Turn a question into a standing check
Writes the query in Axiom, Datadog, Cloudflare or Honeycomb, verifies it against a day of live data, and saves it as a watched check.
I want to do this: Write the query for checkout error rate by region over 24 hours, and save it as a check. ## 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: Turn a question into a standing check Steps: 1. Write the query against the right provider and dataset 2. Run it and sanity-check the output against what you expect 3. Refine the grouping and window until it answers the actual question 4. Save it to the workspace so it becomes a watched check 5. Confirm the check is live and report what its baseline looks like 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.
You've run this query by hand nine times.
The question is always the same; only the day changes. Writing the query is five minutes, remembering to run it is the part that fails.
- The same ad-hoc query, rewritten monthly
- Checks that exist only in shell history
- Coverage that dies when its author goes on holiday
One prompt, this much work. Every step on your real data.
- 1 Write the query against the right provider and dataset
- 2 Run it and sanity-check the output against what you expect
- 3 Refine the grouping and window until it answers the actual question
- 4 Save it to the workspace so it becomes a watched check
- 5 Confirm the check is live and report what its baseline looks like
Asked once, watched forever
The manual question becomes a standing check judged against its own baseline. Your shell history stops being your monitoring system.
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.” 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.” 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.” 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.”