Which AI models support pre-defined instructions (system prompts, docs, links)?

AI Models That Support Predefined Instructions (System Prompts)

System prompts let you give an AI model persistent instructions before any user message.

All Major Models Support System Prompts

system

{"role": "system"}

system_instruction

preamble

Implementation Examples

pythonCopy
# Anthropic Claude
import anthropic
client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-4-6",
    system="You are a senior Python engineer. Always use type hints and docstrings.",
    messages=[{"role": "user", "content": "Write a function to parse JSON safely"}]
)

pythonCopy
# OpenAI GPT-4o
from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a concise technical assistant."},
        {"role": "user", "content": "Explain transformers in 3 lines"}
    ]
)

pythonCopy
# Google Gemini
import google.generativeai as genai
model = genai.GenerativeModel(
    model_name="gemini-1.5-pro",
    system_instruction="You are a Python expert. Be concise and use type hints."
)
response = model.generate_content("Write a binary search function")

Persistent Instructions via Config Files

Beyond API system prompts, tools support persistent per-project instructions:

CLAUDE.md

GEMINI.md

.cursorrules

.aider.conf.yml

System Prompt Best Practices

• Define role: "You are a senior backend engineer specializing in FastAPI"
• Set output format: "Always respond with code examples and type hints"
• Add constraints: "Never suggest deprecated Python 2 syntax"
• Include context: "This project uses PostgreSQL 15 and SQLAlchemy 2.0"
• Keep it under 1000 tokens for most use cases