Build a support data pipeline and dashboard in under an hour with Devin

Posted

Jul 16, 2026 by Devin (Eight Sleep)

·

Last checked

Oct 16, 2026

·

Method:

How we verify

Evidence: Company case studyA write-up published by the company that makes the agent or uses it.

Outcome

At Eight Sleep, a support manager who used to need the data team for dashboards built an end-to-end pipeline and dashboard herself with Devin in under an hour, according to Devin's customer story.

Agent

Devin

The source didn't share its exact prompt, so we wrote this from what it describes.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Build a dashboard from my team's data without waiting for the data team.

Quick-check questions: Which data, which questions should it answer, and who will use it?

What I'll give you:
- Data source access
- The 3–5 questions it should answer
- Who should see the dashboard

Rules:
- Show me the data you'll use before building.
- Keep it simple: one page, clear labels.
- Check at least one number on the dashboard by hand against the source, and show me a sample of the raw data next to it.
- Write a short README explaining the data sources and how the dashboard refreshes.

Output: A working dashboard and a short note on sources and refresh.

If my answers leave a gap, make a sensible choice, say what you assumed, and keep going.

You'll know it worked when: I can answer my questions from the dashboard.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Build a dashboard from my team's data without waiting for the data team.

Questions to ask me first:
- Which data sources?
- Which 3–5 questions should it answer?
- Who will use it?

Inputs (fill in or confirm):
- Data source access
- 3–5 questions it should answer
- Who will use it
- Where the dashboard should live (BI tool, notebook, internal page)

Rules:
- Show me the data and fields you'll use before building.
- Write clear metric definitions.
- Build a pipeline that can be refreshed.
- Keep access limited to the right people.
- Keep the pipeline in version control with a README showing how to rerun it.
- Schedule a refresh and alert on failure.
- Note data latency next to each chart.

Checkpoint: Ask before sharing the dashboard.

If you get stuck: If data quality issues appear, list them. If a login, CAPTCHA or two-step code appears, stop and ask me to handle it; never guess or store passwords.

Verify before you finish: Compare dashboard numbers with the source for one week.

Output: Dashboard link, pipeline code and README.

Done when: the dashboard answers the questions with correct numbers.

Source

https://devin.ai/customers/eight-sleep