Education · AI built and evidenced

The correction lands on the word she wrote. The number leaves with its denominator.

Practice companions, live captions, assessment data and programme operations AI, built into learning programmes and evidenced the way an education review asks for it.

Scope an education build Try the practice room

The three questions Anchor · person · denominator

A tutor that talks is easy. Three things make it evidence

Whether it corrected the right word. Whether a person saw the skill. Whether the number that reaches your board shows how much stands behind it.

  1. Did it correct the right word?

    har gå → har gått

    A correction that describes the mistake in a block underneath is a lecture. One that is anchored to the exact characters the learner wrote can be drawn on her own word, and can be checked: if the offsets no longer point at the original text, it is a model problem and it never reaches a learner metric.

  2. Did a person ever see the skill?

    Observed · past tense, in conversation with a person

    A practice system on its own only records the learner talking to a machine. One optional question to the volunteer after a session asks whether one observable thing happened. Not a score and not a judgement of the person. The third answer is "not enough context", which is never counted as a no.

  3. Can the number show its evidence?

    Reused the corrected form · 2 / 3

    Every metric leaves with a numerator and a denominator. A rate is refused below a floor rather than printed as a percentage that moves twenty points on the next learner, and test traffic is excluded before the first reading.

What YPAI builds Four engagements · one programme at a time

Start from the programme you run

Practice, captions, assessment data and operations, each bought on its own and configured for one programme and one cohort. Four things are settled before the first learner is enrolled.

Agreed before the first learner

  • The programme, the language and the cohort
  • What the model may say, and where a person rules
  • Which controls apply, from FERPA to WCAG 2.2 AA
  • What the evidence ledger contains

  1. Conversational practice systems

    A practice partner that replies in character, corrects on the learner's own word, and knows when to stop.

    A companion built on tool-use: one reply that asks one question, at most one correction anchored to the learner's characters with a one-line explanation, at most two vocabulary items in context, a recap when she has said enough, and voice in and out. Scenarios and pause states are designed, not improvised: on frustration or a jailbreak attempt the companion stops and hands the learner to a person, and it answers course questions only from approved material, with the source cited, or refuses.

  2. Live captions and session transcripts

    Captions in a tutoring call that both people agreed to, and a transcript that exists only if someone chose to keep it.

    Live transcription in video sessions, started only when both participants allow it, with speaker attribution, captions in the session language, and a transcript saved only when a person decides to keep it after the call. Recordings are consented separately.

  3. Assessment and evaluation data

    Rubrics, rater agreement and held-out sets for the models your programme will trust.

    Evaluation data for education models: rubric-scored responses, two-rater agreement measured on the delivered material, held-out test sets, native-speaker evaluation in the languages the model will meet, and red-team probing for the things an education model must not say to a learner.

  4. Programme operations AI

    The admin side of a learning programme, with a person holding every consequential decision.

    Intake triage and cohort assignment with a person confirming, course provisioning into the LMS you already run, certificates and badges issued from the record, campaign copy drafted only behind an approval marker and never from rosters, insight narratives with a banned-word filter, and voice notes transcribed into the record.

Scope the first cohort

Try it yourself Six rules · two languages · one person

Write the sentence yourself

You are the learner. A toy companion of six rules replies, draws the correction on your own word, and a person is asked one question. Every number keeps its denominator.

I dag har gå jeg på møte med kollega

  1. characters 6 to 12 of her sentence

    The correction is drawn, not described.

    The companion returns offsets into the learner's own message. If the offsets no longer point at the original text, the correction is a model problem and never counts.

  2. observed · past tense · a volunteer

    The person is asked about the skill.

    One optional question after a session, about one observable thing. Not a score, and "not enough context" is not a no.

  3. 1 / 3 · rate withheld

    The number keeps its denominator.

    Every metric is a numerator over a denominator. A rate is refused below the floor, so three learners and one retained form is reported as 1 over 3, never as 33 percent.

Practice · At work
  1. Written
  2. Corrected
  3. Asked
  4. Logged

You · the learner

The mark is drawn on the word you wrote, from the offsets the companion returned.

  1. You

    I dag har gå jeg på møte med kollega

  2. Practice

    Så bra! Hva gjorde du på jobb i dag?

    Correction

    har gå har gått

    After "har" the verb takes the perfect form: gått.

    kollega
    a person you work with
    møte
    a meeting; also the verb to meet

The person

Volunteer tutor Met the learner in a session this week

In your conversation, did she use the past tense?

About the skill, never the person. Optional. "Not enough context" is never counted as a no.

The question opens after a correction has landed.

Live captions

Captions in a session only start when both people have allowed them. The transcript is saved only if someone chooses to keep it afterwards.

  • Learner
  • Tutor

Waiting for the other person

This session

Corrections anchored to her text
1 / 1
Corrected form reused later
0 / 1
Skill observed by a person
0 / 0

Rates are withheld below five turns.

Ask the course material

The companion answers a question only from the passages the programme approved, cites the one it used, and refuses when nothing matches. A refusal hands the learner to a person.

A toy companion with six rules, so the mechanics are visible. Not a language model. Nothing on this page is a real delivery or a real result.

How a programme runs Demand · attendance · recap · certificate

Every consequential step arrives with a name

Demand becomes a class, absences become follow-up, a session becomes a recap and a certificate. The model proposes each step. You or a teacher confirms it, and the log keeps the name.

  • The proposal shows its reasons.

    Demand, teacher capacity and the size rule are written next to the proposal, and the candidate score is three visible parts. A crisis tag is shown and never scored.

  • The tone rules are written down and enforced in the system.

    Follow-up is tiered and the wording is checked against rules the programme wrote down. A pinned crisis tag suppresses the template and routes the learner to a named person. The model detects; it never intervenes.

