Build a Customer.io campaign dashboard with Claude

This is an end-to-end example: connect a data source over the CLI, generate a dashboard from live numbers, and close the review loop on one link. Total time, start to shared link, is under fifteen minutes. The same shape works for any of the other examples — only the connection step changes.

Here's the finished dashboard, published to a canvas — click any tile or number to leave a comment, exactly as your team would:

The three moving parts

1. The Customer.io CLI gives Claude read access to your workspace — campaigns, journeys, segments, message delivery metrics — through a single cio api command backed by a service account token. You decide what that token can touch.
2. Claude pulls the numbers and writes a single self-contained HTML dashboard. You iterate on it in the artifact panel until it's right.
3. Drafty turns that HTML into a stable link your team reviews. Comments pin to the exact element; Claude ships the fix to the same URL.

The generation step is fast now. The part this example is really about is the third one — getting the dashboard in front of people without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the Customer.io CLI

Customer.io ships an official command-line tool. Install it once, then authenticate with a service account token — the CLI exchanges it for a short-lived JWT and refreshes automatically.

Install it:

Authenticate — create a service account token under Account Settings → API Credentials → Service Accounts → Create Token, give it read permissions only, then log in:

Paste the token (it looks like sa_live_…) when prompted, and confirm it took with cio auth status. From here, Claude can run cio api calls against the Journeys UI and CDP Data Pipelines APIs — cio schema lists the available read endpoints.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the CLI's read endpoints to fetch real data:

Claude calls Customer.io, returns the figures, and you sanity-check them against the Customer.io app before going further. This is the moment to catch a wrong assumption — the wrong workspace, a date window that excludes a big send, a campaign you thought was paused — while it's cheap.

Step 3 — Build the dashboard

Once the numbers look right, ask for the artifact:

Claude renders it live in the artifact panel. Iterate in place — you're not regenerating from scratch:

• "Make delivery rate the hero number and put bounce rate right under it."
• "Sort the campaigns table by click rate, highest first."
• "Add a small bar next to each journey showing how full each stage is."

Step 4 — Publish to Drafty for review

A Claude artifact link is a preview, not a stable URL — iterate the artifact and the link you already sent now shows the old version. Ask Claude to publish it to a Drafty canvas instead, so the link you share always stays current:

Claude pushes the dashboard and hands back a drafty.im/canvas/… link that renders on any device. Send it — your team opens it in a browser, no login and no Claude account needed.

Step 5 — The review loop

This is the part that's not obvious until you've done it once.

A reviewer clicks the specific tile, campaign, or number they want changed and leaves a pinned comment — "this bounce rate looks high, is the cold re-engagement campaign included?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Customer.io query if needed, and pushes a revised dashboard to the same URL. The reviewer refreshes and sees the change; the thread stays attached to the element.

The mechanic matters because of what it removes. A Slack message about a chart produces "the number on the left looks wrong." A pinned comment on the actual tile produces "this — exclude the cold re-engagement campaign from the bounce rate." One of those produces a correct revision; the other produces a guess.

Keeping it fresh

A CLI-generated dashboard is a snapshot — it holds the numbers Claude pulled when it built it; it doesn't re-query Customer.io when someone opens the link. For a weekly review or a board-ready snapshot, that's fine.

To make it a live canvas that always shows today's figures, copy this prompt — Claude sets up the refresh for you and schedules it to run on its own:

The link stays stable while the content updates underneath it — see keeping a canvas updated automatically.

What to watch for

• Read-only, always. A messaging dashboard needs read access and nothing more. Scope the service account token accordingly.
• Check the figures before you share. The CLI returns exactly what you ask for — if your "delivery rate" query includes a workspace you didn't mean or a date window that drops a big send, the dashboard will confidently show the wrong number. Reconcile against the Customer.io app once.
• The link is the deliverable, not the artifact. Share the Drafty URL, not the Claude artifact preview — that's the one you can update in place.