Prompting Guides

The system prompt is the single biggest lever you have over how a Cloudax Connect agent behaves on a call or in a chat. These guides distil OpenAI's official prompting advice for the model families that power your agents, with ready-to-paste snippets you can drop straight into an agent's system prompt.

Pick a guide

Which guide should I read?

New agents default to 6.1 Terra (no reasoning effort). 6 Luna remains available as a faster, lower-cost option. Use the guides below when you are still tuning a prompt on a 4.1-family or 5-series model, or when you want techniques that transfer after you migrate. Both guides share a common philosophy: be explicit, avoid contradictions, and iterate against real examples.

• 4.1 family (and 6.1 Terra / 6 Luna) : fast, non-reasoning models that follow instructions extremely literally. Use the GPT-4.1 guide for low-latency agents where you spell out every step. 4.1 Nano retires 23 October 2026; 4.1 and 4.1 Mini retire 14 January 2027. Migrate to 6.1 Terra (see Voice & Audio Settings).
• 5-series : reasoning models with a tunable reasoning_effort. Use the GPT-5 guide to calibrate how much the model thinks and explores before it acts. 5.3 Chat retired 10 August 2026. Migrate to 6.1 Terra.

Universal principles

No advice is one-size-fits-all; prompting is an empirical discipline. Still, a handful of principles hold across every model we support:

• Be specific and literal. Modern models follow instructions closely. If behaviour is off, a single clear sentence stating the desired behaviour is usually enough to correct it.
• Remove contradictions. Conflicting or vague instructions force the model to waste effort reconciling them. Review long, multi-author prompts for rules that fight each other.
• Give examples. Demonstrate the exact behaviour you want, and make sure any behaviour shown in an example is also stated in your rules.
• Iterate with evals. Build a small set of representative test cases and re-run them after every prompt change so you can see whether an edit actually helped.

A reliable starting structure

Both guides recommend the same skeleton as a starting point for a system prompt. Add or remove sections to suit your use case:

# Role and Objective
# Instructions
## Sub-categories for more detailed instructions
# Reasoning Steps
# Output Format
# Examples## Example 1
# Context
# Final instructions and prompt to think step by step