1

Check Model Capability

If your agent isn’t following instructions correctly, especially with longer or complex prompts:

  1. Check if you’re using a lightweight model (e.g., 4o-mini)
  2. Switch to a more capable model like gpt-4o
2

Review Prompt Structure

If the issue persists:

  1. Check if your prompt structure is too complex
  2. Follow prompt engineering guide
  3. Break down complex tasks into clear, sequential steps
  4. Add explicit transition conditions between different steps

Was this page helpful?

Troubleshooting Transcript AccuracyDebug call transfer failure