Build a weekly business KPI dashboard workflow with Claude Code + n8n
- Posted
- by AI Hub Landau
- Last checked
- Method:
- How we verify
Evidence: Article or interviewA newsletter, journalist or interview account of what happened.
Outcome
Claude Code built a complex n8n workflow for a client's weekly KPI dashboard in about 15 minutes; the workflow then runs unattended on n8n.
Agent
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Build an n8n workflow that automatically creates a weekly business KPI dashboard from our data sources and runs on a schedule. Data sources: [SOURCES] KPIs to show: [KPIS] Schedule: [DAY AND TIME] Done when: a test run produces the dashboard with every KPI filled in.
Try this in:
This prompt has blanks to fill in, like [SOURCES]. We'll copy it instead of filling it in, so you can edit it before you send.
The source used Claude Code and n8n, which can take actions on your computer or in a browser. These are general chat tools, so results may differ, and a normal chat may only give you a plan.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Goal: Build an n8n workflow that assembles a weekly KPI dashboard from our data sources on a schedule. Inputs (fill in or confirm): - Data sources and credentials method - KPIs with definitions - Where the dashboard lives (Sheets, Notion, Slack) - Schedule Rules: - Write KPI definitions down and confirm them before building. - Store credentials in n8n's credential store, never in nodes. - Handle source failures: send a warning instead of a partial dashboard. - Version the workflow JSON. - Add a failure alert so silent errors are caught. - Test with last week's data and compare numbers with the source. - Document each node in a short README. - Show the week's numbers next to the previous week with the change in %. Checkpoint: Test with last week's data before enabling the schedule. If you get stuck: If a source has no API, say so and propose a manual export step. 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 systems for one week. Output: Workflow JSON, setup notes and a test run screenshot. Done when: the dashboard updates on schedule with numbers that match the sources.
Source
Related cases
After Copilot suggested a subflow that didn't exist in Power Automate Desktop, the poster asked Claude Cowork, which took over and built the flow on their machine.
Claude Cowork · Ops · Source date:
- Build a support data pipeline and dashboard in under an hour with DevinRecreated promptEvidence: Company case study
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.
Poster says:Under an hour
Devin · Data · Source date:
- Automate a daily analytics summary to Slack with Claude CodeRecreated promptEvidence: Described by poster
Claude Code set up a GitHub Actions cron that pulls PostHog data at 8am, summarizes it in Python and posts to Slack; the first report arrived the next morning.
Claude Code · Data · Source date: