Learn AI. Do. Grow.
← All modules

Advanced · Communication and productivity · module 155 of 155

Project lesson: a campaign from idea to evaluation

Plan and create a small communication campaign with AI help, from key message to evaluation, with checks on facts, tone and channels.

After this lesson

You design a campaign with one message for several channels, check facts, tone, rights and accessibility, and evaluate the result.

In view · Step by step

A campaign from idea to evaluation

  1. One key message and fixed facts for all channels.

  2. Facts, tone, rights, accessibility and a second reader.

  3. What you measure is decided in advance and compared with the goal afterwards.

Remember: Likes say little; measure what matters. Open het volledige schema ↗

One message, several channels

Choose a concrete occasion, for example an open day or a new service. Set down the goal, target group and key message, and the facts that are fixed (lesson 151). Let AI make a proposal for each channel: an email, a social media post, a poster and a short text for the website. Each channel calls for a different length and tone, but the facts stay the same everywhere. Make a fact list that you put next to the text for every part (lesson 97).

Checking before publication

Check every part for facts, for tone according to your style guide (lesson 108), for the rights to images (lesson 122), for accessibility (lesson 124) and for translations (lesson 152). Have the campaign proofread by someone who has not seen it yet. Give factual accuracy more weight than an attractive tone: a nice text with a wrong date does more harm than a simple text that is correct (lesson 81). Record who approves each part.

Publishing, measuring and learning

Plan when each part appears and who responds to questions. Decide in advance how you will measure whether the campaign works: registrations, visitors or questions, not just likes. Afterwards, compare with your goal and note what worked and what did not. Keep the approved texts, the fact list and your evaluation, so your next campaign goes faster and better (lesson 100). Where necessary, mention that texts or images were made with AI help.

New practice example

From explanation to a usable result.

A campaign has one message and one fact list, with texts per channel, a check before publication and a measurement afterwards.

Fictional practice situation

Fictional: a library launches a new service for borrowing e-books. The goal: 100 new e-book borrowers in three months. AI makes an email, a poster and a social media post.

View a possible solution

This is how it can be done

Fact list: borrow with your library card via the website, three-week loan period, no renewal. Check: the poster mentioned “unlimited renewals”; that has been deleted. Measurement: the number of new e-book borrowers per month, compared with the goal of 100. After one month: 30 new borrowers; the explanation of how to log in is being made simpler.

Why this works

The measurement links the campaign to the goal. That way, you can already see after one month where you need to adjust.

Make it slightly more difficult

Which question from readers do you expect most often? Write a short answer to it for the website.

Extra practice, at your own pace. You do not need to submit anything. This does not count towards an automatic assessment.

Your workplace · learning by doing

Make something. See what changes.

Ende, your light pink practice buddy

The fictitious source is included. Only when selecting ‘Let Ende answer’ do you send your assignment to the AI service. Do not use private data.

Checking the AI connection… You can already view the written example.

Your result

No answer yet

Present your assignment to Ende.
Read the answer, change one thing, and compare.

You remain in control

What do you want to improve in your next attempt?

My own check

On this device only. AI answers remain only in this page memory. This is self-review, not a grade.

Why this approach works

The measurement links the campaign to the goal. That way, you can already see after one month where you need to adjust.

A step further

Which question from readers do you expect most often? Write a short answer to it for the website.

Try & discover · no obligation

Compare quality with a fixed yardstick

Give tone a lot of weight. Is a beautiful but incorrect answer still allowed to pass?

Fictitious: an online workshop, Saturday from 10 to 11 o'clock. The price is not yet known.
Assign weight to the criteria
Weights adjusted. Factual errors remain a stop criterion, regardless of the total score.

Smooth but incorrect

Discover our amazing online workshop this Saturday from 10 to 11 o'clock, completely free!

Facts: 0/en/3 · Toon: 3/en/3

Weighted score
15

Stop: the free price is made up. A high total score does not offset that error.

Factual and sober

Workshop: Saturday, online, 10–11 o'clock. Price to be confirmed.

Facts: 3/en/3 · Toon: 1/en/3

Weighted score
8

Can proceed to human final check.

The two criterion scores have been pre-assigned for this fictitious case. You change their weight. No free text is automatically assessed.

This trial works locally with fictitious data and does not count towards your lesson completion. It starts anew with a new lesson or reload.

A prompt to get you started

Help me plan a small campaign for a fictional open day at a music school: Saturday from 10:00 to 16:00, free entry, trial lessons for children aged 8 and over, sign up for a trial lesson via the website. Make a fact list and then a proposal for each channel: an email to parents, a social media post, a text for a poster and a short web text. In each part, only use the facts from the list. Also suggest two ways to measure the result.

Apply it

An association used AI to create a campaign for its annual party. The email, the poster and the social media post each state a different end time.

Which approach best fits this situation?

  • Do nothing; people will ask if it isn’t clear.
  • Only adjust the poster, because that is what most people see.
  • Make a fact sheet, bring all parts into line with it and have the campaign proofread before it is shared any further.

With JavaScript, you can check your approach and receive immediate feedback.

Test your insight

Your campaign gets lots of likes, but hardly anyone signs up for a trial lesson. What do you conclude?

  • The campaign is a success, because there were lots of likes.
  • The goal, registrations, has not been reached; look at what made signing up difficult and change that.
  • Make more images with AI next time.
Extra practice

Plan a small campaign for a real or fictional occasion. Check every part against the fact list, have it proofread and write down in advance how you will measure the result.

Fact list: Saturday from 10:00 to 16:00, free, trial lessons from age 8, sign up via the website. Email: friendly, 120 words. Social media: 40 words with a photo of our own. Poster: title, times and a QR code to the registration page. Check: the first post said “from age 6”; that has been corrected. Measuring: the number of registrations for a trial lesson and the number of visitors at the door.

A question? I'll help you on your way.

Drag Aldo to move it. Use the arrow keys on Aldo with the keyboard, Enter to save the position and Escape to cancel.