Asset 20 8 2
Does AI recommend your business? Run the free check →

Join 15,000 business owners, marketers and entrepreneurs. The Sunday newsletter you'll be annoyed only arrives once a week.

Article

Claude Dashboards for Marketers: What to Ask, With Prompts

Marketers get the most from Claude Dashboards by asking questions, not ordering charts. Connect a data warehouse or a connected app such as Salesforce, ask where leads came from, what happened to them next and which campaigns led to outcomes, then open each chart's query to check what it counts before you act on the answer.

The short version: the questions marketers should ask Claude Dashboards.

Marketers don't have a data problem. We have a questions problem. We open a dashboard, look at a wall of charts, nod, and close it again without changing anything. The charts were never the point. The answers were.

That's why Claude Dashboards is interesting for marketing teams. Anthropic's own advice for the feature is to say what you want to know, not just what to chart. So this guide isn't a list of charts to build. It's a list of questions worth asking, with copy-and-paste prompts for each. If you haven't used the feature yet, start with my step by step guide to Claude Dashboards.

How does Claude Dashboards work for marketing data?

You connect a data source, ask a question in plain language, and Claude writes a SQL query for each chart and builds the dashboard. Anthropic lists data warehouses such as Amazon Redshift, BigQuery, ClickHouse, Databricks and Snowflake, plus other apps you've connected to Claude, such as Salesforce. Each chart shows its query and when its data was last refreshed, so you can see exactly what's being counted.

It's in beta on Pro, Max, Team and Enterprise plans. On Enterprise, an owner has to switch it on in Organization settings > Artifacts first.

Why should marketers ask questions instead of asking for charts?

A chart request gets you a chart. A question gets you an answer you can act on. Compare "show me website traffic" with "which channels brought us more enquiries in the past four weeks than in the four weeks before, and which brought fewer?" The second one tells Claude what to compare, over what period and why it matters.

My rule of thumb: if you can't say what you'd do differently depending on the answer, it isn't a question yet. Here's a template that forces that.

Copy this prompt

Using [data source and table], answer this question: [your question].
I'll use the answer to decide: [the decision].
Compare [this period] with [the period before], split by [channel / campaign / product].
Explain the main finding in two sentences, then show the charts that support it.
Tell me what each chart counts, and flag anything that looks unreliable.

What should marketers ask Claude Dashboards about leads and enquiries?

Start where the business feels it. These are questions about where new people come from and whether that's changing.

Copy this prompt

Where did new leads come from over the past [period], split by source?
Which sources are growing and which are shrinking compared with the period before?
Show the trend week by week, and tell me which change is the biggest.

Copy and paste this prompt

Of the leads created in the past [period], how many moved to the next stage, split by source?
Which source brings the most leads that go on to become opportunities, not just the most leads?

What should marketers ask about campaigns?

Campaign reports often stop at activity. Push past that to what happened afterwards.

Copy this prompt

For the campaigns tagged [campaign name or tag] in [data source]:
which ones are linked to new opportunities or orders, and which only drove activity?
Rank them by the outcome that matters to us: [outcome]. Explain how you matched campaigns to outcomes.

That last line matters. Asking Claude to explain how it matched one thing to another is how you catch a dashboard that's quietly counting the wrong thing.

What should marketers ask about customers and repeat business?

Copy this prompt

Which customers bought or renewed before but haven't in the past [period]?
Group them by [product / segment], and show when we last had contact with each group.
I'll use this to plan a win-back campaign, so keep it simple.

Copy and paste this prompt

Work with me

Want AI doing the heavy lifting in your marketing?

I build the systems that handle the boring 80 percent, so you get your week back. Done properly, with the human kept in.

Which products or services do customers most often buy second?
Show the most common first-then-second combinations, so I can plan follow-up emails.

What should marketers ask about content and email?

If your content and email data sits in your warehouse or a connected app, the same rule applies: ask what the content led to, not how busy it looked. Opens and views are easy to count. What people did next is the part that matters.

Copy this prompt

Which pieces of content or emails from the past [period] were followed by an enquiry, a signup or an order within [time window]?
List the top ten, and tell me what they have in common: topic, format or the audience they went to.
Then list the ones that got lots of attention but led to nothing, so I can see the difference.

