Using AI Chat
The Intelligence dashboard includes an AI-powered chat that lets you ask questions about your data in plain English. No technical knowledge required — just ask questions the way you'd ask a colleague.
Getting started
Look for the AI Chat icon in the bottom right of the Intelligence dashboard. Click to open the chat panel, then type your question.
What it does: the assistant reads your portfolio data and translates questions into data queries. It can pull metrics and KPIs, filter by buildings, tenants, or time periods, compare performance across dimensions, and surface insights you might not have thought to look for.
What it doesn't do: it works only with data in the Intelligence dashboard. It can't access external systems, change your content, or take actions on your behalf — it's purely for analysis and exploration.
How to ask good questions
Be specific.
| Instead of… | Try… |
|---|---|
| "Show me data" | "Show me content views by topic for the past 30 days" |
| "How are we doing?" | "Which buildings have the highest engagement rates this quarter?" |
| "Tell me about tenants" | "Which tenants have the lowest action rates?" |
Use natural language. You don't need database terms or jargon — "Which content performed best last month?" works.
One question at a time. Focus on one main question per query, then follow up to dig deeper.
Example questions
- "What's our overall reach rate for the past 90 days?"
- "Which content topics get the most views?"
- "How did content engagement compare between last month and this month?"
- "Which day of the week has the highest building traffic?"
- "Show me tenants with below-average utilization"
- "How do daily scans compare to last quarter?"
Working with results
- Review before reacting — scan for patterns, outliers, and unexpected results.
- Ask follow-up questions — "Why is that content type underperforming?", "Break that down by building."
- Request visualizations — "Show me that as a chart", "Visualize content views over time."
Tips for better results
| Tip | Why it helps |
|---|---|
| Use relative dates ("last 30 days," "this quarter") | The assistant handles date math and timezones automatically |
| Name specific buildings or tenants | Removes ambiguity and gets precise results |
| Start broad, then narrow down | Get the big picture first, then drill into details |
| Ask "why" questions | The assistant can explore what's driving the numbers |
| Verify unexpected results | If something seems off, ask clarifying questions |
Troubleshooting
| Problem | What to try |
|---|---|
| Not getting the answer you expected | Rephrase with more specific details; break complex questions into smaller parts; check your dashboard filters |
| The assistant doesn't understand | Use simpler language; avoid abbreviations and internal jargon; ask a different way |
| Results seem wrong | Ask it to explain how it calculated the result; check whether dashboard filters affect the data; compare against the dashboard cards |
| Don't know what to ask | Start with "What are the key metrics I should know about?", "What's performing well right now?", or "Which buildings need attention?" |
Related
- My Portfolio Analytics — RAUES KPIs and the engagement funnel
- Feature Dashboards — Content and Access deep dives
- Sentiment — tenant feedback trends