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

# PROMPT LIBRARY

> Examples for building, evaluating, and managing models with the Oumi Agent.

The following prompts enable a range of machine learning tasks and workflows, including model development, data generation, evaluation, and project management, to name a few.

<Info>Please note that while this collection highlights common use cases, it represents only a subset of the Oumi Agent’s full capabilities.</Info>

***

## END-TO-END MODEL BUILDING

<AccordionGroup>
  <Accordion title="Build a customer support bot">
    Build a full workflow to create a model that handles customer inquiries.

    ```prompt theme={null}
    Help me build a custom model for handling customer support tickets, including refunds, billing questions, and shipping issues
    ```
  </Accordion>

  <Accordion title="Build a coding assistant">
    Build an end-to-end workflow for a code-focused model.

    ```prompt theme={null}
    Build me a coding assistant that can explain errors, generate code snippets, and review pull requests
    ```
  </Accordion>

  <Accordion title="Build an education tutor">
    Create a tutoring model for students

    ```prompt theme={null}
    Help me train a model that tutors middle school students in algebra, explaining concepts step by step
    ```
  </Accordion>

  <Accordion title="Build a brand voice model">
    Train a model that mimics a specific tone and style

    ```prompt theme={null}
    I want to build a model that writes marketing copy in our brand voice: friendly, concise, and professional
    ```
  </Accordion>

  <Accordion title="Build a medical triage assistant">
    Create a model for initial patient intake

    ```prompt theme={null}
    Help me create a model that performs initial medical triage by asking patients about symptoms and suggesting urgency levels
    ```
  </Accordion>

  <Accordion title="Build a legal document summarizer">
    Train a model to summarize legal texts

    ```prompt theme={null}
    Build me a model that summarizes legal contracts into plain-language bullet points for non-lawyers
    ```
  </Accordion>

  <Accordion title="Build a sales email generator">
    Create a model for drafting outbound sales emails

    ```prompt theme={null}
    Help me train a model that drafts personalized cold outreach emails based on prospect company and role
    ```
  </Accordion>

  <Accordion title="Build a content moderator">
    Train a model to flag inappropriate content

    ```prompt theme={null}
    Build a content moderation model that classifies user-generated posts as safe, needs review, or policy violation
    ```
  </Accordion>
</AccordionGroup>

***

## DATA SYNTHESIS: GENERAL

<AccordionGroup>
  <Accordion title="Generate training data from scratch">
    Create a synthetic dataset for a specific task.

    ```prompt theme={null}
    Generate 500 synthetic training examples for a customer support chatbot that handles refund requests, billing disputes, and account issues
    ```
  </Accordion>

  <Accordion title="Generate diverse scenario data">
    Create data covering a wide range of situations.

    ```prompt theme={null}
    Generate a training dataset with diverse scenarios for a travel booking assistant, covering flights, hotels, cancellations, and itinerary changes
    ```
  </Accordion>

  <Accordion title="Generate multi-turn conversations">
    Create data with realistic back-and-forth dialogue.

    ```prompt theme={null}
    Generate synthetic multi-turn conversations between a user and a technical support Agent troubleshooting Wi-Fi connectivity issues
    ```
  </Accordion>

  <Accordion title="Generate edge case data">
    Create data targeting tricky or unusual inputs.

    ```prompt theme={null}
    Generate training data focused on edge cases for a food ordering bot: ambiguous orders, dietary restrictions, out-of-stock items, and off-topic requests
    ```
  </Accordion>

  <Accordion title="Generate data with specific tone">
    Create data that follows a particular communication style.

    ```prompt theme={null}
    Generate training examples for a friendly, casual chatbot that helps users pick outfit recommendations based on occasion and weather
    ```
  </Accordion>

  <Accordion title="Generate classification data">
    Create labeled data for classification tasks.

    ```prompt theme={null}
    Generate 300 examples of customer feedback classified into categories: product quality, shipping speed, customer service, and pricing
    ```
  </Accordion>

  <Accordion title="Generate structured output data">
    Create data where responses follow a specific format.

