> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnifact.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Keeping Responses Accurate and Factual

> Learn simple techniques to keep Omnifact focused on real information and prevent it from making things up.

<Card title="Stick to the Facts" horizontal>
  Learn how to write prompts that keep Omnifact focused on real information and prevent it from creating details that aren't accurate.
</Card>

## The Core Principle

Sometimes AI creates information that sounds believable but isn't actually true or based on your materials. This includes made-up statistics, fictional details, or confident answers about things it doesn't actually know.

**The solution is simple: Always tell Omnifact to stick to the information you provide and say when it doesn't know something.**

To provide this information, you can copy and paste text or attach files directly to your message. If cloud storage integrations are enabled, you can import documents from Google Drive, OneDrive, or SharePoint using the attachment menu. In Spaces, the AI can also retrieve from **Uploaded Files** and **[Connected Sources](/en/platform/core-features/spaces/connected-sources)**.

When you use these techniques, you:

* **Get more reliable answers** for important business decisions
* **Avoid spreading incorrect information** to colleagues or clients
* **Build appropriate trust** in AI-generated content

Use this pattern for factual accuracy:

```
[INSTRUCTION TO STICK TO FACTS] + [TASK] + [SOURCE MATERIAL]
```

**Example:**

> "Using only the information in this report, summarize the key findings. If any important details are missing, say so clearly.
>
> REPORT: \[your document]"

## Choosing the Right Response Mode

Omnifact offers three [Response Modes](/en/platform/core-features/chats/response-modes) that affect how strictly the AI sticks to facts. Use this framework to pick the right mode before you send your message:

<CardGroup cols={3}>
  <Card title="Auto (Default)" icon="sparkles">
    **Best for:** Questions that may need web search, attached files, or document retrieval alongside your instructions.

    The AI decides which tools to use. Pair with grounding phrases when accuracy matters.
  </Card>

  <Card title="Quick Response" icon="bolt">
    **Best for:** Brainstorming, drafting, or general knowledge when speed matters more than external sources.

    The AI answers from its training data only. Do not use this mode when you need facts from your documents or the web.
  </Card>

  <Card title="Simple Lookup" icon="file-magnifying-glass">
    **Best for:** Answers that must come only from your Space's documents.

    Available in Spaces with Uploaded Files. The most reliable option for preventing made-up details.
  </Card>
</CardGroup>

| If you need...                              | Choose...          |
| ------------------------------------------- | ------------------ |
| Up-to-date information or multiple sources  | **Auto**           |
| A fast draft without tool lookups           | **Quick Response** |
| Answers strictly from your team's documents | **Simple Lookup**  |

<Tip>
  Not sure which mode works best? Send your message in **Auto**, then use the **Response Mode** dropdown on the AI's reply to **regenerate** the answer in **Simple Lookup** or **Quick Response** and compare the results.
</Tip>

## Using Simple Lookup Mode in Spaces

If you are working within a Space that has Uploaded Files, Omnifact offers a built-in feature to guarantee responses are completely grounded in your documents: **Simple Lookup** mode.

When you switch your Response Mode to **Simple Lookup** (using the selector at the bottom left of the chat input), the AI assistant will:

1. Search only through the Space's Uploaded Files.
2. Ignore its general training data.
3. Base its entire response strictly on the retrieved document content.

This is the easiest and most reliable way to prevent hallucinations when you need answers extracted directly from your team's Uploaded Files.

## Helpful Phrases to Keep Responses Accurate

Use these phrases to keep Omnifact focused on facts:

<CardGroup cols={2}>
  <Card title="Set Clear Boundaries" icon="shield">
    * "Using only the information provided..."
    * "Based solely on this document..."
    * "If the answer isn't in the content, say so"
    * "Don't guess beyond what's written"
  </Card>

  <Card title="Encourage Honesty" icon="question">
    * "If you're not certain, say so"
    * "Only answer what you can verify"
    * "Tell me when information is missing"
    * "If unclear, ask for clarification"
  </Card>
</CardGroup>

