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.
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.
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
One prompt, this much work. Every step on your real data.
- 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
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.
The quiet failure 
“Find things that look wrong but never alerted: error spikes, dead crons, growing queues.” Know the account “Map our AWS account: what's running, what depends on what, and what's critical?” Risky config 
“Find the risky configuration: public buckets, missing alarms, single points of failure.” The cron audit “List every scheduled job across our clouds and when each one last succeeded.” Close the gaps 
“Which critical services have no logs or traces? Show the gaps and write the fixes.” Read my dashboards 
“Go through our dashboards and tell me what's drifting from normal this week.” Query to check “Write the query for checkout error rate by region over 24 hours, and save it as a check.” Coverage gaps “Which routes swallow errors or log nothing? Show the gaps and the fixes.” The weekly read 
“Summarise what our telemetry says about last week: regressions, improvements, anything odd.” Watch this deploy “We're deploying checkout-api at 5pm. Watch the metrics after and flag anything that moves.” Instrument the launch “payments-v2 ships next week. What instrumentation should it have before launch? Draft it.”
“Find things that look wrong but never alerted: error spikes, dead crons, growing queues.” Know the account “Map our AWS account: what's running, what depends on what, and what's critical?” Risky config “Find the risky configuration: public buckets, missing alarms, single points of failure.” The cron audit “List every scheduled job across our clouds and when each one last succeeded.” Close the gaps “Which critical services have no logs or traces? Show the gaps and write the fixes.” Read my dashboards “Go through our dashboards and tell me what's drifting from normal this week.” Query to check “Write the query for checkout error rate by region over 24 hours, and save it as a check.” Coverage gaps “Which routes swallow errors or log nothing? Show the gaps and the fixes.” The weekly read “Summarise what our telemetry says about last week: regressions, improvements, anything odd.” Watch this deploy “We're deploying checkout-api at 5pm. Watch the metrics after and flag anything that moves.” Instrument the launch “payments-v2 ships next week. What instrumentation should it have before launch? Draft it.”