Copy and paste this prompt

Compare people who joined our email list through [source A] with those who joined through [source B].
Which group is more likely to become a customer, and how long does it usually take?
Explain how you matched email subscribers to customers.

You'll probably find a few quiet performers you'd forgotten about. Those are the ones to repeat.

What should marketers ask about sales pipeline handover?

If your CRM is connected, Anthropic's example of a dashboard of open Salesforce opportunities is a natural starting point. The marketing question is what happens to the leads you hand over.

Copy this prompt

Make a dashboard of open opportunities by stage and owner, split by the original lead source.
Show which stages opportunities from marketing sources sit in longest.
Tell me where leads from marketing most often stall, in one sentence.

How do you check marketing numbers in Claude Dashboards?

Marketing numbers are easy to misread, so build the check into your habit:

  • Open the query behind any surprising number. Anthropic built every chart to show its query. If it isn't counting what you meant, tell Claude what to change.
  • Check the refresh time. Each chart shows when its data was last refreshed. Don't report on stale data.
  • Ask Claude to explain a number. You can ask it how any number on the dashboard was worked out.
  • Agree definitions once. Decide what counts as a lead, an enquiry or a conversion, then put that definition in every prompt.

If your team argues about which numbers matter at all, my guide to the KPIs a small store should track is a useful way to settle it, even if you don't run a shop.

When should marketers use another analytics tool instead?

Anthropic positions Claude Dashboards for quick, exploratory questions. When a question needs deeper analysis, you can send the dashboard to tools such as Amplitude, Grafana, Hex, Mixpanel, Omni, Perplexity, PostHog or Sigma and carry on there. I'd use Claude Dashboards for the question you'd otherwise never get round to asking, and keep your main analytics setup for the deep dives.

A simple weekly routine for marketers

  1. Ask one question about where leads came from.
  2. Ask one question about what happened to them next.
  3. Open the query behind the biggest change and check it.
  4. Write down one thing you'll do differently this week because of the answer.
  5. Share the dashboard with the people who need it.

That's it. One honest question and one decision a week beats a dashboard nobody reads. If you'd like your marketing team to build habits like this with Claude and the rest of your AI tools, that's exactly what I cover in an AI workshop built around your team's own work.

Frequently asked questions

Can marketers use Claude Dashboards without knowing SQL?

Yes. You ask in plain language and Claude writes a SQL query for each chart. You can open the query behind any chart to see what it counts and ask Claude to explain or change it.

What marketing data can Claude Dashboards use?

Anthropic lists data warehouses such as Amazon Redshift, BigQuery, ClickHouse, Databricks and Snowflake, plus other apps you've connected to Claude, such as Salesforce.

What's the best way to prompt Claude Dashboards?

Say what you want to know, not just what to chart. Name the data source or table if you know it, the periods to compare and the decision the answer will help you make.

Are Claude Dashboards up to date?

Anthropic says Claude keeps dashboards current as the data changes, and each chart shows when its data was last refreshed.

Do Claude Dashboards replace analytics tools?

No. Anthropic positions them for quick, exploratory questions. For deeper analysis, you can send a dashboard to supported analytics tools and continue there.

Published and maintained by the Lilach Bullock team, covering marketing, AI and business growth.
Your buyers are asking AI who to use. Does it say you?

See for free whether ChatGPT, Claude, Perplexity, Gemini and Google name you, and get the plan to become the answer.

Check my AI visibility →
Sundays only

Get the Sunday newsletter.

One email a week. AI experiments, marketing tactics, and the workflows Lilach is building right now in her own business.

Subscribe free

Let’s get your marketing running on AI.

Book a free 30-minute call

We figure out what you need, where AI fits in, and what working together would look like.

Book the call →

Or take the 30-second calculator

You’ll see the hours and the money quietly leaking out of your week, and the three workflows worth building first.

Take the calculator →

Or grab the free AI resource library

Prompt packs, templates, checklists, and swipe files. The exact tools I build for paying clients. Yours, free.

Get the library →
Keep reading

More from the blog.