Your trainees
90 minutes a week for 12 weeks, plus the assessments. Each session gives 60 minutes to one week of school time, then a trained coach leads a 30-minute debrief.
Pilots
Run the first cohorts with us.
We are looking for leadership programmes and school groups to run the first pilots, free or at cost while Synthetic School is validated. A pilot in a new system starts with building that system's pack together.
What a pilot involves
A term of practice, run as a trial.
Your programme
You invite every eligible trainee, and your coaches train to one debrief protocol. The evaluation team takes each trainee's consent directly.
Your system
If your system has no pack yet, we build it with you, and a serving school leader from your system reviews it.
What everyone gets
Every trainee gets a term of Synthetic School. The comparison group gets theirs after the follow-up, and keeps its full programme while it waits.
How the trial works
A randomised trial, published whatever it shows.
A two-stage randomised trial will test whether a term of Synthetic School improves trainee leaders' practice on scenarios they have not seen. The results will be published whatever they show, against a pre-registered plan.
Both groups get the same time and the same debrief. Only one runs the school.
- Recruit and consentAbout 80 trainees in Stage 1, about 150 in Stage 2
- Baseline assessmentTwo held-out scenarios, on form A or form B
- Randomise 1:1 within each programmeDone by an independent statistician
-
Synthetic School
12 weekly sessions of 60 minutes, with some events arriving mid-week. A 30-minute coach-led debrief from the decision log.
Case-based learning
12 weekly sessions of 60 minutes on written cases about the same problems. A 30-minute coach-led debrief from the trainee's written decisions.
- Post-testThe other form plus a transfer scenario, with raters blind to group
- Six-month follow-upMentor or line-manager ratings of practice in the job
- The comparison group gets its termAfter the follow-up, so the ratings still compare
Stage 1 · feasibility
About 80 trainees in two or three programmes, over one term, planned for the two systems whose packs are in build.
It checks recruitment, retention, rater reliability and safety, and estimates the spread of scores Stage 2 needs.
Stage 2 · efficacy
About 150 trainees in four to six programmes, across at least three school systems.
It can detect an effect of 0.4 standard deviations, and an independent team runs the assessment and the analysis.
What the trial measures
Practice on new scenarios primary
An in-tray of documents to act on, and a 15-minute conversation with a trained actor, scored by two raters blind to group.
Transfer
One scenario of a type neither group practised.
Practice in the job
Ratings from a mentor or line manager, on the same rubric, six months after the post-test.
Self-efficacy, usability and use
Secondary measures only, since self-ratings can run ahead of assessed ability.
Cost and retention
Cost per trainee, and whether trainees in post are still in a senior role 12 months on.
Not students' outcomes
School leaders' measured effects on test scores are small even in large datasets, and no trial of this size could detect them.
The rubric maps to each system's own leadership standard. The target for rater reliability is an intraclass correlation of at least 0.75.
When Stage 2 goes ahead
Stage 2 goes ahead only if Stage 1 meets every green criterion, or meets amber ones with a fix agreed first. Any red criterion stops the trial until the design is changed and tested again.
| Criterion | Green | Amber | Red |
|---|---|---|---|
| Trainees consented in the recruitment window | 80 or more | 60 to 79 | Under 60 |
| Trainees completing the post-test | 70 or more | 56 to 69 | Under 56 |
| Synthetic School group completing at least 10 of 12 sessions | 75% or more | 50% to 74% | Under 50% |
| Rater reliability, intraclass correlation | 0.75 or more | 0.60 to 0.74 | Under 0.60 |
| Comparison trainees who saw Synthetic School materials | Under 10% | 10% to 20% | Over 20% |
| Serious adverse events linked to scenario content | None | One, with a fix in place | More than one, or one without a fix |
Stage 1 also checks that the parallel forms of each scenario match in difficulty.
Ethics and independence
The developer stays away from the outcome data.
We have an interest in a good result, so an independent evaluation partner runs the randomisation, the assessment and the analysis. Results are published with that interest declared.
- The trial runs only with approval from the evaluation partner's research ethics committee, and written consent from every trainee.
- No score from the trial reaches an employer, and none feeds any selection, appraisal or programme grade.
- Trainees can leave at any time without giving a reason, and withdraw their data until the analysis is locked.
- Trial data are pseudonymised and stored in a UK or EU region. Recordings are deleted once scoring and fidelity rating are finished.
- Child protection storylines carry a content note and can be skipped, and coaches follow a distress protocol.
Who can take part in the trial
- Trainees on a programme for aspiring school leaders, or school leaders in their first two years with an induction programme
- People who can give 90 minutes a week for 12 weeks, plus the assessments
- Recruited through their programme, never through their employer
- Not open to anyone who wrote, reviewed or tested Synthetic School's scenarios
Other kinds of pilot
AI companies can pilot the test harness, and school groups or education systems the policy lab. A partner from a new system can build its pack with us. Say which in the form.
Request a pilot place
Tell us about your programme.
We read every request. If there is a fit, we agree a pilot plan together, and for a new system, a plan to build its pack.
Prefer email? Write to hello@synthetic.school.
We use these details only to reply to your request. See the privacy notice.
Thank you, {{ firstName }}.
Your request for a {{ useLabel }} pilot is with us. We will reply to {{ email }} within five working days.
Request a pilot place
Tell us about your programme.
We read every request. If there is a fit, we agree a pilot plan together, and for a new system, a plan to build its pack.
Prefer email? Write to hello@synthetic.school.
We use these details only to reply to your request. See the privacy notice.
Aspiring school leader?
Individual seats open after the first pilots. Leave your email and we will write to you once, when they do. See the privacy notice.
Thank you. We will email {{ wlEmail }} when individual seats open.
Aspiring school leader?
Individual seats open after the first pilots. Leave your email and we will write to you once, when they do. See the privacy notice.