This guide takes you from the fundamentals of Harness engineering to its daily practice with the two tools that dominate the market in May 2026 for knowledge workers: ChatGPT and Claude. If you have arrived at this guide after experimenting with an AI assistant and discovering that the results swing between the dazzling and the exasperating, you are in the right place. That swing is not a flaw in the model: it is the unmistakable symptom that a harness is missing around it.
The guide covers exclusively the external harness: the one that you, as a ChatGPT or Claude user, build on top of the infrastructure that OpenAI and Anthropic already provide for you. The internal harness (the mechanisms these products use to manage context, memory, tools, search, etc.) exists, is fascinating, and falls outside the scope of this guide.
Table of contents
- Part I · Fundamentals
- Part II · Setting up the environment
- Part III · Practice with ChatGPT
- Part IV · Practice with Claude
- Part V · Advanced patterns
- Part VI · Evaluation and continuous improvement
- Part VII · From hobbyist to knowledge Harness Engineer
- Glossary
- Annexes
-
Annex A: Project Instructions template
-
Annex B: skill / custom GPT template by role
-
Annex C: ChatGPT ↔ Claude comparison table
-
Annex D: harness audit checklist
-
If you want to learn at your own pace, with your Agile Club membership you can train and measure your knowledge of this topic in Skill Arena.