Sign in Subscribe

Drishti Shah

Meta prompting: Enhancing LLM Performance

Learn how meta prompting enhances LLM performance by enabling self-referential prompt optimization. Discover its benefits, use cases, challenges, and how Portkey’s Engineering Studio helps streamline prompt creation for better AI outputs

Prompt Engineering for Stable Diffusion

Learn how to craft effective prompts for Stable Diffusion using prompt structuring, weighting, negative prompts, and more to generate high-quality AI images.

Understanding prompt engineering parameters

Learn how to optimize LLM outputs through strategic parameter settings. This practical guide explains temperature, top-p, max tokens, and other key parameters with real examples to help AI developers get precisely the responses they need for different use cases.

COSTAR Prompt Engineering: What It Is and Why It Matters

Discover how Costar prompt engineering brings structure and efficiency to AI development. Learn this systematic approach to creating better prompts that improve accuracy, reduce hallucinations, and lower costs across different language models.

Mastering role prompting: How to get the best responses from LLMs

Learn how to get better AI responses through role prompting. This guide shows developers how to make LLMs respond from specific expert perspectives with practical examples and best practices.

Delimiters in Prompt Engineering

Learn how to use delimiters in prompt engineering to improve AI responses. This blog explains delimiter types, best practices, and practical examples for developers working with large language models

LLM Grounding: How to Keep AI Outputs Accurate and Reliable

Learn how to build reliable AI systems through LLM grounding. This technical guide covers implementation methods, real-world challenges, and practical solutions