What is a Goal?
A Goal contains:- Success Criteria - Measurable conditions that define success
- Constraints - Boundaries the agent must respect
- Context - Additional information for decision-making
Defining Success Criteria
Success criteria are measurable conditions that determine if your agent succeeded.Structure
Metric Types
Example
Defining Constraints
Constraints are boundaries your agent must respect during execution.Constraint Types
Categories
time- Execution time limitscost- Token/API cost limitssafety- Safety requirementsscope- What the agent should/shouldn’t doquality- Quality requirements
Example
Complete Example
Here’s a complete goal for a research agent:Best Practices
Do
- Use specific, measurable success criteria
- Include 3-5 success criteria with different weights
- Define hard constraints for critical requirements
- Add context to help the agent make better decisions
Don't
- Use vague criteria like “do a good job”
- Skip constraints entirely
- Set all weights to 1.0 (use relative importance)
- Forget to specify required capabilities
Next Steps
Node Types
Learn about LLM, Router, Function, and Human nodes
Edge Configuration
Configure success, failure, and conditional edges