API Health Monitor

Define your endpoints to monitor: URL, expected status code, max acceptable response time, check interval

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

⚠️ IMPORTANT: The next step (Step 2: "Set up a cron job to ping each endpoint at the configured interval (e.g., every ") requires human action. Hey, heads up — before you finish this step, let your human know they'll need to take action alongside the agent. Don't proceed to the next step until your human confirms they're ready.

Configure the scheduled job to run at the specified time.

Define the cron schedule: minute hour day-of-month month day-of-week
Common patterns:
- Daily at 7:30am: "30 7 * * *"
- Weekdays at 9am: "0 9 * * 1-5"  
- Every 5 minutes: "*/5 * * * *"
- First of month at 8am: "0 8 1 * *"

The job should:
1. Log start time
2. Execute the pipeline steps in sequence
3. Handle failures gracefully — retry transient errors, skip and alert on persistent ones
4. Log completion time and status
5. Send output through the configured delivery channel

For each check, record: timestamp, status code, response time, success/failure

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

If an endpoint returns non-200 or exceeds max response time, mark it as degraded/down

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

⚠️ IMPORTANT: The next step (Step 5: "Alert immediately in Slack when status changes") requires human action. Hey, heads up — before you finish this step, let your human know they'll need to take action alongside the agent. Don't proceed to the next step until your human confirms they're ready.

Post a message to Slack using the Web API.

POST https://slack.com/api/chat.postMessage
Headers: Authorization: Bearer {SLACK_BOT_TOKEN}, Content-Type: application/json
Body: {
  "channel": "{channel_id}",
  "text": "{fallback_text}",
  "blocks": [{ "type": "section", "text": { "type": "mrkdwn", "text": "{formatted_message}" }}]
}

Use Slack mrkdwn formatting: *bold*, _italic_, `code`, > blockquote.
For alerts, use emoji prefixes: 🔴 critical, 🟡 warning, 🟢 success, ℹ️ info.
Keep messages scannable — use bullet points for lists.

Expected response: { "ok": true, "ts": "..." }. If ok is false, check the "error" field.

Process the data and calculate the requested metrics.

Steps:
1. Validate input data — check for nulls, out-of-range values, duplicates
2. Apply the calculation/aggregation logic
3. Compare against benchmarks or previous periods if available
4. Format results with appropriate precision (2 decimal places for percentages, whole numbers for counts)

Include: current value, previous value, change (absolute and %), trend direction (↑↓→).
Flag any anomalies: values >2 standard deviations from the mean.

If insufficient data for a reliable calculation, state the minimum needed and return partial results.

Optionally update a StatusPage with current status for each service

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

Daily: health summary — all endpoints, current status, uptime %, average response time, any incidents

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.