# Onboard onto the architecture in an afternoon

Walks the live system across AWS, Cloudflare, Vercel and Kubernetes and explains what each part does and who depends on it.

## The prompt

```
I want to do this: I'm new here. Walk me through the architecture: the critical path, the data stores, what talks to what.

## 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: Onboard onto the architecture in an afternoon

Steps:
1. Walk the context graph from the entry points inward
2. Explain the critical path: what serves users, what it depends on
3. Map the data stores and who reads and writes them
4. Connect the repos to what they deploy
5. Deliver the tour, each claim linked to the live resource

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

**Onboarding is archaeology with a deadline.** The wiki is stale, the diagram is aspirational, and the people who know are busy. New engineers assemble the system in their heads one incident at a time.

- A wiki last touched two reorgs ago
- "Ask Sam" as the architecture documentation
- Three months before feeling safe touching production

## What the agent does

1. Walk the context graph from the entry points inward
2. Explain the critical path: what serves users, what it depends on
3. Map the data stores and who reads and writes them
4. Connect the repos to what they deploy
5. Deliver the tour, each claim linked to the live resource

## What you get

**Week-one context from the live system** The architecture explained from what's actually running, not what the wiki remembers. The new engineer's first incident isn't also their first tour.

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.