Home · Business · Marketing & Content · Email & CRM campaigns

PARTLY

As of 13 August 2026, AI can only partly personalise marketing emails for your UK customers.

This still needs a person who signs their name to it.

Can you do it?

15 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededpower-user

Who has to check ityou

What the alternative costsNo comparable human-service price is provided in the available tool data; Jasper is a purpose-built AI marketing platform for on-brand campaign copy at volume.

If this goes wrong: customers receive an irrelevant or incorrect offer, or a message is sent to someone without the right marketing permission, creating complaints and commercial or compliance consequences.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Use a tool built for this

    Second choice
  3. Do it yourself

    The distant third

    A chat interface, power-user skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open your CRM or email platform and export only the approved fields needed for the campaign, using customer IDs or merge tags and excluding unnecessary personal data.
    2. Open the campaign brief and record the objective, audience, offer terms, landing-page URL, brand tone, permitted personalisation fields and the recipients who must be excluded.
    3. Paste the brief and a small representative sample of the cleaned segment data into the prompt, then ask the chatbot to produce the email, variants, fallback text and checking lists.
    4. Compare every drafted price, claim, date, product detail and link against your current offer page, terms and product information, then correct the prompt and regenerate anything that does not match.
    5. Paste the approved copy and personalisation rules into your email platform, configure the merge tags and suppression lists, and send test emails to internal addresses for every segment and missing-field fallback.
    6. Open each test email on desktop and mobile, check the rendered name, offer, links, unsubscribe route and recipient eligibility, then have the campaign owner approve the final send.

    Prompt

    Act as a UK email-marketing copywriter and campaign assistant. Create a personalised marketing email campaign for [BUSINESS NAME] promoting [PRODUCT OR OFFER] to [AUDIENCE OR SEGMENT]. Use only the information I provide below. Do not invent customer details, purchases, preferences, prices, discounts, stock, delivery times, claims or deadlines. Do not infer or use sensitive characteristics such as health, ethnicity, religion, political views or sexual orientation. Personalise only with the approved fields listed in the data rules.
    
    Campaign objective: [OBJECTIVE]
    Brand tone: [TONE]
    Call to action: [CTA]
    Landing page: [URL]
    Offer terms and expiry: [TERMS]
    Approved customer fields: [FIELDS, SUCH AS FIRST NAME, CUSTOMER SEGMENT, LAST PURCHASE CATEGORY]
    Data and consent rules: [RULES]
    Customer records or segment summary: [PASTE DATA, USING CUSTOMER IDs OR MERGE TAGS RATHER THAN UNNECESSARY PERSONAL DATA]
    
    Produce:
    1. One main email with a subject line, preview text, body and CTA.
    2. Up to three genuinely different variants for the approved segments.
    3. A personalisation table showing each field used, the fallback text if it is missing, and the segment it applies to.
    4. A plain-text version and a short list of links, claims, prices and dates that need checking.
    5. A pre-send checklist covering recipient eligibility, consent or suppression status, merge-tag rendering, offer terms, unsubscribe wording, links and mobile readability.
    
    Keep the copy clear and natural for UK customers. If any requested personalisation, claim or consent rule is unclear, stop and flag it instead of guessing.

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot know whether your CRM fields are accurate, current or collected with the right marketing permission.
  • AI cannot decide whether a customer segment is commercially sensible when the data supports several interpretations.
  • AI cannot take responsibility for sending to the wrong recipient or using a personal detail in an inappropriate context.
  • AI cannot reliably verify every merge tag, suppression rule, link and offer condition across a live campaign without your platform tests.
  • AI produces variants quickly but does not replace your judgement about brand boundaries, customer relationships or when personalisation feels intrusive.

What caps this at PARTLY: consent and privacy, legal accountability and judgement under ambiguity.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs1
Verification1
Liability1
Effort delta2
Total7 / 10

FAQ

Can AI write personalised emails for my customers?
Yes, it can draft different versions using approved fields such as a customer segment, product interest or previous purchase category. It cannot decide whether those fields are accurate or whether you are permitted to use them, so check the data and recipient rules before sending.
Can AI personalise emails from my CRM?
Some marketing platforms can use CRM or campaign data when you configure the connection and permissions, while a chatbot can only use data you provide. Test merge tags, fallbacks and suppression lists in your email platform rather than trusting the generated copy alone.
Is it safe to use AI for UK marketing emails?
It can help with drafting and campaign variations, but it does not make the campaign compliant by itself. Check consent or another valid marketing basis, the data you use, unsubscribe handling and the accuracy of every offer before sending.
How do I stop AI making up customer details in an email?
Tell it to use only named fields, forbid invented facts and require fallback text when a field is empty. Give it a representative sample, then send tests for each segment and missing-data case before the live campaign.

Nearby answers

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.