All templates

Operations

Weekly metrics report

Queries your warehouse, computes the metrics your team argues about, and posts a report with the anomalies called out.

The prompt

This is the whole configuration

Paste it into a workflow and edit it in plain English. There is nothing else to wire up.

The prompt
Every Monday at 7am, query our ClickHouse events table and our Postgres accounts table to build last week's metrics: signups, activated accounts, weekly active accounts, total runs, revenue, and churn. Compute week-over-week and four-week trends for each. Then look for anything unusual — a metric outside its recent range, a sudden concentration in one region or plan tier, a metric that moved in the opposite direction from its usual correlate — and explain what you found. Post to #metrics with the headline numbers first, then the anomalies, then a short note on what you checked and found normal. Include the SQL you ran as a thread reply.

Trigger

What starts this agent

Mondays at 7:00am

Runs on a schedule. Describe the cadence in plain English and Helios turns it into a cron expression for you.

Integrations required

Authorize each service once. Helios stores the credential envelope-encrypted and attaches it server-side on every run.

Example output

What you get back

Every run leaves a readable record: the steps the agent took and the result it produced.

Metrics · week of Mar 3

  • Signups 1,204 · up 8% week over week
  • Net revenue retention 112%
  • Error rate up 0.4pp, concentrated in one region

New to Helios? Start with Run your first agent.

Run Weekly metrics report on your stack.

Connect the integrations, paste the prompt, attach the trigger. The agent takes it from there.