systems, integrating these AI Engineering Cheatsheets into your workflow can significantly reduce development time and avoid common errors. You should consult the repository for proven best practices and specific recommendations, or use the markdown files to provide advanced context to your LLMs, ensuring your projects benefit from tested engineering decisions.

Key insights

Towards AI offers free, public AI engineering cheatsheets to accelerate LLM system development.

Principles

• Distill complex knowledge into actionable references.
• Share practical experience to prevent common pitfalls.

Method

Access markdown cheatsheets on GitHub, find your situation in a table, and follow the provided recommendations. These can also be fed to LLMs for contextual guidance.

In practice

• Use cheatsheets for quick decision-making mid-build.
• Feed markdown files to Claude for contextual development.

Topics

• AI Engineering
• LLM Systems
• Best Practices
• Developer Resources
• Towards AI Academy

Code references

• louisfb01/ai-engineering-cheatsheets

Best for: NLP Engineer, AI Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• We're sharing our internal AI engineering cheatsheets — Pre-made engineering decisions and architectural guidelines accelerate AI development and improve output quality.
• BugBash'26 Afternoon of Day 1 — LLMs make code cheap, but core software design, correctness, and reliable system engineering remain human-centric challenges.
• A new era for software testing — LLMs can significantly enhance software QA and testing by automating complex, traditionally manual processes without compromising quality.
• AI Is Writing Our Code Faster Than We Can Verify It — AI can make traditional quality engineering affordable, enabling scalable verification of AI-generated code.
• Towards Structured Data: LLMs from Prototype to Production — Deploy LLMs beyond chatbots for structured data, moving NLP projects from prototype to production.
• [FULL WORKSHOP] AI Coding For Real Engineers - Matt Pocock, AI Hero (@mattpocockuk ) — Software engineering fundamentals, like small tasks and clear feedback, are crucial for effective AI integration.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Towards AI Newsletter.