Audit intermediate Works with: Any AI

Email Segmentation and Personalisation Audit

Table output Has example

Check whether personalisation helps or backfires.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Audit my segmentation and personalisation. Segments and rules: [SEGMENTS]. Personalisation fields used and fallback values: [PERSONALISATION]. Data collected and how: [DATA_COLLECTION].

Check data accuracy, sensitive data use, creepy personalisation, errors with blank fields, segments too small to test, and whether messages actually differ between segments.

Return a table with Segment or field, Issue, Risk (red, amber, green) and Fix, a score from 1 to 10 for usefulness and respect, and a test plan. Data protection rules are [VERIFY] for [JURISDICTION].

Also recommend fallback wording for missing names, a test with deliberately blank fields before each send, and a rule never to reveal sensitive inferences, such as health or finances, in the message. Suggest how to document the logic behind each segment.

Use only the numbers I supply, label estimates, and do not promise results. Advertising, consumer and platform rules differ by place and change often, so tag them [VERIFY] for [JURISDICTION] and the platform's current policy.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Review (invented bookshop)
Segment "Crime readers": rule bought 2+ crime titles in 12 months; 840 people. Message differs: yes.
Segment "Gift buyers": rule bought in November or December only; 1,900. Messages same as all. Amber.
Personalisation: "Hi {first_name}" with fallback "friend"; 312 contacts have blank names (appeared as "Hi ,"). Red; test with blank fields.
Data: birth date collected without a use. Remove.
Sensitive inference: segment named "Recently bereaved" from book purchases. Red; delete.
Test plan: crime-reader email vs general email, click rate, 4 weeks. Data protection [VERIFY].

• audit