Chat with CLEA
Ask against the workspace, not a blank chatbot
CLEA is most useful when you ask it to use workspace evidence. That means prompt results, sources, competitors, files, cards, and connected analytics.
If you ask a broad question with no context, the answer will be less grounded.
Grounded chat
Grounded chat means asking CLEA to use dashboard evidence, prompt results, files, or cards before suggesting action.
Dashboard data
Ask CLEA to use the dashboard area you care about. For example, ask about AI readiness, source analytics, competitor movement, or suggestion cards.
This keeps the answer connected to the product surface.
Prompt results
Prompt results show the actual AI answers. Ask CLEA to explain why a brand appeared, why a competitor won, or which prompt needs cleanup.
Use exact prompt names or recent runs when possible.
Use the latest result for this prompt. Explain why the answer named these competitors and which source matters most.
Workspace files
Files give CLEA extra instructions and context. Use them for workflows, brand notes, sitemap plans, or review rules.
When a file matters, mention it directly.
Ask for interpretation before action
Start by asking CLEA to explain what changed or what matters. Then ask for an action.
This prevents jumping from one noisy answer to a task that does not deserve work.
Ask for suggestion cards when ready
When a next step is clear, ask CLEA to turn it into a suggestion card.
The card should point to the right dashboard surface, file, prompt, or page.
Review source gap on comparison prompts
Competitors are named from review pages where your brand is missing. Inspect the prompt evidence and decide whether this needs a page update or source review.
Verify answers against evidence
Do not accept important claims without evidence. Ask CLEA which prompt result, source, or dashboard metric supports the answer.