  • A person signs every consequence.

    Class creation, check-in, recap and certificate each wait for a named confirmation, and the desk log records who did what.

Programme desk · Autumn cohort Every consequential step carries a person's name

Demand to class

Waitlist
Norwegian · A2 17
English · B1 6
Polish · A1 30
Teachers with a free slot
Teacher A · Norwegian Tuesday 18:00
Teacher B · English Thursday 17:00

Attendance to follow-up

    The rules refuse any threat to a learner's place and any streaks, badges, points or leaderboards. A learner is paused, not dropped, and gets fewer emails, not more.

    Recap to certificate

    Session facts
    • past tense
    • at work
    • small talk
    • 9 / 11
    • 4 ?

    Certificate check

    Amal · 7 / 8 Rule: at least 75 percent attendance, over at least eight sessions

    Desk log

    1. Nothing yet. Propose a class to begin.
    A toy desk with fixed demand and a four-learner roster, so the mechanics are visible. No email is sent, no course is created. Nothing on this page is a real delivery or a real result.

    Who we build for Language · assessment · higher education · corporate · accessibility · K-12

    Six kinds of programme, each with its own proof

    A language app, an assessment vendor and a university do not ask the same question of the evidence. The engagement is written for the question your programme asks.

    1. Language-learning AI Corrections a learner can check Practice companions and tutoring tools, evidenced by anchored corrections, observed skills and numbers with denominators.
    2. Assessment and tutoring AI Rater agreement on the delivered set Rubric data, two-rater agreement, held-out sets and red-team probing for what a model must not say to a learner.
    3. Higher education and LMS Built into the system you run Retrieval over course material, provisioning into the LMS, certificates from the record, and the documentation an institutional review asks for.
    4. Corporate learning Skills evidence a manager can read Workplace practice, session captions with consent, and impact metrics that show their denominators to the people who fund the programme.
    5. Accessibility and integrity WCAG 2.2 AA and Annex III controls Assistive reading and captioning built to WCAG 2.2 AA, and the high-risk documentation an exam-integrity or proctoring deployment carries under the EU AI Act.
    6. K-12 and school platforms Controls written for children Publisher AI, district software and adaptive platforms built under Article 8, COPPA and FERPA, with age-appropriate design and a person at every consequential step.

    From edu-AI start-ups to proctoring vendors, each engagement names the kind of programme it is written for.

    What the delivery contains One row per turn · totals with denominators

    The ledger your funder and your review will read

    Every turn with its correction and its anchor, whether the corrected form came back, and what a person observed. Written by what you did above.

    1. 01

      I dag har gå jeg på møte med kollega

      har gå har gått · anchored 6 to 12 · Valid · offsets point at her text

      Norsk · Practice · At work

      Reused later
      Not yet
      Person
      Not asked
    Anchored
    1 / 1
    Reused
    0 / 1
    Observed
    0 / 0

    Example ledger, built from what you ran above

    The first cohort Five stations · one decision

    One programme, one language, one cohort

    A pilot runs the same engagement on one programme, one language and one cohort. The scenarios, the controls and the ledger's fields are fixed before the first learner is enrolled, one cohort runs with a person at every consequential step, and the pilot ends with a ledger and a decision. You judge it against your programme and your review.

    Fixed before the first learner: the programme, the language and the cohort, what the companion may say, and where a person rules, the controls that apply, from consent to WCAG 2.2 AA, the floor below which no rate is reported, and what the evidence ledger must contain.

    1. Scenarios

      The situations the companion practises, the corrections it may make, and the pause states, written and agreed.

    2. Controls

      Consent, age and data controls mapped to the programme, with the person named at each step.

    3. Cohort

      One cohort runs, with captions and observations gated on people, and test traffic excluded.

    4. Ledger

      Every turn, correction, anchor, observation and metric, with denominators, in the delivery.

    5. Decision

      Continue, change or stop, on your own criteria, with the ledger as the record.

    The pilot ends with a ledger your review can read row by row.

    Scope a pilot

    Children, consent and residency GDPR Article 8 · COPPA · FERPA · Annex III

    The controls a review of learner data will ask for

    A Norwegian company under GDPR. Learner data stays in Europe by default, is handled for the learner's age under Article 8, and carries the documentation an Annex III education deployment needs. US programmes run under FERPA and COPPA.

    Jurisdiction
    Norway · GDPR-native
    Children
    GDPR Article 8 handling · COPPA where it applies
    Records
    FERPA controls for US educational records
    EU AI Act
    Annex III education documentation
    Accessibility
    WCAG 2.2 AA at code level · no overlay widgets
    Transparency
    AI-drafted text labelled to learners · Article 50
    Storage
    EEA by default
    Consent
    Captions and recordings consented separately
    Contracts
    Standard DPA terms · SCCs available
    Erasure
    30-day end-of-contract SLA

    The AI Implementation service line AI Data & Evaluation Human and model evaluation

    Scope a programme A feasibility read · a bounded first cohort

    Tell us the programme

    We scope against the programme as it runs today, agree what the model may say and where a person rules, and prove the method on a bounded first cohort.

    1. Scope
    2. Scenarios
    3. Controls
    4. First cohort
    5. Ledger

    A bounded first cohort carries its own acceptance criteria and its own ledger. You judge it against your programme.

    Briefs are treated as confidential. We are used to programmes that cannot be named and learner data that cannot leave the EEA.

    The brief Tell us the programme, the learners and what the model will do for them. We reply with a feasibility read.

    What the programme needs (optional)

    We use the information you provide to assess, respond to and manage your enquiry in accordance with our Privacy Policy.