    ```prompt theme={null}
    Generate training examples where the assistant responds with structured JSON containing fields: intent, confidence, and suggested_action
    ```
  </Accordion>

  <Accordion title="Generate test/evaluation data">
    Create a held-out dataset for evaluation purposes.

    ```prompt theme={null}
    Generate 100 evaluation examples for a customer support bot covering common and edge-case scenarios to use as a test set
    ```
  </Accordion>
</AccordionGroup>

***

## DATA SYNTHESIS: IMPROVED SAMPLES

<AccordionGroup>
  <Accordion title="Improve existing dataset quality">
    Refine and enhance samples in an existing dataset.

    ```prompt theme={null}
    Improve the quality of samples in my existing dataset by making responses more detailed, accurate, and consistent in tone
    ```
  </Accordion>

  <Accordion title="Fix low-scoring samples">
    Target improvements on data that scored poorly in evaluation.

    ```prompt theme={null}
    Improve the samples in my dataset that scored low on helpfulness and accuracy based on my evaluation results
    ```
  </Accordion>
</AccordionGroup>

***

## DATA SYNTHESIS: GENERATE COMPLETIONS

<AccordionGroup>
  <Accordion title="Add responses to prompts">
    Generate model completions for a prompt-only dataset.

    ```prompt theme={null}
    Generate completions for my prompt-only dataset using GPT-4o
    ```
  </Accordion>

  <Accordion title="Replace existing completions">
    Re-generate responses with a different model.

    ```prompt theme={null}
    Generate new completions for my dataset, replacing the existing responses, using Claude
    ```
  </Accordion>

  <Accordion title="Generate completions with system instruction">
    Add responses with a specific persona or behavior.

    ```prompt theme={null}
    Generate completions for my dataset using GPT-4o with the system instruction: You are a helpful and concise technical support Agent
    ```
  </Accordion>

  <Accordion title="Generate completions with custom temperature">
    Control response creativity/randomness.

    ```prompt theme={null}
    Generate completions for my dataset using a temperature of 0.3 for more deterministic responses
    ```
  </Accordion>
</AccordionGroup>

***

## MODEL TRAINING

<AccordionGroup>
  <Accordion title="Fine-tune with LoRA">
    Parameter-efficient fine-tuning on your data.

    ```prompt theme={null}
    Fine-tune a model on my training dataset using LoRA
    ```
  </Accordion>

  <Accordion title="Full fine-tune">
    Update all model weights for maximum customization.

    ```prompt theme={null}
    Set up full fine-tuning for my model on my training dataset
    ```
  </Accordion>

  <Accordion title="Train with on-policy distillation">
    Use a teacher model to train a student model.

    ```prompt theme={null}
    Train a model using on-policy distillation with a teacher model
    ```
  </Accordion>

  <Accordion title="Train with specific hyperparameters">
    Customize training configuration.

    ```prompt theme={null}
    Fine-tune a model on my dataset with 3 epochs, a learning rate of 2e-5, and LoRA rank 16
    ```
  </Accordion>

  <Accordion title="Train with validation set">
    Include a validation dataset for monitoring.

    ```prompt theme={null}
    Train a model on my training dataset and use my validation dataset to monitor training progress
    ```
  </Accordion>

  <Accordion title="Train on specific data">
    Point training at a known dataset.

    ```prompt theme={null}
    Fine-tune Llama on my customer support dataset
    ```
  </Accordion>
</AccordionGroup>

***

## EVALUATION: EVALUATOR/JUDGE CREATION

<AccordionGroup>
  <Accordion title="Create a helpfulness judge">
    Evaluate how helpful model responses are.

    ```prompt theme={null}
    Create an evaluator that judges how helpful and complete the model's responses are
    ```
  </Accordion>

  <Accordion title="Create an accuracy judge">
    Evaluate factual correctness.

    ```prompt theme={null}
    Create an evaluator that judges whether the model's responses are factually accurate and free of hallucinations
    ```
  </Accordion>

  <Accordion title="Create a safety judge">
    Evaluate responses for harmful content.

    ```prompt theme={null}
    Create an evaluator that judges whether responses are safe, avoiding harmful, biased, or inappropriate content
    ```
  </Accordion>

  <Accordion title="Create a tone judge">
    Evaluate communication style.

