Skip to content
Synthetic School
Menu

How it works

A school year, run by rules and voiced by agents.

You lead a complete synthetic school from an inbox and a diary. In a 1,000-student school, roughly 1,900 AI agents play the staff, students and families, and a rules engine decides what each decision causes.

Inbox

Week 7 · first morning, 08:00

  • Parents

    A parent asks why her son was moved to a lower maths set.

  • Staff reports

    Science says every class is on track for the end of term.

  • Pastoral referrals

    A concern about a student's attendance and mood, logged on Thursday.

  • External bodies

    Your board wants the budget forecast before its next meeting.

Illustration. Every item reaches you through a channel, and each channel has its own delays and faults.

A week in the chair

Each sitting is one school week.

A sitting has a target of 45 to 75 minutes of play, still to be tested with the first school leaders who play it. A programme seat covers 12 played weeks, about 9 to 15 hours, and the other weeks are fast-forwarded or delegated.

  1. 01

    The first morning

    The week opens on the inbox and diary as they stand at 08:00, already filtered through the school's channels.

  2. 02

    Triage

    You read, rank, reply, delegate or leave things. Every choice is logged with its time.

  3. 03

    The week runs

    The engine ticks through each day. Play pauses for a knock at the door, and some events keep the clock running while you decide.

  4. 04

    Conversations and meetings

    You talk to anyone you choose and chair the meetings in your diary.

  5. 05

    The end of the week

    You see only what you would plausibly know by then. Play on, fast-forward, branch or stop.

Time is the scarce thing

Every action takes time from the pack's table of what each action costs, and the diary fills as you spend it. Items left unread age by rule, so an unanswered complaint can grow into a formal one.

Four speeds of clock

Live
Minute by minute, for a crisis morning or a hard meeting
Day
A school day in 10 to 15 minutes
Week
A school week in one sitting, the default
Delegate
Weeks pass with your senior team acting on standing instructions

Eight surfaces make up the chair

Inbox

Email, notes, referrals and requests from the board or authority

Diary

Meetings, duties, events and deadlines

Floor plan

Every room by period and who is in it, so you can drop into a lesson

Conversation

One person at a time, in text, with voice to follow

Meetings

Senior team, departments, all staff, parents and the board

Dashboards

The school's data as it was entered, faults included

Levers

Staffing, timetable, budget, curriculum, policy, interventions, communication and delegation

Time controls

Pause, play, delegate, fast-forward and branch

Every lever costs staff hours, money or trust. A lever pulled without that cost met, such as a new policy with no training time, fails later by rule.

Your words as moves

Talk freely. The rules still decide.

Each reply carries the moves the agent read in your words, from a fixed list of 16. Rules decide what each move does to trust, workload and the case at hand.

A move repeated to the same person loses force, so daily praise soon stops buying trust. If you think a line was misread, you can contest it.

  • agree
  • refuse
  • overrule
  • delegate
  • promise
  • praise
  • thank
  • challenge
  • ask
  • listen
  • apologise
  • instruct
  • inform
  • reassure
  • defer
  • escalate

Conversation · Head of maths

Tuesday, period 4

Head of maths

We're two teachers down on Thursday and I can't cover Year 11 again.

You

Leave it with me.

Read as promise

A side panel shows how each line was read. Here, "leave it with me" counts as a promise.

The engine

Agents propose. The engine resolves.

The school lives in typed records: students, staff, families, classes, the timetable, the budget, procedure cases and the relationships between people. Only the engine writes to them.

An agent's output is an intent, such as phoning a parent or refusing a cover request. The engine checks it against the agent's remit and resolves it by rule.

Each school day runs eight steps

  1. 1

    Events fire

    Calendar and random

  2. 2

    Attendance

    Who is in today

  3. 3

    Lessons

    Progress and engagement

  4. 4

    Incidents

    Behaviour and referrals

  5. 5

    Procedures

    Steps and timers

  6. 6 · model calls

    Scenes

    Agents talk and act

  7. 7 · model calls

    Channels

    Records and documents

  8. 8

    Log

    The day's events kept

End of each week

Morale and wellbeing drift, the budget posts and a snapshot is saved

End of each term

Tracking and reports, then the debrief

Each year

Exams and results, leavers, the new intake and the staffing round

In the daily loop, only scenes and the documents that channels carry call a model. Every other step is plain code.

Rules you can open

Rules are plain functions with named parameters. If you dispute a consequence, you can open the rule and the numbers behind it.

Procedures hold

Steps set by law or national guidance are fixed in each system's pack. An agent can carry out a step badly, but it cannot skip, add or reorder one.

Effects from published trials

Interventions move a rule's parameters by amounts taken from published trials. Each effect is held as a range with a central default, and a programme can choose the setting.

Beliefs can be wrong

Agents keep their memories outside the school's state, so what a member of staff believes can differ from what is true.

What you see

You see the school through its channels.

Information reaches you only through channels, and every channel has its own delay and faults. Reading through the gap between the school's true state and what the channels show is part of the job.

