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

# Learning Feature

> Capture a successful run as a learning so an agent replicates that good example and improves over time.

## Introduction

The Learning feature helps your agents improve over time. When an agent completes a task particularly well, you can capture that success as a "learning" that guides future runs.

## What is Learning?

Learning allows you to tell an agent: "This is how you should handle this type of task." By marking a successful run as a learning, you help the agent understand what good looks like.

Think of it as positive reinforcement—showing the agent an example of excellent work so it can replicate that success.

## Why Use Learning?

### Improve Consistency

When an agent handles a task perfectly, capture that approach so future runs follow the same pattern.

### Handle Edge Cases

If an agent successfully navigates a tricky situation, save that learning so it knows how to handle similar cases.

### Refine Over Time

As you work with an agent, you can continuously improve it by adding learnings from its best performances.

### Reduce Instruction Complexity

Instead of writing detailed instructions for every scenario, let the agent learn from examples of good work.

## How to Create a Learning

<Tabs>
  <Tab title="From Past Runs">
    <Steps>
      <Step title="Open your run history" icon="history">
        Go to your agent's run history.
      </Step>

      <Step title="Find an excellent run" icon="search">
        Find a run that completed the task excellently.
      </Step>

      <Step title="Create the learning" icon="graduation-cap">
        Click the **Create Learning** button at the top of the run.
      </Step>

      <Step title="Reference it going forward" icon="arrow-right">
        The agent will now reference this run for guidance.
      </Step>
    </Steps>
  </Tab>

  <Tab title="From Current Runs">
    While viewing a run in progress or just completed:

    <Steps>
      <Step title="Spot a strong run" icon="thumbs-up">
        If the run is going well, look for the **Create Learning** option.
      </Step>

      <Step title="Save it as a learning" icon="graduation-cap">
        Click to save this run as a learning.
      </Step>

      <Step title="Benefit on future runs" icon="arrow-right">
        Future runs will benefit from this example.
      </Step>
    </Steps>
  </Tab>
</Tabs>

## How Learning Works

When you create a learning:

<Steps>
  <Step title="The agent analyzes the run" icon="search">
    The agent analyzes what made that run successful.
  </Step>

  <Step title="It extracts patterns" icon="shapes">
    It extracts patterns and approaches used.
  </Step>

  <Step title="Future runs reference it" icon="book-open">
    Future runs reference this learning for guidance.
  </Step>

  <Step title="It applies the approach" icon="wand-sparkles">
    The agent applies similar approaches to new tasks.
  </Step>
</Steps>

The learning becomes part of how the agent approaches its work—like institutional knowledge that improves performance.

## Best Practices

### Choose Representative Examples

Select runs that:

* Completed the task correctly
* Handled the typical case well
* Demonstrate the approach you want
* Produced the output quality you expect

### Avoid Edge Cases Initially

Don't make unusual situations the learning:

* Start with standard, successful runs
* Edge cases can create unexpected patterns
* Build a foundation with typical examples

### One Learning at a Time

Each agent carries only one learning:

* Creating a new learning replaces the old one
* Choose your best example
* Update when you find a better example

### Review Results

After creating a learning:

* Monitor subsequent runs
* Verify the learning improves performance
* Adjust if results aren't as expected

## Real-World Examples

### Example 1: Email Responses

Your agent drafts customer responses. One response was particularly well-written—professional tone, addressed all concerns, and followed brand guidelines perfectly.

**Create a learning from this run.** Now future responses will follow this high-quality example.

### Example 2: Data Processing

Your agent extracts data from invoices. One run correctly handled a complex invoice with multiple line items and applied the right categorization.

**Create a learning from this run.** The agent now knows how to handle similar complex invoices.

### Example 3: Report Generation

Your agent creates weekly reports. One report had exactly the right structure, formatting, and level of detail.

**Create a learning from this run.** Future reports will follow this successful template.

## Limitations

<AccordionGroup>
  <Accordion title="Single Learning" icon="layers">
    Agents carry only one learning at a time:

    * New learnings overwrite previous ones
    * Choose your best example carefully
    * You can always update the learning later
  </Accordion>

  <Accordion title="Not Visible in Instructions" icon="eye-off">
    The learning influences behavior but:

    * Isn't shown directly in the instructions
    * Works behind the scenes
    * Complements your written instructions
  </Accordion>

  <Accordion title="Task-Specific" icon="target">
    Learnings work best when:

    * The task is similar to the learned example
    * Inputs are comparable
    * Expected outputs are consistent
  </Accordion>
</AccordionGroup>

## Things to Know

* Learning helps agents improve through positive examples
* Only one learning can be active per agent
* Creating a new learning replaces the previous one
* Learnings work alongside your written instructions
* Choose runs that represent your best outcomes