The Moodmix Control Room
Last reviewed
IntermediateWhat you'll learn
~30 min- Build a private browser-based analytics dashboard from CSV exports
- Parse and visualize Spotify for Artists and Shopify data
- Identify geographic overlaps between listeners and merch buyers
- Generate actionable next-move recommendations from your own data
What you’re building
You have ~50K monthly listeners on Spotify. You have a Shopify store selling merch. But those are two separate dashboards with two separate mental models. You have no idea which cities are streaming your music AND buying your desk pads. You can’t easily see if a track blowing up in Chicago translates to merch sales in Chicago.
You’re going to build a single dashboard that combines both data sources and tells you exactly where the opportunities are.
Everything in this lesson runs in your browser. Your Spotify and Shopify data never leaves your computer. There’s no server, no upload, no third-party analytics service. You open an HTML file, drag in your CSV exports, and the dashboard renders locally. When you close the tab, the data is gone. This matters when you’re working with revenue numbers and listener geography.
Getting your data
Before building the dashboard, you need two CSV exports:
Spotify for Artists
- Log in to artists.spotify.com
- Go to Music > select a time period (last 28 days works well)
- Click the download icon next to the data you want (Spotify for Artists exports song stream counts, the Audience timeline, and the Songs and Playlists tables in Music as .csv files)
- The song export includes columns like track name, streams and listeners. City-level listener data is not in Spotify’s list of exportable stats, so if your export has no city column, ask the AI to show “Geographic data unavailable” in those sections instead of mixing in sample data
Shopify
- Log in to your Shopify admin
- Go to Analytics > Reports and open the sales report broken down by product (filter the list by the Sales category; report names change)
- Export as CSV
- Also export Customers by location. It counts new customers by their most recent shipping location, so repeat buyers are not in it; treat its city counts as a floor
If you’re just getting started and don’t have significant Spotify or Shopify data, you can still build the dashboard. You will ask your agent to include a “Load Sample Data” button that creates realistic mock data so you can see the dashboard in action. Swap in your real CSVs when they’re ready.
Before you start
First, if your AI tool is still open, leave it: type /exit and press Enter (if you use Antigravity, press Ctrl+D with nothing typed instead), and wait until you see the $ or % prompt. Make a clean folder for this lesson inside ~/producer-workbench:
mkdir -p ~/producer-workbench/04-moodmix-control-room && cd ~/producer-workbench/04-moodmix-control-roomOn Windows PowerShell, run mkdir -Force ~/producer-workbench/04-moodmix-control-room; cd ~/producer-workbench/04-moodmix-control-room, or open the folder in your desktop agent app. Then start your agent the way your track’s setup lesson showed.
Switch to plan mode
Once your agent is open, switch to Plan mode inside the session (Shift+Tab, /plan, or your desktop app’s mode picker). In plan mode it asks clarifying questions and shows you a plan before building.
The conversation
Each message below is an example. Say it in your own words.
Say what you want
Start with a short plain-English description of what you want to build:
I want to build a single-file browser analytics dashboard called control-room.html that takes Spotify and Shopify CSV uploads, compares listener and merch cities, highlights opportunity gaps, and suggests next moves. Ask me what you need first.Answer its questions
Your agent will ask a few questions about CSV parsing, sections, and privacy. Answer each briefly:
| If it asks | You might say |
|---|---|
| How should CSV files be loaded, and what if I have none yet? | Use two drag-and-drop CSV upload zones in the browser, plus a Load Sample Data button with realistic mock data. |
| What sections should the dashboard display? | Name them THE DROP (KPIs), FREQUENCY (top 10 tracks), CITY LIGHTS (city comparison), THE GAP (opportunity tables), and NEXT MOVE. |
| How should city names and currency strings be matched and cleaned? | Lowercase city names, strip state suffixes, expand abbreviations like NYC or LA, and strip $ and commas from revenue. |
| What should the NEXT MOVE recommendations look like? | Generate 3-5 plain-language action prompts citing specific city names, stream counts, and merch order numbers from the loaded data. |
| What visual style and privacy rules should it follow? | Dark #0a0a0a theme with #f97316 orange bar charts, no network uploads, and a YOUR DATA STAYS LOCAL badge. |
Read the plan
Before approving, check the plan for four domain essentials:
- All CSV processing stays in the browser session. PapaParse and Chart.js render everything client-side in
control-room.html, with a visible"YOUR DATA STAYS LOCAL"header badge and nothing uploaded or saved tolocalStorage. - City names and currency values normalize cleanly. City comparisons lowercase names, strip state or country suffixes (
", CA",", US"), and expand common abbreviations (NYCtoNew York,LAtoLos Angeles), while currency fields strip$and commas before summing. - THE GAP and NEXT MOVE use real numbers from the data. Opportunity tables flag high-stream/zero-merch cities and high-merch/low-stream cities, and NEXT MOVE writes 3-5 specific recommendations naming the actual cities and counts.
- A Load Sample Data button works immediately. Clicking it populates realistic power-law stream distributions and scattered US merch orders so every chart and table can be verified before dropping in real CSV exports.
If the first plan compares raw city strings without normalizing state suffixes or leaves out the sample data button, say so briefly:
Normalize city names by stripping state suffixes and expanding NYC, LA, and SF before comparing, and include a Load Sample Data button.When the plan covers all four, approve it: pick the option to proceed or say Yes, go ahead and build it (in Codex, press Shift+Tab first to leave plan mode). Once you verify control-room.html in your browser, ask your agent to save a Git checkpoint:
Save a checkpoint with Git so we can roll back if needed.What you get
Ask your agent to open control-room.html in your browser so you can test it:
Open control-room.html in my browser so I can test the dashboard with sample data.You can also open control-room.html directly from your project folder in any browser.
