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

# Create a study

> Create a study from goals to launch with the Study Builder.

This guide walks you through creating a study from start to finish. By the end, you have a live Researcher Agent ready to interview your users.

## Overview

Creating a study involves these steps:

1. Start a new study and describe your objective
2. Review and refine your goals in the builder chat
3. Configure your Agent, Outreach, Persona, Reward, and Interview Depth in the sidebar
4. Test your study with the embedded preview
5. Go live when ready

## Step 1: Start a new study

From your [dashboard](https://app.trypillow.ai), click **New** in the sidebar. Enter your study objective in plain language:

> Our purchase funnel is: browse, add to cart, enter payment, confirm order. We're seeing a big dropoff at the payment step. I want to understand what's causing users to leave at that point and what would get them to complete the purchase.

<Info>
  The more context you provide, the better the goals Pillow drafts.
</Info>

## Step 2: Review and refine goals

After you describe your objective, Pillow drafts a set of study goals. The builder can **search the web** for context on your product or market, and it **suggests goals** you might not have thought of.

Use the chat to refine your goals. Example prompts:

* "Add a goal about whether users trust us with their payment info"
* "Remove goal 3, we already know about cart abandonment"
* "Make the pricing goal more specific to the payment step"
* "Merge the last two goals into one"
* "Reorder goals to prioritize the dropoff reasons first"

### Reverting changes

To undo a change, click the revert icon next to any of your messages. This restores the goals to their previous state and places your message back in the input field.

Your goals decide what the agent covers, so more specific goals lead to more focused interviews.

### Adding images

You can attach up to 4 images to a builder message. Choose how each image should be used:

* **Show to users**: the image is saved with the relevant goals and participants can see it during the interview. Use this for UI screens, design mockups, ads, logos, packaging, or product photos you want reactions to.
* **Agent context**: the image is saved with notes as internal background for the Researcher Agent. Participants will not see it.

Goal cards only hold **Show to users** images. Click the image icon on a goal card to upload participant-visible images. Supported formats: PNG, JPEG, WebP.

### Adding notes

Notes are instructions your agent follows as ground truth, the fastest way to give it constraints, terminology, and context that don't fit into goals. Add them in the **Notes** panel. See [Steer your agent with notes](/guides/agent-notes).

## Step 3: Configure in the sidebar

The right sidebar panel provides quick access to configure your study. These settings are accessible at any time during the building process.

<Note>
  After you go live, these settings move into your study's **Settings** tabs: **Brief** (goals and persona), **Agent & Depth**, **Outreach**, **Reward**, and **Integration**.
</Note>

### Agent

Click **Agent** in the sidebar to customize your Researcher Agent:

* **First name**: Choose a friendly, human name (e.g., Sarah, Alex, Jordan)
* **Role**: Customize the text shown under the agent's name in the chat header. Use `{{org_public_name}}` to include your public organization name. For custom roles, turn on **Auto-translate role** to localize it for supported participant languages.
* **Gender**: Select **Female**, **Male**, or **Non-binary** (used for grammatical agreement in gendered languages)
* **Look**: Choose **Logo** (uses your organization logo), **Text** (auto-generated from the agent's name), or **Custom** (upload your own image or generate with AI)
* **Tone of voice**: Set the interview style
* **Reveal policy**: Control how the agent responds when asked if it's AI
* **Formal address**: Toggle on for languages with formal pronouns (vous, usted, Sie). When enabled, the agent uses the formal form of address.

### Interview depth

The Interview Depth slider in the sidebar controls how many questions the agent asks:

| Level        | Behavior                                                |
| ------------ | ------------------------------------------------------- |
| **Express**  | Fewest questions, no follow-ups; fast and broad         |
| **Quick**    | Brief interviews with minimal follow-ups                |
| **Balanced** | Default: a mix of coverage and depth                    |
| **Deep**     | More questions with follow-ups on interesting responses |

<Tip>
  Start with **Balanced** for most studies. Use **Express** for quick pulse checks and **Deep** when you need thorough exploration.
</Tip>

### Outreach

Click **Outreach** in the sidebar to set your opening message. This is the first message participants see:

> Hi, I'm `{{agent_name}}` from `{{org_public_name}}`. We're trying to make checkout smoother, and I'd love to hear about your last purchase. How did it go?

When you open the Outreach panel, Pillow drafts an opening message from your goals and agent. Click **Regenerate** for a new version, or edit it directly. You can also add translations for multi-language studies.

<Info>
  Short, friendly messages with a question at the end tend to see the best engagement.
</Info>

### Persona <Badge>Optional</Badge>

Click **Persona** in the sidebar to describe your target audience. Attributes are freeform key-value pairs that give the agent context about who it's interviewing.

For a checkout study, you might add:

| Key                  | Value           |
| -------------------- | --------------- |
| `purchase_frequency` | `2-3 per month` |
| `account_age`        | `3+ months`     |
| `payment_method`     | `credit card`   |

<Info>
  Persona attributes guide the interview but don't restrict who can participate.
</Info>

[Define your persona →](/guides/persona-attributes)

### Reward <Badge>Optional</Badge>

Offer participants a reward for completing the interview, and collect a way to reach them. Choose whether every participant is rewarded or a few winners are drawn at random, then pick what identifier the agent collects (email, phone, username, or a custom field).

[Offer rewards and collect identifiers →](/guides/rewards-incentives)

### Editing via chat

You can also modify any of these settings by chatting with the Study Builder. Ask it to change the agent's name, update the outreach message, adjust persona attributes, or switch the interview depth, and the builder updates the configuration inline.

<Tip>
  Use the chat for quick adjustments. Use the sidebar panels when you want to review all settings at once.
</Tip>

## Step 4: Test your study

Once your Agent and Outreach are configured, click **Start testing** to generate a test link.

The sidebar shows:

* **Test link**: Share internally for QA before going live
* **Embedded preview**: Test the interview directly in the builder

<Info>
  Test interviews are never included in your dashboard reports or insights. Test as much as you want without affecting your data.
</Info>

### What to test

* Does the agent ask relevant questions based on your goals?
* Are follow-ups appropriate based on responses?
* Does the interview feel natural?
* Is the tone appropriate for your audience?

Use the chat in the study builder to refine your goals and agent behavior based on what you observe during testing.

## Step 5: Go live

When you're satisfied with testing:

1. Review your configuration one final time
2. Click **Switch to live** in the sidebar
3. Your production link is ready to share

<Check>
  Your study is now live at `https://pillow.so/abc123`
</Check>

## What's next

<CardGroup cols={2}>
  <Card title="Test vs. live mode" icon="flask-conical" href="/guides/test-vs-live">
    Understand how testing works before going live.
  </Card>

  <Card title="Broadcast your study" icon="share" href="/guides/broadcast-study">
    Learn how to share your link effectively.
  </Card>
</CardGroup>