Jenna
First-marking your coursework, done by Jenna on your own portal
Jenna signs in to your platform as an assessor, reads every answer, marks against the official guidance, writes feedback the way an instructor would and holds anything below the minimum. Your assessor keeps the final say, and gets the first read-through back.
Nothing to install · No integration · Works on your existing portal
The marking bottleneck
Learners submit written coursework chapter by chapter, as a continuous trickle rather than a batch. An assessor opens each learner, reads every answer against the mark scheme, enters a mark per question, writes feedback where marks are lost, then records the decision. Twenty to forty minutes of qualified time per chapter, and a portal with no view of "chapters waiting to be marked".
Centres want that first pass automated without lowering the bar: marks must follow the awarding body's guidance, feedback must never reveal the model answer, and the assessor must stay accountable for every Pass.
What Jenna does, chapter after chapter
In a real browser, on your portal, with a dedicated assessor account.
-
She opens the submitted chapter
Triggered when a learner submits, or on demand. She signs in with the account you gave her, stored encrypted, and finds the chapter to mark.
-
She marks question by question, against the official guidance
The awarding body's scheme is her only reference: we never write criteria of our own. Every mark carries its rationale and the learner's quoted words, so a wrong mark is visible and correctable in the portal exactly as today.
-
She writes instructor-style feedback
Where marks are lost, a comment that points the learner in the right direction without ever giving the model answer, in the tone your instructors use.
-
She passes or holds, never refers
A chapter that meets the minimum everywhere is recorded as a Pass under the assessor account. As soon as one answer is below its minimum, the chapter is held with comments for the learner. A formal Refer stays a human decision.
-
Your assessor reviews and signs off
Every result is reviewed by the centre's assessor, who remains accountable for the outcome and spends their time on the edge cases rather than the first read.
Our reference engagement
A UK training centre delivering Active IQ Level 2 and Level 3 qualifications (gym instructor, personal trainer), on its own portal, measured against its own assessor. September and October 2026.
AI pre-assessment for an Active IQ training centre
The problem, the set-up, a run step by step, how we checked it before trusting it, the results chapter by chapter, and what we got wrong and fixed. With screenshots from the runs.
Read the case study → MethodologyHow we set up AI pre-assessment on your platform
Four principles, six phases from read-only discovery to go-live, what we need from you, what stays human, safety and data handling, and what it costs.
Read the methodology →How we set it up
Six phases, always in the same order, with your assessor at every step.
Read-only discovery
We look at your portal, your qualifications and your mark scheme without changing anything, and tell you honestly whether the case fits.
Validation and calibration
Jenna marks chapters your assessor has already marked. We compare question by question and adjust until her standard is yours. The bar stays your call.
Supervised go-live
Runs triggered by learner submissions, the assessor reviewing, and a watch on systematic errors. Then extension to further levels.
What stays human
The decision
Every Pass is reviewed by your assessor. Referring a learner is never automatic.
The bar
Where the guidance says only "a more detailed and accurate description", your assessor decides what that means, not us.
The edge cases
Hand-annotated images, files the portal cannot preview, ambiguous answers: flagged for a person, never settled by the AI.
Your data
Jenna works on your account, with your credentials stored encrypted, at a capped rate. Learners are anonymised in any report that leaves your account, and recordings can be deleted on request.
What it costs
Set-up is billed by the hour and quoted after discovery. Day-to-day running consumes the minutes on your Jenna account, with the Autopilot subscription (€29/month, 725 minutes included) to store your credentials and schedule the runs.
| Marker | Time per chapter | Cost per chapter |
|---|---|---|
| A qualified assessor | 20 – 40 minutes | ≈ €7 – 13 |
| Jenna, standard model | ≈ 36 minutes of browser time | ≈ €1.4 |
| Jenna, high-effort mode | 30 – 50 minutes of browser time, billed at 2.5× | ≈ €3.5 |
Figures measured on Active IQ Level 2 chapters of 14 to 16 questions. Your chapters may be shorter or longer. See all pricing.
Questions centres ask
Do we need to change our learning platform?
No. Jenna works through a real browser on your existing portal with a dedicated assessor account. There is no integration, no plugin and nothing to install. If your portal is deep-linkable, runs are faster; if not, Jenna navigates like a person would.
Does the AI decide who passes?
No. Jenna first-marks and writes feedback. Where an answer is below its minimum, the chapter is held with comments for the learner, never referred. Your assessor reviews every result and remains accountable for the outcome.
What about answers that are images, posters or PDFs?
Jenna opens the preview your portal provides and marks from what she sees: on our reference engagement, a poster assignment was marked 13 out of 13 in agreement with the assessor. Hand-annotated images and anything the portal cannot preview are flagged for a person.
What happens when the model is wrong?
Every mark carries its rationale and the learner's quoted words, so a wrong mark is visible and correctable in the portal exactly as today. Systematic errors are what validation and calibration exist to find. On our reference engagement the pattern was leniency on vague criteria, and the calibration moved seven of nine targeted questions to the assessor's mark.
Which qualifications and platforms?
Any written coursework marked online against a published mark scheme. We started with Active IQ Level 2 and 3 on a custom Laravel portal; Moodle and similar learning platforms follow the same six phases.
How do you keep learners' data safe?
Jenna runs on your own account with your own credentials, stored encrypted. We read your portal only as agreed, at a capped rate. Learners are anonymised in any report that leaves your account, and run recordings live on your account and can be deleted on request.
Start with a 15-minute discovery call
Tell us which qualification you mark and on which platform. We will say honestly whether it fits and what the set-up would take.