> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Criteria
> Define success conditions for agent tasks
Agents can validate their work against criteria before returning results.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Validation Flow"
A[🤖 Agent] --> B[📝 Output]
B --> C[✅ Criteria]
C -->|pass| D[📤 Return]
C -->|fail| E[🔄 Retry]
end
classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
classDef tool fill:#189AB4,stroke:#7C90A0,color:#fff
classDef check fill:#6366F1,stroke:#7C90A0,color:#fff
classDef result fill:#10B981,stroke:#7C90A0,color:#fff
class A,B agent
class C check
class D,E result
classDef agent fill:#8B0000,color:#fff
classDef tool fill:#189AB4,color:#fff
```
## Quick Start
```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import { Agent } from 'praisonai';
const agent = new Agent({
instructions: 'Write blog posts',
criteria: 'Must be at least 500 words and include 3 key points'
});
const result = await agent.chat('Write about AI trends');
// Agent validates output meets criteria before returning
```
```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
const agent = new Agent({
criteria: [
'Contains at least 500 words',
'Includes an introduction',
'Has actionable takeaways'
]
});
```
***
## User Interaction Flow
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Agent
participant Validator
User->>Agent: "Write an article"
Agent->>Agent: Generate content
Agent->>Validator: Check criteria
alt Passes
Validator-->>Agent: ✅ Valid
Agent-->>User: Final output
else Fails
Validator-->>Agent: ❌ Retry
Agent->>Agent: Improve and retry
end
```
***
## Configuration Levels
```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
// Level 1: String - Simple criteria
const agent = new Agent({
criteria: 'Must be professional and concise'
});
// Level 2: Array - Multiple criteria
const agent = new Agent({
criteria: [
'At least 300 words',
'Includes examples',
'No jargon'
]
});
// Level 3: Dict - With options
const agent = new Agent({
criteria: {
rules: ['professional', 'concise'],
maxRetries: 3,
strict: true
}
});
```
***
## Criteria Options
| Option | Description |
| ------------ | ------------------------- |
| `rules` | List of validation rules |
| `maxRetries` | Attempts before failing |
| `strict` | Fail on any criteria miss |
***
## API Reference
Agent configuration including criteria
***
## Best Practices
"At least 500 words" is better than "long enough".
Criteria the agent can verify work best.
Prevent infinite loops with maxRetries.
***
## Related
Self-improvement
Output formats