Respond to the page with context
Reads the failing signal, checks what changed, opens the investigation and drafts the first Slack update in #incidents.
I want to do this: We're seeing 500s on api.example.com. Start an investigation and post findings to #incidents. ## 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: Respond to the page with context Steps: 1. Read the failing signal: which endpoints, since when, how bad 2. Check deploys and config changes in the window across providers 3. Start the Polylane investigation on the issue so hypotheses run in parallel 4. Pull the blast radius from the context graph: what else is affected 5. Draft the first status update with the evidence so far, ready to post 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 first ten minutes are tab management.
Every page starts the same: open the dashboard, open the deploy list, open Slack, type "looking". Ten minutes of setup before any actual debugging happens, at the hour you're worst at it.
- Four tabs open before the first real query
- The deploy three minutes before the spike, missed until later
- "Any update?" arriving before you have one
One prompt, this much work. Every step on your real data.
- 1 Read the failing signal: which endpoints, since when, how bad
- 2 Check deploys and config changes in the window across providers
- 3 Start the Polylane investigation on the issue so hypotheses run in parallel
- 4 Pull the blast radius from the context graph: what else is affected
- 5 Draft the first status update with the evidence so far, ready to post
Land in the incident, not in the tabs
Thirty seconds after the page you have the signal, the suspect change, and a running investigation. The first Slack update is written before anyone asks.
What broke overnight? 
“Triage everything that fired overnight: what was real, what was noise, and what's still open?” Root cause 
“P99 on checkout-api doubled at 14:10. Find the cause and show the evidence.” Postmortem “Write the postmortem for yesterday's incident: timeline, root cause, and the follow-ups.” What changed? 
“Did anything deploy or change config in the last two hours that could explain this latency?” War-room brief “Summarise the open incident for the exec channel: impact, cause so far, next steps.” Close the loop “The incident is resolved. Draft the permanent fix and link the evidence.” Which release? “Errors started around Tuesday. Which release introduced them?” Dedupe the pager “Group last month's pages into distinct issues. How many were the same thing twice?” Audit the alerts “Go through our alert rules: which ones fire the most, and which were ever real?”
“Triage everything that fired overnight: what was real, what was noise, and what's still open?” Root cause 
“P99 on checkout-api doubled at 14:10. Find the cause and show the evidence.” Postmortem “Write the postmortem for yesterday's incident: timeline, root cause, and the follow-ups.” What changed? “Did anything deploy or change config in the last two hours that could explain this latency?” War-room brief “Summarise the open incident for the exec channel: impact, cause so far, next steps.” Close the loop “The incident is resolved. Draft the permanent fix and link the evidence.” Which release? “Errors started around Tuesday. Which release introduced them?” Dedupe the pager “Group last month's pages into distinct issues. How many were the same thing twice?” Audit the alerts “Go through our alert rules: which ones fire the most, and which were ever real?”