Abstract: Historically, email sequences for sales and marketing must be generated manually, which is a time-intensive and labor-intensive process. Accordingly, disclosed embodiments use machine learning to automatedly generate personalized, relevant, and/or performant email sequences, at scale. In particular, an email sequence may be generated by, for each email message in an email sequence and for each content block in the email message, generate a prompt based on one or more parameter values, input the prompt to a generative language model to produce the content block, and add the content block to the email message. In an embodiment, a user may easily regenerate the entire email sequence or regenerate individual content blocks within the email sequence.

Abstract: Methods, systems, and techniques for data mapping. Company identifiers and an electronic commerce transaction history, such as an online banking transaction history, of a user are retrieved from one or more data repositories. The electronic commerce transaction history includes purchases made from one or more companies identified by the company identifiers. Data mapping is then performed to associate the company identifiers with the purchases represented in the electronic commerce transaction history to identify the companies represented by the company identifiers from which the user made purchases. The company identifiers are then caused to be displayed on a graphical user interface as suggestions to the user as investment suggestions.