## Real Examples You Can Use

<Tabs>
  <Tab title="Market Research">
    "What are the latest trends in our industry and how do they affect our strategy?" <br />

    "Based on the market research I'm providing, identify industry trends mentioned and their potential impact on our strategy. If you need additional recent information not in these documents, let me know. <br />

    RESEARCH DOCUMENTS: \[your research]"
  </Tab>

  <Tab title="Contract Review">
    "Review this contract for potential issues. Use only information clearly stated in the contract. If legal interpretation is needed, tell me where expert review is required. <br />

    CONTRACT: \[your contract]"
  </Tab>

  <Tab title="Financial Data">
    "Pull out the key financial numbers from these quarterly reports. For each number, tell me which document and section it came from. <br />

    REPORTS: \[your financial documents] <br />

    Format: Number | Amount | Source (Document + Section)"
  </Tab>

  <Tab title="Customer Feedback">
    "Analyze customer feedback about our new feature using only the survey responses I'm providing. Don't make generalizations beyond what's actually documented. <br />

    CUSTOMER FEEDBACK: \[your survey data]"
  </Tab>
</Tabs>

## Common Mistakes That Lead to Made-Up Information

<AccordionGroup>
  <Accordion title="Asking for Information You Haven't Provided">
    **Problem:** Requesting details that aren't in your materials\
    **Instead of:** "What's our customer satisfaction score?" (when you haven't shared survey data)\
    **Try:** "What does this customer survey data tell us about satisfaction levels?"
  </Accordion>

  <Accordion title="Asking for Predictions Without Historical Data">
    **Problem:** Asking for forecasts without past information\
    **Instead of:** "What will our sales be next quarter?"\
    **Try:** "Based on these past 4 quarters of sales data, what trends do you see?"
  </Accordion>

  <Accordion title="Asking for General Best Practices">
    **Problem:** Asking for advice without your specific context\
    **Instead of:** "What are the best marketing strategies for SaaS companies?"\
    **Try:** "Based on our company profile and these market research documents, which marketing approaches might work best for us?"
  </Accordion>
</AccordionGroup>

## When It's Still Not Working

<AccordionGroup>
  <Accordion title="Omnifact still makes assumptions">
    **Be more explicit about boundaries:**

    * Add "Don't assume standard practices not mentioned"
    * Use "If this information isn't provided, state that clearly"
    * Try "Limit your analysis to only what's documented"
  </Accordion>

  <Accordion title="Responses are too vague">
    **Ask Omnifact to cite sources:**

    * "For each point, tell me which section of the document it comes from"
    * "Quote relevant sections to support your analysis"
    * "Point to specific data from the materials provided"
  </Accordion>

  <Accordion title="Missing important warnings">
    **Explicitly ask for limitations:**

    * "Clearly state any assumptions you're making"
    * "Tell me what additional information would be needed"
    * "Point out any sections that are unclear or could be interpreted differently"
  </Accordion>
</AccordionGroup>

<Tip>
  When Omnifact says "I don't have enough information to answer that accurately," that's actually good—it shows the AI is being careful rather than making things up.
</Tip>

## When to Be Extra Careful

Watch out for these situations where made-up information is more likely:

* **Requests for specific statistics** without providing data sources
* **Questions about recent events** or current market conditions
* **Requests for industry benchmarks** without providing reference materials
* **Legal or compliance questions** without specific documentation
* **Technical specifications** not provided in your materials

<Warning>
  For critical business decisions, financial analysis, legal matters, or compliance issues, always double-check AI responses with appropriate experts and authoritative sources.
</Warning>

## Other Intermediate Guides

* Review [Separating Data and Instructions](/en/guides/prompt-engineering/intermediate/separating-data-instructions) to structure your prompts clearly
* Learn [Thinking Step by Step](/en/guides/prompt-engineering/intermediate/step-by-step) to guide AI reasoning processes
* Practice [Using Examples](/en/guides/prompt-engineering/intermediate/examples) to show exactly what you want
* Return to the [Beginner Level](/en/guides/prompt-engineering/beginner/basic-structure) to review the basics.