Dstillery Has A New Agentic AI Interface For Refining Audiences Faster | AdExchanger

"DS-1 allows Dstillery's clients to develop custom audiences in minutes and push those segments to The Trade Desk for activation. Under the hood, DS-1 was built using Model Context Protocol and can integrate into whatever platform a client chooses, including Slack, Microsoft Teams, web browsers or a brand's own custom collaboration platform."

"In the past, Keynes would compile audience data, including pixels, first-party brand data and performance data from past campaigns, which it would use to predict audience traits based on the product for sale. Keynes would then communicate those attributes to someone on Dstillery's team."

"From there, Dstillery would 'seed' a model by gathering signals or behaviors indicative of the optimal customer, said CEO Michael Beebe, such as whether they viewed a specific product page. In the past, a lot of that data came via cookies, but once Google started talking about deprecation, Dstillery shifted to anonymized data sets like opt-in consumer panels."

Programmatic advertising has traditionally relied on manual processes involving extensive email communication and hands-on data analysis to refine audience segments before campaign launch. Dstillery's new DS-1 agentic AI interface streamlines this workflow by allowing clients to develop custom audiences within minutes and directly push segments to The Trade Desk for activation. Built using Model Context Protocol, DS-1 integrates with various platforms including Slack, Microsoft Teams, web browsers, and custom collaboration tools. Early adopter Keynes, a CTV advertising platform, previously spent significant time compiling audience data from pixels, first-party brand data, and past campaign performance, then communicating these attributes to Dstillery's team for model seeding. This process involved identifying signals and behaviors indicative of optimal customers. Dstillery has adapted its data approach from cookie-based signals to anonymized datasets like opt-in consumer panels, incorporating multimodal signals to address privacy concerns.

Read at AdExchanger