GPT-5 prompting guide
by OpenAI
Model-specific advice on agentic eagerness, tool preambles and instruction conflicts.
OpenAI records prompting lessons for GPT-5, including instruction following and agentic workflow control. The source now labels the guide archived, so treat it as version-specific historical advice rather than current API guidance.
- Level
- Intermediate
- Models
- gpt-5
- Category
- Prompting
- Tags
- model-specific, archived
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- stale
- Prerequisites
- Assumes basic LLM familiarity or the ability to read examples and configure a workflow.
- Subcategory
- model specific guides
- Region
- West
- Original language
- en
- Access
- free
- Resource reuse
- closed: No general open-reuse grant established from the inspected page. Closed is the conservative index bucket, not a legal finding; the resource is publicly readable. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.