Tips for Better Results

AIRA is powerful, but the quality of your results depends on how you ask. These best practices will help you get more useful, accurate, and actionable responses.

Be Specific

The more detail you provide, the better AIRA's response. Vague questions produce vague answers.

Specific questions give AIRA clear boundaries — what data to pull, what time frame to use, and how to organize the results.

Provide Context

AIRA works best when it understands what you are trying to accomplish, not just what data you want.

• Use @-mentions to reference documents from your Library. Upload brand guidelines, competitor reports, or campaign briefs and pull them into the conversation. See Library & File Mentions.
• Use playbooks for structured queries that you run regularly. Playbooks ensure consistent formatting and variables. See Playbooks.
• State your goal so AIRA can tailor its response. For example:

"I am planning a retention campaign and need to identify at-risk customers who have not purchased in 60 days but had high order values previously."

This gives AIRA both the data request and the business context, resulting in more actionable output.

Iterate on Responses

Your first question does not have to be your last. AIRA remembers the full conversation, so you can build on previous answers:

• Ask follow-ups to dig deeper: "Can you break that down by customer segment?"
• Add data points: "Can you also include average order value and purchase frequency?"
• Request clarification: "Can you explain what 'at-risk' means in this context?"
• Refine the output: "Can you turn this into a table sorted by revenue?"

Each follow-up refines the analysis without starting over. Treat it as a conversation, not a one-shot query.

Use Playbooks for Repeatable Tasks

If you run the same type of analysis regularly — weekly revenue reports, monthly customer reviews, campaign performance checks — create a playbook for it.

• Playbooks save time by pre-writing the prompt with fill-in-the-blank variables.
• Playbooks ensure consistency so you get the same format and depth every time.
• Playbooks reduce errors because the prompt is tested and refined once, then reused.

Learn how to create and use playbooks in the Playbooks guide.

When AIRA Works Best

AIRA delivers the strongest results when:

• Analyzing connected data — Shopify orders, Klaviyo campaigns, Google Analytics traffic. The more integrations you have, the richer the insights.
• Generating reports and summaries — Weekly business reviews, customer segment analysis, product performance breakdowns.
• Answering specific business questions — Revenue by channel, top customers, retention rates, campaign ROI.
• Creating content based on your brand — Email copy, social media posts, product descriptions — especially when you @-mention your brand guidelines.

Common Pitfalls

Asking vague questions

"Show me data" gives AIRA too little to work with. Be specific about what data, what time period, and what format you want.

Not connecting enough data sources

AIRA can only analyze data it has access to. If you have only connected Shopify, AIRA cannot answer questions about email campaign performance. Connect more integrations from Data Sources for richer insights.

Ignoring artifacts

When AIRA generates a report or table, save the important ones to your Library. Artifacts that are not saved are only available in the chat history — saving them makes them searchable, shareable, and available for @-mentioning in future conversations.

Skipping follow-ups

Your first question often opens the door to deeper analysis. Do not stop at the first answer — ask follow-ups to dig into the details that matter most for your decision.