The school's channels, with their delays and typical faults
Channel Carries Delay Typical faults
RegistersDaily and period attendanceSame dayMissed marks, wrong codes, late corrections, out-of-date class lists
TrackingTermly attainment estimatesEach reporting windowOptimism, gaps, uneven scales, late entry
Behaviour logIncidents and sanctionsHours to daysUnder-recording that varies by teacher
Pastoral referralsWellbeing and child protection concernsHours to daysThresholds that vary by person
Finance reportsSpend against budgetMonthlyLag and miscoded lines
Statutory returnsCensus and other returnsSet datesCoding errors, such as a miscoded reason for support
Staff reportsDepartment and team statusWeekly or on requestSpin and omission
Corridor and staffroomMood and rumour, sometimes an early warningImmediateDistortion and selective reach
ParentsComplaints and praiseVariableThe loudest families are over-represented
External bodiesRequests and findings from those the school answers toVariableThey arrive without context

People are channels too

Staff decide what to pass on. That depends on how serious the matter is, how far they trust you, what reporting would cost them and their own threshold for escalation.

A leader who punishes bad news hears less of it, and a leader who thanks people for early warnings gets more of them.

Faults you can fix, at a cost

Each channel carries four fault settings: delay, error rate, omission rate and bias. You can lower them with data-quality work or new routines, and each costs staff hours.

Faults also drift, so a department under pressure records less. None of the settings comes from real student records.

The cast

Everyone in the building is an agent.

A 1,000-student school holds about 79 teachers plus support staff, every student, one agent per family and a handful outside the building, from inspectors to social workers. Agents think only when something reaches them, so running cost grows with conversations and barely moves with the size of the school.

They remember

Each agent keeps a log of what it took part in, weekly summaries and the beliefs it revises each term. It also keeps a short list of key moments, such as whether you keep promises about cover.

They differ

Candour, conscientiousness, ambition, conflict style and appetite for risk are drawn from ranges in the pack, so each staffroom has its own spread of temperaments.

They talk without you

News travels through cliques. Scenes you never watch still happen and still have consequences, and you can replay any of them in the debrief.

They know only their part

Each prompt holds only what that role could know. A reply that relies on a fact outside the agent's knowledge is checked, regenerated and logged.

When played people go wrong

Research on language-model agents documents how they fail. Each failure has a counter in the design.

They agree too readily

Goals that conflict with yours, a conflict style in every persona, and an engine that ignores flattery when it resolves intents.

Voices flatten into one

Dispositions and histories drawn by the engine supply the variation, because raising a model's temperature does not.

Simulated students are too able

The engine decides attainment, attendance and behaviour, and the model only voices those decisions.

A trainee talks an agent out of role

Your words reach agents only as speech in the scene, never as instructions, and the engine owns the state.

Agents may never change the school's state directly, invent a statutory or child protection step, claim to be a real person, or produce graphic or sexual content. Every output passes schema and rule checks before it reaches the engine or you.

Save points and branches

Go back to any week and decide differently.

Every week ends at a save point. Return to any of them, play the rest differently and compare both runs side by side.

Both runs share the same random draws, so the engine's luck is identical. Agents your decision reaches reply afresh, so part of any difference in how they behave is model chance, and branches carry an illustrative label.

Programmes can switch branching off, so a cohort lives with one run as a real school leader would.

Watch two copies of a school split

A run and one branch

Main run

W1
W2
W3
W4
W5

Branch from the end of week 3

W4b
W5b
A run is a seed, a log of every event, a snapshot at the end of each week and the model replies it received. A branch stores only the days after its save point, and any run replays exactly.

The debrief

Each term ends with evidence, never a score.

A coach leads the debrief, and a facilitator sets up cohorts and storylines; one person can do both. Either sees your record only with your consent.

  1. 01

    Accounts from the school

    Up to 30 of the people you dealt with most each give a short account in their own voice, limited to what they knew.

  2. 02

    The record

    Every decision, its time and what it touched in the engine. A coach can open the cause chain behind any outcome.

  3. 03

    Your vision against your term

    The vision you wrote at the start of the year, set beside where your diary hours and the budget went.

  4. 04

    Outcomes, true and as reported

    The engine's measures for the term beside what the channels told you, so you see what they hid.

  5. 05

    Your system's standard

    Moments mapped to the leadership standard your system uses, without a score.

  6. 06

    Branches

    If you branched, the two runs side by side, with a private question about what you could have done differently.

How programmes use the debrief

Seats

Any seat can be human.

  • The school leader's chair is the default. A trainee can instead take a deputy's, a middle leader's or a student support leader's seat, or a board member's in an international school.
  • A senior team can play together, each in their own seat, turn by turn within the week.
  • A cohort can run the same school from the same start, so debriefs compare like with like and nobody is ranked.
  • A junior seat, under an agent playing the school leader, shows a trainee what it is like to be led, well or badly.

What is built

Four stages, each ending in something you can use.

A prototype of the engine already runs a year of attendance and is calibrated in two school systems. Each stage passes a gate before the next begins, on published figures, panels of serving school leaders and the build's own replay and cost tests.

  1. Stage 1 · in build

    The engine, two packs and the channels

    Gives case files and data courses. Gate 1: both packs meet their calibration targets and every run replays exactly. The identical-policy test and sensitivity analysis apply too.

  2. Stage 2

    The cast and the chair

    Gives a school leader a full term to play. Gate 2: serving leaders' predictions, blind transcript panels, identity audits and state checks.

  3. Stage 3

    The debrief and facilitator console

    Gives a cohort a term to learn from. Gate 3: a partner cohort plays a term and its debrief.

  4. Stage 4

    Team play, the harness and many schools

    Built in the order the first buyers ask for.

The results of each gate are published as a short note. See the evidence so far.

Shape the first term with us.

Design partners play the first terms and tell us where the school feels wrong. Pilots are free or at cost while Synthetic School is validated.

Request a pilot place