Create Your First Task

Let’s build your first Rightbrain Task. In this quickstart, we’ll draft a prompt, structure your outputs and choose an appropriate model for the job.

Understanding Task Components

Before we start, let’s understand the four core components of every Task:

💬 Instructions - Craft clear prompts that tell the model exactly what to do and how to behave.

🧩 Dynamic Inputs - Use placeholders, such as {customer_review}, to insert real input data at runtime

📊 Structured Outputs - Define your expected fields and schema to ensure consistent, predictable responses.

🧠 Model Selection - Choose the model that best balances speed, cost, and capability for your use case.

Step 1: Set Your Prompts

First, we’ll compose the Task instructions using the user prompt. For this demo, we’re building a sentiment analysis Task that can also verify product images.

User Prompt

Navigate to the user prompt field and enter:

Please conduct a comprehensive sentiment analysis on the {customer_review} and describe the product image (if one is included). Verify that the image matches the product described in the review.

Notice the {customer_review} variable - this is a dynamic placeholder that gets replaced with actual data when the Task runs. The Task is also designed to handle optional image inputs.

System Prompt (Optional)

You can add a system prompt to define the AI’s role and behavior:

You are an expert product review analyst specializing in e-commerce sentiment analysis and visual verification.

Step 2: Configure Inputs and Outputs

Now we’ll define what data goes in and what structure comes out.

Define Input Variables

Your Task can accept:

• Text strings – simple text inputs like support tickets, reviews or any text data feed.
• Images – visual inputs such as product photos, receipts, or screenshots for multimodal analysis and verification.
• Documents – commonly Word, PDF, PPT or CSV files for data extraction, summarisation or classification.
• URLs – web addresses that the Task can fetch and analyse for content, metadata or linked resources.
• Web Search - a live search via Perplexity that returns up to the top 20 results for further analysis.

For our Task, the {customer_review} variable is automatically detected from your prompt. You can add additional inputs if needed.

Specify Output Structure

Define exactly what data structure you want back. This ensures every Task execution returns consistent, parseable results.

Add these outputs to your Task manually or by pasting the JSON schema:

Step 3: Choose Model and Configure Settings

Select Your Model

Different models excel at different tasks. For our sentiment analysis with image verification, we need a vision-capable model:

Configure Task Settings

What’s Next?