En garde! Building guardrails for our agent
This exercise is part of the course
Building AI Agents with Google ADK
Exercise instructions
Safety first! Equip your agent with some safety rails, so every response stays aligned with expectations:
- Use the
.SafetySetting()class to define how the agent should handle dangerous content. - Create a
.GenerateContentConfig()instance to bundle together safety settings with other content generation settings. - Pass these configurations to the agent as an argument.
Note: If you’re running DataLab in Restricted Mode, this exercise isn’t supported yet. We’re actively working on making it available in the future.
Hands-on interactive exercise
Turn theory into action with one of our interactive exercises
Start Exercise