# Get the week's story from the telemetry

Reads the week across Datadog, Axiom, Better Stack, Sentry and Cloudflare: what regressed, what improved, what got strange.

## The prompt

```
I want to do this: Summarise what our telemetry says about last week: regressions, improvements, anything odd.

## 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: Get the week's story from the telemetry

Steps:
1. Read the week's series across every connected provider
2. Split the movement: regressions, improvements, and the genuinely odd
3. Attach likely causes from the week's change records where they line up
4. Note what deserves a check that doesn't have one yet
5. Deliver the weekly read, each item with its series and evidence

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

**The only telemetry review is the incident review.** Between pages, nobody reads the signals. Slow regressions compound, wins go unnoticed, and the weird blip from Tuesday gets remembered only when it recurs as an outage.

- Trends reviewed only after they become incidents
- Improvements nobody noticed or credited
- That odd Tuesday spike, never explained

## What the agent does

1. Read the week's series across every connected provider
2. Split the movement: regressions, improvements, and the genuinely odd
3. Attach likely causes from the week's change records where they line up
4. Note what deserves a check that doesn't have one yet
5. Deliver the weekly read, each item with its series and evidence

## What you get

**A week of signals in five minutes** The story your telemetry was telling all week, read and summarised with causes attached. Regressions get caught as trends; the odd blip gets explained on Tuesday.

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.