How to Ask Effective Questions

The quality of an AI Chat response depends on how clearly you define the task. Well-scoped prompts improve retrieval accuracy and make the output easier to verify against the underlying evidence.

Define the scope clearly

Avoid prompts that are too broad or that do not identify a topic, time range, or source set. A specific prompt helps AI Chat retrieve the right evidence and produce a more useful answer.

Less effective	Better
“Tell me about this case.”	“Summarize the private vehicle sales mentioned in these WhatsApp invoices and identify the main individuals involved.”

Useful details include names, date ranges, identifiers, and file or folder context.

Examples:

• “In which documents does Valerio Simoni appear, and in what context?”
• “Which relationships connect this company to luxury vehicle sales in 2023?”
• “List all phone numbers and IBANs mentioned in the selected files, grouped by source document.”

Specify the output you want

If you do not define the expected output, AI Chat may return a narrative answer that is harder to review. State the format you need so the result is easier to validate and reuse. Common output formats include:

Output type	Example
Summary	Short or detailed overview of a topic
Structured list	Entities, identifiers, or events
Comparison	Differences across documents or versions
Relationship list	Who is connected to whom, and why
Timeline	Events ordered by date
Open questions	Gaps, contradictions, or missing evidence

Examples:

• “Summarize all references to private vehicle sales in this folder. Output: bullet list with date, seller, buyer, amount, and source file.”
• “How are these two records connected? Output: the shortest connection path and the supporting sources.”
• “What unanswered questions remain in this dataset? Output: top 10 questions and which documents might answer each one.”

Use AI Chat for interpretation

AI Chat is most useful for interpretation and synthesis across sources. It works well when you need to connect information, summarize evidence, or identify patterns across multiple documents.

Use AI Chat to:

• interpret context across documents
• connect records, concepts, and relationships
• summarize long text or multiple files
• identify themes, patterns, or inconsistencies
• suggest follow-up lines of inquiry

For exact counts or exhaustive totals, use Search and filters where possible. AI Chat responds from retrieved context and may not produce complete numerical aggregation unless the full relevant set has been retrieved and reviewed. Safer prompt patterns include:

• “Based on the retrieved sources, list the transactions you can cite. Do not estimate totals.”
• “If you cannot confirm a count from the sources, say so and list what you found.”

Ask for citations and verify

For sensitive findings or anything that will be used in a report, ask AI Chat to cite its sources. This makes the answer easier to trace back to the underlying evidence.

Prompts such as these can help:

• “Provide citations for each statement.”
• “For every name, amount, and date, cite the source document and the passage.”

Then verify the result by reviewing the references, opening the cited files or records, and checking the original content directly. Treat summaries as pointers, not as final evidence.

Work in small steps

For complex questions, it is often better to split the task into two passes. First extract the facts with citations, then ask AI Chat to analyze the retrieved material.

A typical pattern looks like this: 1.Extract facts with citations “List all vehicle sale transactions with date, parties, and amount, with citations.” 2.Analyze patterns “Based on the cited transactions, identify the top three individuals involved and how they are connected.”

This approach makes the output easier to validate and reduces the risk of missed details.