With sample data
Click Load Sample Data first. You should see:
- THE DROP metrics panel with stream counts, revenue, and top track/product
- FREQUENCY bar chart showing your top tracks ranked by streams
- CITY LIGHTS side-by-side city charts for Spotify and Shopify
- THE GAP tables highlighting mismatches between streaming and merch geography
- NEXT MOVE 3-5 actionable recommendations in plain language
With your real data
- Export your Spotify CSV from artists.spotify.com
- Export your Shopify CSV from your admin
- Drag each file onto its respective upload zone
- Watch the dashboard populate with your actual numbers
- If your Spotify export has no city column, the city comparison below has nothing to compare. Type a small
cities.csv(two columns:city,listeners) from the listener cities Spotify for Artists shows you, and ask your AI CLI tool to add an upload zone for it
The most valuable insight from this dashboard is the geographic comparison. When you see that Miami has 3,000 listeners but zero merch orders, that’s a specific, actionable finding. Maybe you run a targeted ad. Maybe you price a Miami-exclusive bundle. Maybe you book a gig there. The data tells you where the gap is; you decide what to do about it.
If something is off
| Problem | Follow-up prompt |
|---|---|
| CSV parsing fails | The CSV upload isn't parsing my Spotify export because it uses semicolons instead of commas. Detect the delimiter automatically when reading uploaded CSV files. |
| Charts don’t show | The bar charts are rendering blank even after data loads. Make sure the charting script finishes loading before drawing the charts, and show a clear message if a chart fails to render. |
| City matching misses similar names | The geographic comparison isn't matching "New York" (Spotify) with "New York City" (Shopify). Normalize city names by stripping "City", expanding abbreviations like NYC, LA, and SF, and comparing in lowercase. |
| Sample data doesn’t look realistic | The sample data is too uniform. Give streams a realistic top-heavy distribution, scatter cities across the US, and keep sample merch orders under 0.1% of stream counts. |
Customize it
Add time-series trends
Add a WAVELENGTH section with a dual-line chart plotting daily Spotify streams alongside daily Shopify merch orders when date columns are present.Add product performance breakdown
Add a MERCH RACK section with a revenue donut chart by product category and a table sorted by revenue showing units sold and average order value.Export a report
Add an Export Report button that downloads a markdown summary of THE DROP metrics, top 5 tracks and cities, top 3 gaps, and NEXT MOVE actions.Add release correlation
Add a RELEASE RADAR section where I can enter release dates and see vertical release markers drawn on the daily streams chart.🔍Why private dashboards beat third-party analyticsclick to expand
Services like Chartmetric, Soundcharts, and Spotify for Artists give you dashboards. So why build your own?
- Cross-platform: Your streaming stats and your store orders live in separate dashboards. Your dashboard bridges them.
- Custom questions: You can’t ask Chartmetric “which cities stream me but don’t buy merch?” Your dashboard answers exactly the questions you care about.
- Privacy: Your revenue numbers, geographic data, and listener demographics stay on your machine. No uploading to yet another analytics service.
- Free: No monthly subscription for another SaaS tool. You built it once, you use it forever.
- Extensible: When you want a new metric or chart, it’s one follow-up prompt away. Try asking Chartmetric to add a custom section.
The tradeoff: you don’t get real-time data or API integrations. You’re working with CSV exports, which means periodic manual updates. For an independent artist checking numbers weekly, that’s perfectly fine.
When Things Go Wrong
Use the Symptom → Evidence → Request pattern: describe what you see, paste the error, then ask for a fix.
Putting it all together
Over these four lessons, you’ve built the foundation of a complete toolkit:
- Release Asset Engine (Lesson 1) — one command generates platform-ready artwork
- Campaign Generator (Lesson 2) — one metadata file produces captions, hashtags, calendar, and an EPK
- Episode Builder (Lesson 3) — one notes file generates all YouTube publishing metadata
- Control Room (Lesson 4) — one dashboard shows where listeners and buyers overlap
These tools connect. The asset engine’s output feeds into the campaign generator’s EPK. The campaign calendar drives your posting schedule. The episode builder handles your YouTube content. And the control room tells you what’s working and where to focus next.
Try it yourself
- Open your AI CLI tool in your lesson folder and switch to plan mode.
- Talk your agent through the plan and approve it to build
control-room.html. - Click Load Sample Data to see the dashboard in action.
- If you have real Spotify and Shopify CSVs, drag them in and see your actual data.
- Pick one customization (time-series trends or product breakdown work well) and add it.
Key takeaways
- CSV exports are your raw material — Spotify for Artists and Shopify both let you export data. Your dashboard turns those exports into intelligence.
- Geographic overlap is the highest-value insight — knowing where listeners and buyers overlap (or don’t) drives real business decisions.
- Private dashboards protect your data — no uploads, no third parties, no subscriptions. Everything runs in your browser.
- Action prompts beat raw numbers — the NEXT MOVE section translates data into “do this next” recommendations, which is what you actually need.
- This is the orchestrator pattern at scale — you didn’t write a charting library or a CSV parser. You directed your AI CLI tool to combine existing tools (PapaParse, Chart.js) into something specific to your needs.
Your dashboard shows that Austin has 2,800 Spotify listeners but zero Shopify merch orders. What does this tell you?
What’s next
In the next lesson, you’ll build The Royalty Reconciliation Tool — a CLI that ingests royalty CSVs from multiple distributors, reconciles the numbers, and flags discrepancies. Reporting errors and mismatched statements are common across distributors. This tool catches what you’d otherwise miss.