# Build a demographics dashboard in Claude

> Tier: recipe. Operating recipe: real tool sequence, core rules, known traps.

Builds the Get MCP Ads Demographics template as a Claude dashboard for Meta, Google Ads, TikTok, Pinterest, Snapchat and LinkedIn: spend, impressions, clicks, conversions and value by age bracket and gender (age x gender on Meta and TikTok; job function, seniority and industry on LinkedIn), with CPM, CTR, CPC, CPA, ROAS and each bracket's share of the platform, against the comparison period the reader picks. Delivery a platform does not attribute to a bracket stays visible as Unknown, and Google's Performance Max, which reports no demographics, as Not reported.

**Intent.** A live page showing which ages and genders each platform reaches and which of them earn their spend, so the team can adjust targeting, bids and creative by audience.

## When to use

- Someone asks who their ads reach, which age group or gender converts, whether the spend matches the target audience, or for an age and gender report they can keep in Claude.
- Before narrowing or widening an audience, changing age or gender bids, or briefing creative for an audience, and to check afterwards what changed.

## When not to use

- Changing targeting or demographic bids: the dashboard reads only; changes go through the platform tools with preview and confirmation.
- Configured targeting (who the ad sets are allowed to reach): that is the targeting audit, not delivery.
- Hosts without Claude's Dashboard artifact type: answer in the conversation with the matching reports instead.

## Sources

Required: any connected source
Optional: Meta Ads, Google Ads, TikTok Ads, Pinterest Ads, Snapchat Ads, LinkedIn Ads

## Preconditions

- The organisation is on Team or Enterprise: ready-made dashboards are not offered on Free or Pro.
- The account is among the chosen accounts, confirmed via list_accounts.

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Resolve the client's workspace and its ad accounts, one per platform (Meta, Google Ads, TikTok, Pinterest, Snapchat, LinkedIn), with list_accounts.
2. Fetch the demographics template with every account (accounts, one per platform, each with its currency). — tools: `get_dashboard_template`
3. Create a Dashboard artifact, write every document exactly as given in one batch, read its check, hand over with the lines given.

## Decision rules

- **When** The template is refused with PLAN_REQUIRED → **conclude** Say the dashboards come with Team and Enterprise and that only the account owner changes the plan; answer the question in the conversation meanwhile.
- **When** The person asks which age or gender to cut → **conclude** Compare CPA and ROAS within one platform and under one conversion type, weigh each bracket's share of spend and conversions, and say that Meta's figures by age and gender are its estimates and that a bracket the algorithm feeds little may be small on purpose; never compare brackets across platforms, whose brackets and conversions differ.
- **When** A large Unknown or Not reported row → **conclude** Leave it as is and name it: Unknown is delivery the platform does not attribute to a bracket, Not reported is Google Performance Max, which has no demographic reporting. Never spread either over the brackets.
- **When** The client advertises on LinkedIn → **conclude** Say LinkedIn reports no age or gender: its page shows job function, seniority and industry, approximate by LinkedIn's design and without conversion value.
- **When** A reader sees a source fail to load → **conclude** Their own Get MCP Ads access decides: check that their connection covers this client's workspace and that their plan includes dashboards before changing the dashboard.

## Evidence requirements

- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.

## Human approval boundary

- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.

## Failure modes

- Editing the template's page or queries by hand loses the provenance of each figure: ask for changes by name instead.
- Adding brackets across platforms: Snapchat's 18-20 and 21-24, Pinterest's 45-49 and 50-54 and TikTok's 55+ are each platform's own, and each platform's conversions are its own claim.
- Counting Performance Max inside a Google age or gender, or reading Unknown as one more age group.

## Output

- **Readout**: The figures, with windows and accounts named.
- **Flags**: What deserves a deeper skill or a human decision.

## Related

- Skill: [audience-segments-dashboard](https://www.getmcpads.com/skills/audience-segments-dashboard.md)
- Skill: [google-ads-audience-readout](https://www.getmcpads.com/skills/google-ads-audience-readout.md)
- Skill: [pinterest-targeting-report](https://www.getmcpads.com/skills/pinterest-targeting-report.md)
- Skill: [scorecard-dashboard](https://www.getmcpads.com/skills/scorecard-dashboard.md)