brexhq/prompt-engineering

"Tips and tricks for working with Large Language Models like OpenAI's GPT-4".

github.com/brexhq/prompt-engineering
brexhq/prompt-engineering homepage screenshot

About brexhq/prompt-engineering

brexhq/prompt-engineering is an open-source guide created by Brex from internal research on creating LLM prompts for production use. It explains large language models, prompts, tokens and token limits, and strategies for building programmatic systems on models like OpenAI's GPT-4, including data formatting, prompting methods, fine tuning, and safety topics.

Examples were generated with a non-deterministic language model and may give different results, and the guide is described as a living document because practices change rapidly.

Key features

  • Explains LLM basics, prompts, tokens and token limits
  • Covers prompt hacking, jailbreaks and leaks
  • Describes embedding data as lists, tables, JSON and text
  • Explains chain of thought, ReAct and command grammars
  • Compares GPT-4 vs GPT-3.5 for production use
  • Discusses fine tuning downsides and safety recommendations
Best for: Best for developers and researchers creating prompts for production use with large language models.
Good for
  • Covers history, strategies, guidelines and safety recommendations for production LLM use
  • Open source guide that encourages discussion and suggestions for improvement
  • Addresses safety topics including prompt hacking, jailbreaks and leaks
Watch out for
  • Example outputs may differ because they were generated with a non-deterministic model
  • Content can become outdated because LLM best practices evolve rapidly

brexhq/prompt-engineering at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

brexhq/prompt-engineering alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Search & Research

Well-known listings from the same topic.

All 125

brexhq/prompt-engineering FAQ

Will I get the same results as the examples?
Not necessarily. The guide notes examples were generated with a non-deterministic model and may give different results.
What topics does the guide cover?
History of language models plus strategies, guidelines and safety recommendations for working with and building programmatic systems on models like GPT-4.
Can I suggest improvements to the guide?
Yes. Discussion and suggestions for improvements are encouraged.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing