All templates

Engineering

CI cost & speed report

Attributes build spend to the workflows driving it, finds the jobs that got slower, and names the change responsible.

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, pull last week's job history and spend data from WarpBuild. Attribute spend to each repository and workflow, and compare it against the previous week. Identify the three workflows that grew the most in cost and the three jobs whose p95 duration grew the most. For each one, look at the GitHub pull requests that changed that workflow file or its dependencies in the past two weeks, and say which change most likely caused the increase. Also report median and p95 queue time across the fleet, and the overall CI pass rate. Post this to #platform as a short report. Lead with the total and the week-over-week change.

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.

CI spend · week of Mar 3

  • $3,140 total · up 12% week over week
  • `e2e` p95 rose from 8m to 19m after #2790
  • `build-matrix` queues 4m before it starts

New to Helios? Start with Run your first agent.

Run CI cost & speed report on your stack.

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