Learning Feature

Introduction

The Learning feature helps your assignments improve over time. When an assignment 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 assignment: "This is how you should handle this type of task." By marking a successful run as a learning, you help the assignment understand what good looks like.

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


Why Use Learning?

Improve Consistency

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

Handle Edge Cases

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

Refine Over Time

As you work with an assignment, 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 assignment learn from examples of good work.


How to Create a Learning

From Past Jobs

  1. Go to your assignment's job history

  2. Find a run that completed the task excellently

  3. Click the Create Learning button at the top of the run

  4. The assignment will now reference this run for guidance

From Current Runs

While viewing a run in progress or just completed:

  1. If the run is going well, look for the Create Learning option

  2. Click to save this run as a learning

  3. Future runs will benefit from this example


How Learning Works

When you create a learning:

  1. The assignment analyzes what made that run successful

  2. It extracts patterns and approaches used

  3. Future runs reference this learning for guidance

  4. The assignment applies similar approaches to new tasks

The learning becomes part of how the assignment 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 assignment 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 assignment 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 assignment 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 assignment now knows how to handle similar complex invoices.

Example 3: Report Generation

Your assignment 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

Single Learning

Assignments carry only one learning at a time:

  • New learnings overwrite previous ones

  • Choose your best example carefully

  • You can always update the learning later

Not Visible in Instructions

The learning influences behavior but:

  • Isn't shown directly in the instructions

  • Works behind the scenes

  • Complements your written instructions

Task-Specific

Learnings work best when:

  • The task is similar to the learned example

  • Inputs are comparable

  • Expected outputs are consistent


Things to Know

  • Learning helps assignments improve through positive examples

  • Only one learning can be active per assignment

  • Creating a new learning replaces the previous one

  • Learnings work alongside your written instructions

  • Choose runs that represent your best outcomes

Last updated