Blog / AI in Education / How can AI provide formative feedback?
AI in Education
7 min read
How can AI provide formative
feedback on students' writing
assignments?
Formative feedback is one of the most powerful tools in education
but it breaks down at scale. Here is how AI changes the arithmetic
without sacrificing quality.
Eduface Team
January 2025 · 7 min read
Ask any student what really helps them learn, and chances are you'll hear "feedback." It's
no coincidence that John Hattie (2009), in his large-scale research, concluded that
feedback is one of the most powerful learning interventions.
But what do we actually mean by feedback? Hattie & Timperley (2007) define it as:
"information provided to a student about aspects of their performance or understanding."
That information can take different forms. Sometimes it's a grade — also known as
summative feedback. Useful for administration, but with one big drawback: the student
only hears what could have been improved after submitting, with no chance to apply
those improvements. The learning process essentially ends too soon.
That's why more teachers are choosing formative feedback: feedback given before the
final evaluation. This allows students to actively work on improvements, refine their
assignments, and deepen their understanding. For learning, this is invaluable.
Providing formative feedback takes an enormous amount of time — often hours spent
reviewing long reports, formulating concrete suggestions, and repeatedly explaining
learning objectives. And then the question naturally arises: shouldn't modern technology,
such as AI, play a bigger role here?
What makes good formative feedback?
Formative feedback is worth its weight in gold for learning. But there's a catch —
feedback can also completely miss its purpose. As Valerie Shute (2008) aptly put it:
"Feedback can be extremely powerful if done well and extremely ineffective, or
even harmful if done poorly."
— Valerie Shute (2008)
Simple or elaborate?
A good example comes from Elder & Brooks (2008) in a nursing program. Students
received two types of feedback: simple ("correct" or "incorrect"), and elaborate — with
an explanation of what a better answer would be and why.
The outcome? Students who received elaborate feedback performed better on follow-up
assignments and reported having a deeper understanding of the material. Explanation +
context = more learning.
Hattie & Timperley's three questions
Elaborate feedback alone is not enough. Hattie & Timperley (2007) formulated three key
questions that good feedback should answer:
Feed up
Where am I going?
Feedback
How am I doing now?
Feed forward
What is the next step?
They also distinguish four levels of feedback:
1
Task level: Is the answer correct? 'This answer is correct because you used the right formula.'
2
Process level: How well does the student apply strategies? 'Good approach, but next time also think about X.'
3
Self-regulation level: How can the student improve themselves? 'You check your work thoroughly that helps prevent mistakes.'
4
Person level: Feedback on the student as a person. 'Well done!' not effective for learning.
Nicol & Macfarlane-Dick's seven rules
Nicol & Macfarlane-Dick (2006) formulated seven "rules" for good feedback — think of it
as a mini-rubric:
Clarifies learning goals and performance standards
Encourages self-evaluation and reflection
Provides informative, usable feedback
Promotes dialogue between student and teacher
Strengthens motivation and self-confidence
Offers concrete guidance for improvement
Gives teachers insight into learning problems
Their main message: feedback is not a one-time event, but a continuous process.
Students need multiple rounds of feedback to truly steer and improve their learning
(Shute, 2008; Hattie & Timperley, 2007).
How AI can support the feedback process
Sounds great, right? The only issue: all of this takes an enormous amount of time. How
often can teachers realistically provide such elaborate, repeated, and well-thought-out
feedback to every student?
This is precisely where AI becomes relevant. Not as a replacement for the teacher, but as
a first layer that handles the time-consuming, repetitive parts — so that teachers can
focus their energy on the moments where their expertise truly matters.
When Jeroen van Gessel started Eduface in 2023, he asked himself a simple question:
can AI help provide formative feedback? Because even the most dedicated teacher finds
it challenging to always phrase feedback in a way that perfectly aligns with the guidelines
described above — let alone doing so for every student, every assignment.
How we approach this at Eduface
With Eduface, we are building an AI feedback model that supports teachers in reviewing
writing assignments. The model is didactically grounded, trained on key research sources
(such as Hattie & Timperley, 2007 and Nicol & Macfarlane-Dick, 2006), and delivers
feedback that is immediately actionable.
One important choice we made: how to present feedback. Many teachers provide
feedback at the end of an assignment or in a separate document. But research by
O'Donovan, Rust & Price (2015) shows this is often ineffective — students understand
such feedback less well, don't see exactly where the issue lies, and rarely apply it.
That's why we place feedback directly in the text itself, right where improvement is
needed. Short, concrete, with explanation, and always with a feedforward: what can the
student do now to move forward? This keeps the feedback loop as small as possible.
Safety and transparency
We know teachers are rightfully critical of AI. That's why from day one we have made
clear promises:
🔒
Our own AI model
No OpenAI — 100% developed for education.
📚
Built in Europe
Fully compliant with the EU AI Act.
🧾
GDPR-proof
Your files belong to you. We don't train on them, and delete them immediately on request.
🎓
Didactically trained
Tailored to writing assignments and educational research.
One thing is certain: AI cannot replace formative feedback, but it can strengthen it. It
lightens the heavy workload for teachers and gives students the opportunity to take their
assignments to the next level.
Stay ahead of AI in higher education
New articles on assessment, feedback, and AI policy, straight to your inbox.