Have the dashboards read for you
Reads every dashboard in Datadog, Honeycomb, Grafana and Axiom, and reports only the series drifting from their own normal.
I want to do this: Go through our dashboards and tell me what's drifting from normal this week. ## 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: Have the dashboards read for you Steps: 1. Enumerate the saved queries and dashboards across connected providers 2. Read each series against its own history: rhythm, not flat thresholds 3. Flag sustained drift and direction-of-worse moves; ignore blips 4. Cross-check flagged series against recent changes for a cause 5. Deliver the weekly read: what's drifting, since when, and what likely moved it 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 dashboards are watched by nobody.
Every team builds dashboards; no team stares at them. The drift that precedes the incident is on a chart someone made two years ago and nobody has opened since.
- Forty dashboards, zero viewers
- Drift visible for weeks before the alert fires
- "Normal" defined by whoever last looked
One prompt, this much work. Every step on your real data.
- 1 Enumerate the saved queries and dashboards across connected providers
- 2 Read each series against its own history: rhythm, not flat thresholds
- 3 Flag sustained drift and direction-of-worse moves; ignore blips
- 4 Cross-check flagged series against recent changes for a cause
- 5 Deliver the weekly read: what's drifting, since when, and what likely moved it
Every chart read, every week
The dashboards finally have a reader. Drift gets surfaced while it's a trend, not a page, with the likely cause already attached.
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.” 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.” 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.” 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.”