5 articles in this category
Deep dive into the AGENTS.md files from the Document Copilot repo — the dependency policy, configuration rules, anti-patterns, and other nuggets that make a repo AI-agent-ready.
A structured comparison of the three approaches to improving LLM outputs — retrieval-augmented generation, fine-tuning, and prompt engineering — with a decision framework for choosing the right method.
How GEPA — a genetic Pareto optimizer — evolves DSPy 3 agent prompts through natural-language reflection, outperforming RL methods like GRPO with 35x fewer rollouts. Covers the GEPA algorithm, metric design, multi-agent patterns, and a complete agentic chat implementation.
Auto-CoT (Zhang et al., 2022) automatically constructs chain-of-thought demonstrations by clustering questions for diversity and generating reasoning chains with zero-shot CoT. Matches or exceeds hand-crafted Manual-CoT across ten benchmark reasoning tasks with GPT-3.
A comprehensive prompt engineering cheatsheet drawing from IBM techniques and best practices to help you write better prompts and get more reliable AI results