Building Your Mission Control

Interact with the Notion database using the Notion API.

POST https://api.notion.com/v1/pages (to create)
POST https://api.notion.com/v1/databases/{db_id}/query (to query)
Headers: Authorization: Bearer {NOTION_TOKEN}, Notion-Version: 2022-06-28, Content-Type: application/json

For creating pages: structure properties to match the database schema.
For querying: use filters and sorts to get relevant entries.
Handle rich text by wrapping content in the proper block format.

If the API returns 429 (rate limited), wait 1 second and retry. Max 3 retries.

TASK INTELLIGENCE: Build smart task queries — 'what's overdue?', 'what's due today?', 'what's my highest priority item?', 'show me all tasks tagged #work due this week'

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 3: "CALENDAR INTEGRATION") 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.

Fetch today's calendar events using the Google Calendar API.

GET https://www.googleapis.com/calendar/v3/calendars/{calendarId}/events?timeMin={todayStart}&timeMax={todayEnd}&orderBy=startTime&singleEvents=true

For each event, extract: summary (title), start/end time, location, attendees (names + emails), description.
Sort chronologically. Flag any conflicts (overlapping events).
Format each event as: "9:00-10:00 AM | Team Standup | Conference Room B | 5 attendees"

If no events today, return "No events scheduled today."

Fetch unread emails from Gmail using the Gmail API.

GET https://gmail.googleapis.com/gmail/v1/users/me/messages?q=is:unread&maxResults=20

For each message, GET the full message to extract: sender, subject, date, snippet.
Classify each email:
- 🔴 Urgent: needs reply today (from known contacts, contains "urgent", "ASAP", time-sensitive)
- 🟡 Action Required: needs a response but not time-critical
- 🔵 FYI: newsletters, notifications, CC'd threads
- ⚪ Low Priority: automated receipts, marketing

Return: total unread count, then the top 5 by urgency with sender, subject, and classification.

Use the OpenWeatherMap API to fetch weather data for the user's location.

GET https://api.openweathermap.org/data/2.5/forecast?q={city}&appid={api_key}&units=imperial

Extract: current temperature, conditions, humidity, wind speed, and rain probability.
Format concisely: "72°F, Partly Cloudy, 45% humidity, 8mph wind, 10% rain"

If the API returns an error, retry once with a 2-second delay. If it fails again, use "Weather data unavailable" as a placeholder and continue with the remaining steps.

Analyze the input and classify it into the defined categories.

Classification approach:
1. Extract key signals from the content (keywords, sender, urgency markers, topic)
2. Match against category definitions
3. Assign confidence score (high/medium/low)
4. For ambiguous cases, classify as the more important/urgent category (err on the side of caution)

Output for each item: { category, priority, confidence, reasoning }

If an item could belong to multiple categories, pick the primary one and note the secondary.

Send the compiled content via email using the configured email API.

Compose the email:
- To: {recipient_email}
- Subject: {subject_line}
- Body: Format as clean HTML with proper headings, bullet points, and styling.
  Use inline CSS for compatibility. Keep it mobile-friendly (max-width: 600px).

Send via the configured email provider (SendGrid, Resend, or SES).
Verify the response indicates successful delivery (202 for SendGrid, 200 for Resend).
Log: timestamp, recipient, subject, and delivery status.

If send fails, retry once after 3 seconds. If it fails again, save the email content locally and alert the user.

Compile the gathered data into a structured report.

Format as clean Markdown with:
- Title/date header
- Executive summary (2-3 sentences)
- Key metrics section with actual numbers
- Detailed sections with bullet points
- Action items or recommendations at the end

Keep it scannable — busy people read reports in 30 seconds.
Use emoji sparingly for visual anchors (📊 metrics, ✅ wins, ⚠️ concerns, 📋 action items).
Include data comparisons: "X this period vs Y last period (↑Z%)"

If any data source was unavailable, note it clearly: "⚠️ [Source] data unavailable — excluded from this report."

WEEKLY REVIEW: Sunday evening — week in review with completion rates, productivity trends, upcoming week preview, and suggested time blocks for deep work

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.

Monitor the data for anomalies and trigger alerts when thresholds are exceeded.

Detection rules:
1. Compare current values against defined thresholds
2. Check for sudden changes (>X% deviation from rolling average)
3. Look for pattern breaks (missing expected data, unusual timing)
4. Cross-reference multiple signals for higher confidence

For each detected anomaly:
- Severity: 🔴 Critical (immediate action) / 🟡 Warning (attention needed) / 🔵 Info (notable)
- What: specific metric and current value
- Why: what threshold or pattern was violated
- Context: recent trend, baseline comparison
- Suggested action: what to do about it

Suppress duplicate alerts — don't re-alert for the same issue within the configured cooldown period.

NATURAL LANGUAGE INTERFACE: Wire up conversational commands — 'add task: review Q4 report, P2, due Friday', 'what's on my plate today?', 'reschedule my 3pm to tomorrow', 'draft a reply to Sarah's email about the proposal'

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.

CONNECT OTHER COOKBOOKS: Mission Control is your hub. As you build other cookbook agents (fitness, finance, sales), have them report status into Mission Control's activity feed and alert system. Your fitness agent can post 'Workout completed: Push day, 45min' to the feed. Your sales agent can alert 'New lead scored 85+ in pipeline'.

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.