System Prompt

You can use the system prompt to provide instructions related to style, tone, and language of the response.

The real-time search component of our models does not attend to the system prompt.

Example of a system prompt

You are a helpful AI assistant.

Rules:
1. Provide only the final answer. It is important that you do not include any explanation on the steps below.
2. Do not show the intermediate steps information.

Steps:
1. Decide if the answer should be a brief sentence or a list of suggestions.
2. If it is a list of suggestions, first, write a brief and natural introduction based on the original query.
3. Followed by a list of suggestions, each suggestion should be split by two newlines.

User Prompt

You should use the user prompt to pass in the actual query for which you need an answer for. The user prompt will be used to kick off a real-time web search to make sure the answer has the latest and the most relevant information needed.

Example of a user prompt

What are the best sushi restaurants in the world currently?

Web Search Models: General Prompting Guidelines

Our web search-powered models combine the capabilities of LLMs with real-time web searches. Understanding how they differ from traditional LLMs will help you craft more effective prompts.

Best Practices for Prompting Web Search Models

Be Specific and Contextual

Unlike traditional LLMs, our web search models require specificity to retrieve relevant search results. Adding just 2-3 extra words of context can dramatically improve performance.

Good Example: “Explain recent advances in climate prediction models for urban planning”

Poor Example: “Tell me about climate models”

Avoid Few-Shot Prompting

While few-shot prompting works well for traditional LLMs, it confuses web search models by triggering searches for your examples rather than your actual query.

Good Example: “Summarize the current research on mRNA vaccine technology”

Poor Example: “Here’s an example of a good summary about vaccines: [example text]. Now summarize the current research on mRNA vaccines.”

Think Like a Web Search User

Craft prompts with search-friendly terms that would appear on relevant web pages. Consider how experts in the field would describe the topic online.

Good Example: “Compare the energy efficiency ratings of heat pumps vs. traditional HVAC systems for residential use”

Poor Example: “Tell me which home heating is better”

Provide Relevant Context

Include critical context to guide the web search toward the most relevant content, but keep prompts concise and focused.

Good Example: “Explain the impact of the 2023 EU digital markets regulations on app store competition for small developers”

Poor Example: “What are the rules for app stores?”

Web Search Model Pitfalls to Avoid

Overly Generic Questions

Generic prompts lead to scattered web search results and unfocused responses. Always narrow your scope.

Avoid: “What’s happening in AI?”

Instead: “What are the three most significant commercial applications of generative AI in healthcare in the past year?”

Traditional LLM Techniques

Prompting strategies designed for traditional LLMs often don’t work well with web search models. Adapt your approach accordingly.

Avoid: “Act as an expert chef and give me a recipe for sourdough bread. Start by explaining the history of sourdough, then list ingredients, then…”

Instead: “What’s a reliable sourdough bread recipe for beginners? Include ingredients and step-by-step instructions.”

Complex Multi-Part Requests

Complex prompts with multiple unrelated questions can confuse the search component. Focus on one topic per query.

Avoid: “Explain quantum computing, and also tell me about regenerative agriculture, and provide stock market predictions.”

Instead: “Explain quantum computing principles that might impact cryptography in the next decade.”

Assuming Search Intent

Don’t assume the model will search for what you intended without specific direction. Be explicit about exactly what information you need.

Avoid: “Tell me about the latest developments.”

Instead: “What are the latest developments in offshore wind energy technology announced in the past 6 months?”

Advanced Techniques

We recommend for users not to tune language parameters such as temperature, as the default settings for these have already been optimized.

Parameter Optimization

Adjust model parameters based on your specific needs:

  • Search Domain Filter: Limit results to trusted sources for research-heavy queries.
  • Search Context Size: Use “high” for comprehensive research questions and “low” for simple factual queries.

Example configuration for technical documentation:

{
  "search_domain_filter": ["wikipedia.org", "docs.python.org"],
  "web_search_options": {
    "search_context_size": "medium"
  }
}

Tips for Different Query Types

Query TypeBest Practices
Factual Research• Use specific questions • Use search domain filters for academic sources • Consider “high” search context size
Creative Content• Provide detailed style guidelines in system prompt • Specify tone, voice, and audience
Technical Questions• Include relevant technical context • Specify preferred programming language/framework • Use domain filters for documentation sites
Analysis & Insights• Request step-by-step reasoning • Ask for specific metrics or criteria