> ## Documentation Index
> Fetch the complete documentation index at: https://futureagi.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart: Optimizing Your First Prompt

> A quick, hands-on guide to getting started with prompt optimization using the agent-opt Python library. Optimize your first prompt in minutes.

This guide will walk you through the essential steps to optimize your first prompt using the `agent-opt` Python library. We'll use the `RandomSearchOptimizer` to keep things simple and demonstrate the core workflow.

### 1. Installation and Setup

First, install the library and set up your environment variables to connect to Future AGI for evaluations. You can get your API keys from the [Future AGI dashboard](https://app.futureagi.com/dashboard/keys).

```bash theme={null}
pip install agent-opt
```

<CodeGroup>
  ```python Python theme={null}
  import os

  os.environ["FI_API_KEY"] = "YOUR_API_KEY"
  os.environ["FI_SECRET_KEY"] = "YOUR_SECRET_KEY"
  ```
</CodeGroup>

### 2. Prepare Your Dataset

Optimization is data-driven. You'll need a dataset, which is a simple list of Python dictionaries. For this example, we'll create a small dataset for a summarization task.

```python theme={null}
dataset = [
    {
        "article": "The James Webb Space Telescope has captured stunning new images of the Pillars of Creation, revealing intricate details of gas and dust clouds where new stars are forming.",
        "target_summary": "The JWST has taken new, detailed pictures of the Pillars of Creation."
    },
    {
        "article": "Researchers have discovered a new enzyme that can break down plastics at record speed, offering a potential solution to the global plastic pollution crisis.",
        "target_summary": "A new enzyme that rapidly breaks down plastics has been found."
    },
]
```

### 3. Configure and Run the Optimization

Now, let's set up the components and run the optimization. We'll configure an `Evaluator` to score our prompts, a `DataMapper` to connect our data, and the `RandomSearchOptimizer` to run the process.

<CodeGroup>
  ```python Python theme={null}
  from fi.opt.optimizers import RandomSearchOptimizer
  from fi.opt.generators import LiteLLMGenerator
  from fi.opt.datamappers import BasicDataMapper
  from fi.opt.base.evaluator import Evaluator

  # a. Define the generator with the initial prompt to be optimized
  initial_generator = LiteLLMGenerator(
      model="gpt-4o-mini",
      prompt_template="Summarize this: {article}"
  )

  # b. Setup the evaluator to score prompt performance
  evaluator = Evaluator(
      eval_template="summary_quality",  # A built-in template for summarization
      eval_model_name="turing_flash"    # The model to perform the evaluation
  )

  # c. Setup the data mapper to link dataset fields
  data_mapper = BasicDataMapper(
      key_map={"input": "article", "output": "generated_output"}
  )

  # d. Initialize the Random Search optimizer
  optimizer = RandomSearchOptimizer(
      generator=initial_generator,
      teacher_model="gpt-4o",  # A powerful model to generate prompt ideas
      num_variations=5         # Generate 5 different versions of our prompt
  )

  # e. Run the optimization!
  result = optimizer.optimize(
      evaluator=evaluator,
      data_mapper=data_mapper,
      dataset=dataset
  )
  ```
</CodeGroup>

### 4. Analyze the Results

The `result` object contains the best prompt found and its final score.

```python theme={null}
# Print the best prompt and its score
print(f"--- Optimization Complete ---")
print(f"Final Score: {result.final_score:.4f}")
print(f"Best Prompt Found:\n{result.best_generator.get_prompt_template()}")

# You can also review the history of all tried variations
for i, iteration in enumerate(result.history):
    print(f"\n--- Variation {i+1} ---")
    print(f"Score: {iteration.average_score:.4f}")
    print(f"Prompt: {iteration.prompt}")
```

### 5. Next Steps

You've successfully optimized your first prompt! From here, you can explore more advanced strategies.

<CardGroup cols={2}>
  <Card title="Optimizers Overview" icon="scale-balanced" href="/future-agi/get-started/optimization/optimizers/overview">
    Compare all available optimizers and find the best one for your task.
  </Card>

  <Card title="Python SDK Guide" icon="code" href="/future-agi/get-started/optimization/how-to/using-python-sdk">
    Take a deeper dive into the SDK's features and advanced configurations.
  </Card>
</CardGroup>