1. Write Clear, Conflict-Free Instructions

GPT-5 excels at following precise directions but struggles with ambiguity. When setting up your coding environment (

.cursor/rules or AGENTS.md), avoid vague or contradictory guidelines.

Key practice: Review your configuration files to eliminate conflicting instructions that might confuse the model.

  1. Match Reasoning Effort to Task Complexity

GPT-5 automatically applies reasoning to problems. Use high reasoning effort for architecture decisions and complex algorithms. Use medium or low effort for straightforward tasks like formatting or simple refactoring.

Watch for: If the model overthinks simple tasks, be more explicit in your instructions or dial down the reasoning level.

  1. Structure with XML-Style Tags

GPT-5 processes structured context exceptionally well. Use XML-like tags to organize your coding guidelines:

<code_standards>
<core_principles>
- Prioritize modularity and reusability
- Write self-documenting code
</core_principles>
<tech_stack>
- Styling: TailwindCSS
- Framework: Next.js
</tech_stack>
</code_standards>
  1. Avoid Over-Emphatic Language

Previous models responded well to forceful instructions like "ALWAYS gather COMPLETE context before responding!" With GPT-5, this can backfire.

Better approach: Use measured language. The model will naturally be thorough without aggressive prompting.

Advanced Techniques

  1. Enable Planning and Self-Reflection

For new applications, guide the model to think strategically before executing:

<planning_phase>

</planning_phase>

  1. Fine-Tune Agent Behavior

GPT-5 tends toward comprehensiveness. Control this with explicit guidelines:

Tool usage budget: Specify how many tools the agent should call

Thoroughness levels: Define when to be exhaustive vs. efficient

Check-in points: Indicate when to confirm with you vs. proceed independently

Parallelization: Specify if tool calls should run simultaneously or sequentially

Example configuration:

<agent_behavior>
- Make reasonable assumptions and document them
- Don't ask for clarification mid-task
- Adjust based on results rather than seek approval
</agent_behavior>

Quick Reference

When to Use High Reasoning

When to Use Low Reasoning

Red Flags