> ## 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.
# Self Reflection
> Let agents evaluate and refine their own responses before delivery
Enable `reflection=True` on an agent and it critiques its own answer before returning — improving quality within the same task.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="Analyst",
instructions="Provide thorough, accurate analysis.",
reflection=True,
)
agent.start("Summarise recent AI safety developments")
```
The user asks a question; the agent drafts an answer, reflects on quality, then returns the improved response.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Self-Reflection Loop"
In[Input] --> Agent[Agent]
Agent --> Draft[Draft answer]
Draft --> Reflect{Reflect}
Reflect -->|improve| Agent
Reflect -->|satisfied| Out[Output]
end
classDef input fill:#6366F1,stroke:#7C90A0,color:#fff
classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
classDef gate fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class In input
class Agent,Draft agent
class Reflect gate
class Out output
```
## Quick Start
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="Analyst",
instructions="Provide thorough, accurate analysis.",
reflection=True,
)
agent.start("Summarise recent AI safety developments")
```
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, ReflectionConfig
agent = Agent(
name="Analyst",
instructions="Provide thorough, accurate analysis.",
reflection=ReflectionConfig(
min_iterations=1,
max_iterations=3,
llm="gpt-4o",
prompt="Check accuracy, completeness, and clarity.",
),
)
agent.start("Summarise recent AI safety developments")
```
***
## How It Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant U as User
participant A as Agent
participant R as Reflection pass
U->>A: Prompt
A->>A: Generate draft
loop min to max iterations
A->>R: Evaluate draft
R-->>A: Improve or accept
end
A-->>U: Final answer
```
After each response, the agent runs one or more reflection passes (between `min_iterations` and `max_iterations`). Each pass asks whether the answer meets quality criteria; if not, the agent revises before returning.
***
## Configuration Options
Full parameter reference for ReflectionConfig
**Precedence ladder** — choose the level you need:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Level 1: Bool (simplest — enable with defaults)
agent = Agent(reflection=True)
# Level 2: ReflectionConfig (full control)
agent = Agent(reflection=ReflectionConfig(
min_iterations=1,
max_iterations=3,
llm="gpt-4o",
prompt="Evaluate for accuracy, completeness, and clarity.",
))
```
| Option | Type | Default | Description |
| ---------------- | ------------- | ------- | ---------------------------------------------- |
| `min_iterations` | `int` | `1` | Minimum reflection passes |
| `max_iterations` | `int` | `3` | Maximum reflection passes |
| `llm` | `str \| None` | `None` | Model for reflection (defaults to agent model) |
| `prompt` | `str \| None` | `None` | Custom evaluation prompt |
***
## Choosing Reflection Strength
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
Q{Need higher quality?} -->|No| Off[reflection=False
fastest]
Q -->|Yes| Q2{Latency budget?}
Q2 -->|Tight| Light[reflection=True
defaults 1–3]
Q2 -->|Flexible| Heavy[ReflectionConfig
max_iterations=5]
classDef q fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef opt fill:#189AB4,stroke:#7C90A0,color:#fff
classDef off fill:#6366F1,stroke:#7C90A0,color:#fff
class Q,Q2 q
class Light,Heavy opt
class Off off
```
***
## Best Practices
Reflection adds an extra LLM pass per turn. Set `reflection=False` on agents that call tools frequently to keep latency down.
Use `ReflectionConfig(llm="gpt-4o")` when the main model is fast but you want a stronger critic.
`reflection` improves *this* answer within the task. `self_improve` captures reusable skills for *next* time — they compose independently.
Cap `max_iterations` in production to avoid runaway loops on open-ended prompts.
***
## Related
Capture reusable skills after each task
Validate agent outputs with policies
Let agents plan before acting
Configure agent execution limits