Iterate on Tembo’s pull requests using natural language feedback directly in GitHub or GitLab.

How it works

  1. Initial Solution - Tembo creates a pull request to solve an issue
  2. Review & Comment - You review the PR and leave feedback mentioning “@tembo”
  3. Automatic Retry - Tembo processes your feedback and updates the PR with improvements
  4. Iteration - Continue providing feedback until you’re satisfied

Using Feedback

Option 1: Use GitHub’s PR Review function

  • Submit a normal PR review - no need to mention “@tembo”
  • Tembo automatically processes all review feedback

Option 2: Comment in threads

  • Mention “@tembo” in your comment for detection
@tembo Add error handling for the database connection
@tembo Use TypeScript interfaces instead of any types

Tembo responds with:

  • 👀 Acknowledges your feedback
  • 🚀 Starts processing changes
  • New commits with improvements

Best Practices

✅ Be specific:

@tembo Add input validation for the email field using regex

❌ Too vague:

@tembo fix the validation

Types of improvements Tembo can make:

  • Performance optimization
  • Error handling and logging
  • Code structure and refactoring
  • Type safety improvements
  • Testing and documentation

Configuration

Feedback Loop: Enabled by default

External PR tools: If you use tools like Diamond, enable integration in your Workspace settings.


You are responsible for all merged code. Read our AI First Software Development guide for more information.