# Audit the weekend's deploys

Lists every deploy since Friday across Vercel, Render, Cloudflare and Fly, and flags the ones whose metrics moved afterwards.

## The prompt

```
I want to do this: List every deploy since Friday and flag the ones whose metrics moved afterwards.

## Setup (skip if Polylane is already set up)

Read and follow https://polylane.com/auth.md for non-interactive signup and setup. Start by checking whether I am already signed in; reuse my account and workspace.

If the CLI is missing, bootstrap it without starting the interactive wizard:

curl -fsSL 'https://polylane.com/setup?ref=prompts' | bash -s -- --install-only

Then follow the guide through email verification, workspace selection, source connections, and MCP authentication. Ask me for an email code or OAuth consent only when needed. Verify each step; report pending setup instead of claiming success from installation alone.

## How to work

Over MCP: searchTools lists what this workspace exposes, with each tool's schema; call it first. runTool runs one tool, runCode chains several in one call and returns just the answer. search and execute cover the full Polylane REST API: threads, issues, investigations, autofixes, memories.
From the terminal: the polylane CLI wraps the same API, with structured output and non-interactive flags everywhere.
Reads always work. Write tools appear only if I have opted in, and every write is screened.

## Task: Audit the weekend's deploys

Steps:
1. List every deployment and infrastructure change since Friday across connected providers
2. For each, pull the key metrics of the affected service before and after
3. Flag the deploys where a metric moved beyond its normal rhythm
4. Check whether any flagged move already has an issue or investigation
5. Deliver the audit: what shipped, what moved, what needs a look

Ground every claim in data you actually pulled: the query, the log line, the change record. If the data is inconclusive, say so. Ask me before anything that writes.
```

## What it replaces

**Monday starts with archaeology.** Three days of deploys across four platforms, and the only record is a scroll through each provider's dashboard. Whether any of them hurt anything is a separate investigation each.

- Four deploy dashboards, none of them linked to the metrics
- A slow regression from Saturday found on Thursday
- "Did anything happen this weekend?" answered with a shrug

## What the agent does

1. List every deployment and infrastructure change since Friday across connected providers
2. For each, pull the key metrics of the affected service before and after
3. Flag the deploys where a metric moved beyond its normal rhythm
4. Check whether any flagged move already has an issue or investigation
5. Deliver the audit: what shipped, what moved, what needs a look

## What you get

**Monday morning in two minutes** The weekend's story on one page: every deploy, every metric that moved, and the ones worth a closer look, before standup starts.

Every prompt: https://polylane.com/prompts/

Get started with one command: `curl -fsSL https://polylane.com/setup | bash` installs the CLI, connects your coding agents, and creates the account.