# brexhq/prompt-engineering

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

Repository: https://github.com/brexhq/prompt-engineering
Canonical: https://ross.abutalabs.com/products/prompt-engineering
License: MIT
License Family: permissive
Last push: 2023-10-23T01:41:26+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 87
- inputs: {"age_days": 1231, "days_push": 1046, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9585, forks 514 (observed 2026-08-28T04:10:35.932458+00:00)

## What it is
Brex's prompt engineering guide, a documentation-style resource covering strategies, guidelines, and safety recommendations for building systems on large language models like GPT-4. It explains LLM fundamentals, prompt hacking, data embedding formats, chain of thought, and fine-tuning based on production lessons.

## Use cases
- learn prompt engineering for llms
- write better gpt-4 prompts
- understand prompt injection and jailbreaks
- structure data in llm prompts
- apply chain of thought prompting
- decide between prompting and fine-tuning
- build production llm applications safely

## When to choose
- you are new to prompting LLMs and want a practical, production-oriented guide
- you need strategies for embedding data and getting structured output from models
- you want to understand prompt hacking, jailbreaks, and safety recommendations

## When to avoid
- you need runnable code or a library rather than prose guidance
- you need up-to-date coverage of the newest models, since the guide last saw a release in 2023
- you want an interactive course or tutorials with exercises

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: prompt-engineering, llm-inference, rag, documentation
- domain: large-language-models, artificial-intelligence, tutorials
- platform: cross-platform
- tags: llm-guide, gpt-4, prompting-strategies, chain-of-thought, llm-safety, best-practices, natural-language-processing

## Member repositories
- brexhq/prompt-engineering (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:35.932458+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:21:54.946602+00:00, confidence not recorded.
  - readme: https://github.com/brexhq/prompt-engineering (fetched 2026-08-28T04:10:35.932458+00:00, sha 1f734095cdc9)
- Data as of 2026-08-30T08:39:29.467469+00:00.