Learn the account nobody fully knows
Walks the live system across AWS, Cloudflare, Vercel, Kubernetes and Supabase, and tells you what runs, what depends on what, and what everything else leans on.
I want to do this: Map our AWS account: what's running, what depends on what, and what's critical? ## 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: Learn the account nobody fully knows Steps: 1. Pull the full resource list from the context graph, grouped by service 2. Walk the dependency edges: what talks to what, across providers 3. Rank by tier and traffic: the critical path versus the long tail 4. Flag the orphans: resources nothing depends on and nothing updates 5. Deliver the map: critical systems, their dependencies, and the candidates for cleanup 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.
The account outgrew everyone's head years ago.
Hundreds of resources, some load-bearing, some abandoned by someone who left. The only guide is tribal knowledge, and the tribe keeps shrinking.
- "What is this instance?" asked into the void
- Critical paths that exist only in one person's head
- Abandoned resources billing quietly forever
One prompt, this much work. Every step on your real data.
- 1 Pull the full resource list from the context graph, grouped by service
- 2 Walk the dependency edges: what talks to what, across providers
- 3 Rank by tier and traffic: the critical path versus the long tail
- 4 Flag the orphans: resources nothing depends on and nothing updates
- 5 Deliver the map: critical systems, their dependencies, and the candidates for cleanup
The account, back in one head
A live answer to what's running and why it matters, from the graph rather than from asking around. Onboarding the next engineer takes an afternoon, not a quarter.
The quiet failure 
“Find things that look wrong but never alerted: error spikes, dead crons, growing queues.” 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.” Onboard me “I'm new here. Walk me through the architecture: the critical path, the data stores, what talks to what.” 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.” 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.” Onboard me “I'm new here. Walk me through the architecture: the critical path, the data stores, what talks to what.” Instrument the launch “payments-v2 ships next week. What instrumentation should it have before launch? Draft it.”