    ```prompt theme={null}
    Create an evaluator that judges whether the model maintains a friendly, professional tone throughout its responses
    ```
  </Accordion>

  <Accordion title="Create an instruction-following judge">
    Evaluate adherence to instructions.

    ```prompt theme={null}
    Create an evaluator that judges how well the model follows the specific instructions given in the user's prompt
    ```
  </Accordion>

  <Accordion title="Create a conciseness judge">
    Evaluate response brevity.

    ```prompt theme={null}
    Create an evaluator that judges whether responses are concise and to the point without unnecessary verbosity
    ```
  </Accordion>

  <Accordion title="Create a code quality judge">
    Evaluate generated code.

    ```prompt theme={null}
    Create an evaluator that judges the quality of generated code: correctness, readability, and adherence to best practices
    ```
  </Accordion>

  <Accordion title="Create a multi-axis evaluation suite">
    Set up multiple evaluators at once.

    ```prompt theme={null}
    Help me create evaluators for helpfulness, accuracy, safety, and tone for my customer support model
    ```
  </Accordion>
</AccordionGroup>

***

## EVALUATION: RUNNING EVALUATIONS

<AccordionGroup>
  <Accordion title="Run a baseline evaluation">
    Benchmark an unmodified model before training.

    ```prompt theme={null}
    Run a baseline evaluation on the base model using my test dataset and evaluators before I fine-tune it
    ```
  </Accordion>

  <Accordion title="Evaluate a fine-tuned model">
    Assess quality after training.

    ```prompt theme={null}
    Evaluate my fine-tuned model using the same test dataset and evaluators I used for the baseline
    ```
  </Accordion>

  <Accordion title="Evaluate a hosted model">
    Test an API model's performance on your task.

    ```prompt theme={null}
    Evaluate GPT-4o on my test dataset using my evaluators to see how it performs on my task
    ```
  </Accordion>

  <Accordion title="Compare two models">
    Benchmark two models side by side.

    ```prompt theme={null}
    Help me compare my fine-tuned model against the base model by running evaluations on both with the same dataset and evaluators
    ```
  </Accordion>

  <Accordion title="Evaluate with specific dataset">
    Run evaluation on a particular dataset.

    ```prompt theme={null}
    Run an evaluation on my model using my latest test dataset
    ```
  </Accordion>
</AccordionGroup>

***

## PROJECT EXPLORATION & RESOURCE MANAGEMENT

<AccordionGroup>
  <Accordion title="List all datasets">
    See what datasets exist in your project.

    ```prompt theme={null}
    List all my datasets
    ```
  </Accordion>

  <Accordion title="Preview dataset contents">
    Inspect what's inside a dataset.

    ```prompt theme={null}
    Show me what's inside my dataset. Preview the first few items.
    ```
  </Accordion>

  <Accordion title="List trained models">
    See models you've fine-tuned.

    ```prompt theme={null}
    Show me all the models I've trained
    ```
  </Accordion>

  <Accordion title="List evaluators">
    See available judges.

    ```prompt theme={null}
    What evaluators do I have set up?
    ```
  </Accordion>

  <Accordion title="List evaluations">
    See past evaluation runs.

    ```prompt theme={null}
    Show me all my evaluation runs and their results
    ```
  </Accordion>

  <Accordion title="Check job status">
    Monitor running operations.

    ```prompt theme={null}
    What's the status of my running jobs?
    ```
  </Accordion>

  <Accordion title="Find latest resource">
    Locate the most recently created item.

    ```prompt theme={null}
    Show me the most recently created dataset
    ```
  </Accordion>

  <Accordion title="List available models for training">
    See what models are available for fine-tuning.

    ```prompt theme={null}
    What models are available for training?

    ```
  </Accordion>

  <Accordion title="List available models for synthesis">
    See models you can use for data generation.

    ```prompt theme={null}
    What models can I use for data synthesis?
    ```
  </Accordion>

  <Accordion title="List available models for evaluation">
    See models you can use as judges.

