> For the complete documentation index, see [llms.txt](https://docs.dstillery.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dstillery.com/data-and-audience-products/audiences/custom-built-audiences.md).

# Custom built audiences

Build a predictive audience from the signals that define your target.

### What it is

Custom Built Audiences are for brands that want a custom audience without sharing first-party data. Instead of starting from a CRM list or pixel, a seed set uses websites, keywords, products, or a combination of [Pre-built audiences](/data-and-audience-products/audiences/pre-built-audiences.md).

Dstillery's multimodal AI builds a predictive model from those signals. It finds people most likely to engage with your brand across the programmatic landscape. Custom Built Audiences include specialized builds like Custom Search Lookalikes and Retail Purchase Intent Audiences, each optimized for a specific seed type.

Use the DS-1 agent that matches your seed:

* [Build a domain seeded audience](/using-ds-1/agents/build-a-domain-seeded-audience.md) for websites and domains.
* [Build a search LAL audience](/using-ds-1/agents/build-a-search-term-seeded-audience.md) for search terms.
* [Build a purchase intent audience](/using-ds-1/agents/build-a-purchase-intent-audience.md) for retail products.

Available self-serve via DS-1, or fully managed through your Dstillery Client Services team.

### Why it's different

{% columns %}
{% column %}

#### Before

Without first-party data, you are stuck choosing generic off-the-shelf segments. They were not built for your brand, product, or specific audience.
{% endcolumn %}

{% column %}

#### After

A seed defines the target, and Dstillery does the rest. No first-party data is required to get a custom-built audience.
{% endcolumn %}
{% endcolumns %}

### How it works

{% stepper %}
{% step %}

#### Define the seed

Define a custom seed set, such as websites, keywords, products, or Pre-built Audiences. Dstillery can recommend seed inputs based on campaign goals and category.
{% endstep %}

{% step %}

#### Model the intent

Dstillery's multimodal AI analyzes behavioral patterns across 400M+ devices to find users who match that intent.
{% endstep %}

{% step %}

#### Receive and refresh

A custom predictive model is built and delivered to your DSP within 24 hours. The model refreshes every 24 hours, so your audience never goes stale.
{% endstep %}

{% step %}

#### Activate

One model powers every activation method, from user segments to custom bidding algorithms.
{% endstep %}
{% endstepper %}

### Key benefits

{% hint style="success" %}

* No first-party data required. Build a high-performing custom audience from proxy signals.
* Fully customizable seed set. Mix and match websites, keywords, products, or Pre-built Audiences.
* Uses the same multimodal AI as Custom AI Audiences, with no performance compromise.
* Activatable as ID-based or cookieless via ID-free technology, flexible across all environments.
  {% endhint %}

### Good fit if you

* Do not have first-party data to work with, but know the websites, keywords, or products that define your audience.
* Want to target a specific niche not covered by Pre-built Audiences.
* Are new to programmatic and want a fast, low-barrier way into custom targeting.
* Are running a campaign on a sensitive topic where a cookieless approach is the better fit.

### Pricing

See [Pricing](/data-and-audience-products/audiences/pricing.md) for current rates.