> ## Documentation Index
> Fetch the complete documentation index at: https://agent-observability-docs.splunk.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Reducing Hesitation and Uncertainty

> Learn how to reduce hesitation and uncertainty in your AI models

Some models struggle to confidently generate responses, leading to hesitation, incomplete answers, or repeated disclaimers.

For example, consider this prompt and response:

```text theme={null}
Prompt: "Tell me about climate change."
```

<Card>
  Model Response: "Well, there are many aspects to climate change. Some people
  think it's caused by humans, and others think it's just natural. It's hard to
  say exactly."
</Card>

## What went wrong?

* The prompt did not provide enough context for confident decision-making
* The model allowed too much randomness in token selection
* The prompt was ambiguous in the response it expected

## How it showed up in evaluators

* **High Uncertainty**: The model hesitated in its response
* **High Prompt Perplexity**: The model struggled with predicting the next token
* **Mid-range Instruction Adherence**: The model understood the instructions but lacked decisiveness

## Improvements and solutions

For the following improvements, we will be showing how we could change a simple prompt script like the below example:

<CodeGroup>
  ```python Python theme={null}
  import os
  from splunk_ao.openai import openai
  from dotenv import load_dotenv
  load_dotenv()

  client = openai.OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

  prompt = "Tell me about climate change."
  response = client.chat.completions.create(
  model="gpt-4o",
  messages=[{"role": "system", "content": prompt}],
  )
  print(response.choices[0].message.content.strip())
  ```
</CodeGroup>

<Steps>
  <Step title="Provide Stronger Context in Prompts">
    Include explicit guiding statements, for example:

    <CodeGroup>
      ```python example.py theme={null}
        prompt = """Tell me about climate change.
          Assume the following is true:
          1. Climate change is driven by human activity.
          2. Provide an explanation based on scientific evidence."""
      ```
    </CodeGroup>

    This should reduce the uncertainty and perplexity in your evaluators on Splunk Agent Observability.
  </Step>

  <Step title="Adjust Model Sampling Parameters">
    Lower **temperature** to make the model more deterministic, for example:

    <CodeGroup>
      ```python example.py theme={null}
      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[{"role": "user", "content": "Tell me a joke."}],
          temperature=0.3  # Reduced temperature for more predictable responses
      )
      ```
    </CodeGroup>

    Use **top-k sampling** to limit options and prevent hesitation, for example:

    <CodeGroup>
      ```python example.py theme={null}
      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[{"role": "user", "content": "Tell me about climate change."}],
          # This is often how top k would be set.
          # In practice, ChatGPT does not allow modifying top-k, but other models do
          top_k=50  # Limits token selection to the top 50 choices
      )
      ```
    </CodeGroup>

    Lowering the `temperature` and decreasing `top_k` both generally increase the prompt adherence.
  </Step>

  <Step title="Modify Prompt Structure">
    Use direct phrasing to force a single, clear response, for example:

    {" "}

    <CodeGroup>
      `python example.py prompt = "Provide a single, definitive explanation of climate change in two sentences." `
    </CodeGroup>

    Avoid prompts that allow multiple equally valid answers, for example avoiding confusing by adding the source of the opinion we care about:

    <CodeGroup>
      ```python example.py theme={null}
      prompt = "What are the primary causes of climate change according to scientists?"
      ```
    </CodeGroup>
  </Step>

  <Step title="Apply Uncertainty-Based Filtering">
    Automatically reject responses with an **Uncertainty** score above a set threshold
  </Step>
</Steps>