    ```prompt theme={null}
    What models are available for evaluation?
    ```
  </Accordion>

  <Accordion title="Resume previous work">
    Pick up where you left off.

    ```prompt theme={null}
    Where did we leave off? What should I do next?
    ```
  </Accordion>

  <Accordion title="View failed operations">
    Investigate what went wrong.

    ```prompt theme={null}
    Show me any failed operations and what went wrong
    ```
  </Accordion>
</AccordionGroup>

***

## RESOURCE CLEANUP

<AccordionGroup>
  <Accordion title="Delete a dataset">
    Remove a dataset from the project.

    ```prompt theme={null}
    Delete my old test dataset
    ```
  </Accordion>

  <Accordion title="Delete a model">
    Remove a trained model.

    ```prompt theme={null}
    Delete the model I trained last week
    ```
  </Accordion>

  <Accordion title="Delete an evaluation">
    Remove an evaluation run.

    ```prompt theme={null}
    Delete my failed evaluation run
    ```
  </Accordion>

  <Accordion title="Delete an evaluator">
    Remove a judge configuration.

    ```prompt theme={null}
    Delete the evaluator I'm no longer using
    ```
  </Accordion>
</AccordionGroup>

***

## PLATFORM KNOWLEDGE

<AccordionGroup>
  <Accordion title="Explain training methods">
    Understand SFT vs OPD.

    ```prompt theme={null}
    What training methods do you support and when should I use each?
    ```
  </Accordion>

  <Accordion title="Explain LoRA vs full fine-tuning">
    Understand parameter update strategies.

    ```prompt theme={null}
    What's the difference between LoRA and full fine-tuning? Which should I choose?
    ```
  </Accordion>

  <Accordion title="Explain synthesis types">
    Understand data generation options.

    ```prompt theme={null}
    What types of data synthesis are available and when should I use each?
    ```
  </Accordion>

  <Accordion title="Explain evaluation workflow">
    Understand how evaluation works.

    ```prompt theme={null}
    How does the evaluation workflow work? What do I need to set up?
    ```
  </Accordion>

  <Accordion title="Explain on-policy distillation">
    Understand teacher-student training.

    ```prompt theme={null}
    What is on-policy distillation and when should I use it instead of SFT?
    ```
  </Accordion>

  <Accordion title="Understand the full workflow">
    Get an overview of the end-to-end process.

    ```prompt theme={null}
    Walk me through the full workflow for building a custom model from scratch
    ```
  </Accordion>
</AccordionGroup>

***

## ITERATION & IMPROVEMENT

<AccordionGroup>
  <Accordion title="Analyze evaluation results">
    Understand what the scores mean.

    ```prompt theme={null}
    Help me analyze my evaluation results and identify where my model is weakest
    ```
  </Accordion>

  <Accordion title="Generate targeted training data">
    Create data to fix specific weaknesses.

    ```prompt theme={null}
    Generate more training data focused on the areas where my model scored lowest in evaluation
    ```
  </Accordion>

  <Accordion title="Retrain with adjustments">
    Modify training config and try again.

    ```prompt theme={null}
    Retrain my model with a lower learning rate and more epochs to see if results improve
    ```
  </Accordion>

  <Accordion title="Add new evaluator">
    Expand evaluation coverage.

    ```prompt theme={null}
    Add a new evaluator to measure conciseness. My model's responses are too long.
    ```
  </Accordion>

  <Accordion title="Re-evaluate after changes">
    ```prompt theme={null}
    Re-evaluate my model after changes to see if performance has improved.
    ```
  </Accordion>

  <Accordion title="Re-evaluate after retraining">
    Re-evaluate my model after retraining.

    ```prompt theme={null}
    Re-evaluate my model after retraining to see if the scores improved compared to the baseline
    ```
  </Accordion>
</AccordionGroup>

***

## TIPS FOR BEST RESULTS

* **Be specific:** Include details about your task, audience, and desired format for better results.
* **Provide context:** Tell the Agent about your use case, target users, and desired tone upfront.
* **Iterate:** After any step, ask the Agent to adjust configs, re-run with changes, or pivot.
* **Attach files:** Upload example data files in the chat to help the Agent understand your format and style.