Skip to main content
Welcome to Tembo Automation Examples! This guide contains practical automation ideas and best practices to help you get started with building powerful automations on Tembo.

​
Getting Started

Tembo automations allow you to build intelligent workflows that run on a schedule or are triggered by events. Each automation has access to:
  • MCP Servers: Connect to external services (GitHub, Linear, Slack, etc.)
  • AI Models: Use Claude and other AI models to analyze and generate content
  • Scheduling: Run automations on a schedule (hourly, daily, weekly, monthly)
  • Triggers: React to events from your integrations

​
Best Practices

​
1. Start Simple and Iterate

Begin with straightforward automations that solve clear problems. Don’t try to automate everything at once. Good first automation: Daily changelog summary Avoid starting with: Complex multi-step workflows with many conditionals

​
2. Use Clear, Specific Prompts

Your automation prompt should be:
  • Specific: Define exactly what you want to happen
  • Structured: Use numbered steps or bullet points
  • Error-aware: Include instructions for edge cases
Example - Vague Prompt: 
Check for new issues and do something with them
Example - Clear Prompt: 
1. Find Linear issues created in the last 24 hours with label "bug"
2. For each issue, check if it has reproduction steps
3. If missing reproduction steps, comment: "Please add reproduction steps to help us fix this faster"
4. If it has reproduction steps, add label "triaged"

​
3. Test with Dry Runs

Before enabling an automation that posts to Slack or creates issues:
  1. Test with a private Slack channel or test repository
  2. Review the first few runs manually
  3. Adjust the prompt based on actual output
  4. Enable for production channels once validated

​
4. Schedule Appropriately

Choose the right frequency for your automation:
  • Hourly: Event monitoring (new tags, CI failures)
  • Daily: Summaries and digests (changelog, standup updates)
  • Weekly: Reports and reminders (stale issues, metrics)
  • Monthly: Long-term trends and cleanup tasks
Avoid over-polling APIs. Most information doesn’t need minute-by-minute updates.

​
5. Format for Readability

Use Slack Block Kit or Markdown to make automation outputs easy to scan: Good: 
✨ New Features
• User authentication - PR #123
• Dark mode support - PR #456

🐛 Bug Fixes
• Fixed login redirect - PR #789
Bad: 
New feature user authentication in PR 123 and dark mode in PR 456. Also fixed bug with login redirect in PR 789.
Always provide links back to the source:
  • GitHub PR or issue links
  • Linear issue links
  • Commit SHAs for code changes
  • Direct links to logs or dashboards
This helps team members quickly jump to relevant information.

​
7. Handle Errors Gracefully

Your automation should handle common errors: 
1. Try to fetch data from API
2. If API returns an error:
   - Log the error
   - Post a brief error message to #automation-errors
   - Do not spam the team channel
3. If no data is found:
   - Skip posting (don't post "no updates")
4. Continue to next step

​
8. Respect Rate Limits

Be mindful of API rate limits:
  • GitHub: 5,000 requests/hour
  • Linear: Rate limits vary by plan
  • Slack: Different limits for posting vs reading
Tips:
  • Batch operations when possible
  • Cache data that doesn’t change frequently
  • Use webhooks instead of polling when available

​
9. Document Your Automations

For each automation, document:
  • Purpose: What problem does it solve?
  • Schedule/Trigger: When does it run?
  • Dependencies: What MCP servers does it need?
  • Output: Where does it post/what does it create?
  • Owner: Who maintains it?
This helps your team understand and maintain automations over time.

​
Getting Help