Whoever creates a training project uploads the documents. The system generates the path, calibrates the quizzes where needed, reformulates the explanations in the style that works for each learner. A single system serves three distinct audiences: companies training their own employees, professionals preparing for exams and certifications, students studying on their own materials.
The founding principle of AYXZA Tutor is simple: whoever creates a training project uploads the manuals, and the system does the rest. From the uploaded documents the artificial intelligence generates a proposal for a structured learning path, which the creator validates. End users walk the modules with explanations generated from the corpus, quizzes that focus where they get it wrong and reformulations calibrated on the approach that works for them. Companies get completion tracking and certificates; individuals get a personal tutor that knows them.
Three different needs coexist in the same system. The content and the context change, not the engine. This is the platform's first economic advantage: a single engineering practice serves markets that normally require separate products.
Onboarding, internal procedures, compliance (for example safety or anti-money-laundering material as non-certified internal training), updates on one's own products and services. The company uploads its manuals and trains its employees on its real material.
Qualifying exams, technical certifications, public competitions. The professional uses a project from the official catalogue or uploads their own materials and builds a tailored path, with quizzes that insist where they are weakest.
The student uploads their own notes and books and has the path built for them: explanations drawn from their material, assessments that return to wrongly-answered concepts, review cards written from their own books.
The training project is the central entity. From uploading the documents to issuing the certificate, the path goes through a precise sequence. The system generates the learning proposal; approval always stays with a person.
A guarantee constraint, not a detail: no project goes into delivery without human validation of the syllabus. The machine proposes, the person responsible for the content approves. It is the safeguard that holds together the promise of automation with training responsibility.
The platform is organised on a four-level hierarchy. The colour identifies the role throughout the interface: slate for the superuser, indigo for the company, petrol for whoever takes the courses. An intermediate level, the reseller, exists in the data model without an interface of its own: every company is attached to it through a default reseller.
| Level | Who they are | What they can do |
|---|---|---|
| L4 · Superuser | AYXZA | Manages the entire platform: the companies, the catalogue of official projects and their enabling per company, the system status, AI costs and spending quotas, campaigns and sponsor boxes. |
| L3 · Reseller | Data model only | No interface. The level exists in the data model: every L2 is attached to a default reseller. |
| L2 · Company / Individual | Client company, or the single professional/student | Manages its own L1s (companies only), creates internal training projects, assigns to its members the catalogue projects AYXZA has enabled for the company, sees completion reporting, enables or disables personal creation for its users, uploads the logo shown on certificates. |
| L1 · End user | Employee, professional, student | Has their own login and a personal learning history. Walks the assigned projects and, if enabled, creates personal projects. |
A professional or a student registers on their own and lives the experience as an ordinary single account. Underneath, the system creates in a single operation an “individual” L2 and an L1 within it. The interface never shows employee management, group reporting or company permissions. This choice has a precise reason: a single path in the code for permissions, quotas and billing. Billing is always to the L2, whatever it is.
Every project has an owner, a visibility perimeter and a lifecycle. The underlying rule is clear: only the creator modifies. A company does not touch another company's projects or those of the official catalogue; it uses them. A catalogue project enabled for a company stays AYXZA property: the company assigns it, does not modify it.
Every enabled level: the superuser for the official catalogue, the company for its own internal paths, the end user for their own (if the company allows it; for individuals it is always allowed).
The creator uploads the source documents: PDF with text, Word, plain text or Markdown. Technical requirement: the files must contain extractable text. Image-scans are rejected on upload with a clear message and guidance on how to obtain a text document.
Language of syllabus, explanations and assessments (Italian, English, Spanish, French, German, Portuguese), whatever the language of the manuals, with proper names and technical terms left in the original; length of the explanations (standard, short, in-depth); breadth of the modules (standard, compact, broad); pass threshold; review cards yes or no. True/false questions and the certificate come out in the same language.
Two passes: first a map of the manual's themes, then the structure in modules and topics, each with references to the sections it derives from.
Syllabus references not found in the manual block approval until the creator corrects them, deletes them or explicitly chooses to keep them. A topic added by hand is linked to a section of the manual.
The creator reviews the proposal: renames, reorders, merges, deletes, adds modules. Approval is explicit and mandatory, and the approved syllabus becomes an immutable version.
After approval the system writes the explanations, the assessment questions and the review cards. Before starting it shows the cost estimate, next to the real cost of the last run.
New manuals, syllabus revision, new version. A revision is approved when nobody is walking the course, and the topics that stayed the same keep the content already generated and the learners' choices.
| Created by | Visibility | Example |
|---|---|---|
| L4 | Official catalogue: AYXZA enables it for individual companies, which assign it to their users | “State-exam preparation”, “Basic IT security” |
| L2 company | Only its own users | “Onboarding new hires”, “Internal quality procedures” |
| L1 | Only themselves | The student uploads the university course notes |
Personal creation by employees is governed by a permission, off by default in companies and always on for individuals. When it is on, an employee's personal projects live within the company perimeter but their content is not visible to the company: the company knows they exist and how much space they occupy, not what they contain. It is the principle of proportionality applied to data.
The explanations are written from the passages of the manuals that the syllabus cites for each topic, in the length chosen by the course creator, and are navigable by topic. A second pass checks them against the same passages.
Multiple choice and true/false, generated from the manual and verified against the sources before being administered. The pass threshold is set by the course creator (seventy out of a hundred unless changed).
Once the threshold is passed, the module is completed and the next one unlocks, with a recorded date. On completing all modules: final project outcome and, where provided, certificate.
Three to five short questions per topic, with a one- or two-sentence answer, written specifically from the manual and checked against the sources. You reveal the answer and mark “I knew it” or “To review”; the system shows first the cards of topics answered wrongly in assessments and those marked for review. They do not count towards the score.
Adaptivity is not a label. It takes two concrete forms, both based on fine tracking of every answer, traced back to the syllabus concept it belongs to.
Every topic answered wrongly returns in the next assessment with at most two unscored questions, until it is answered correctly, with at most two topics per assessment. The review does not depend on the days elapsed but on the errors still open.
With two or more errors on the same topic the alternative explanation arrives by itself, for at most two topics per submission; the learner can also ask for it, with a button, on any topic answered wrongly. The reformulation uses an alternative approach: practical example, formal definition, analogy, step-by-step procedure. It records which approach preceded success. The effective-style profile, learned per person, guides reformulations across all their projects. An explicit guard in the prompts prevents the reformulation from being a mere paraphrase: it must change the approach, not the words.
The reporting is deliberately asymmetric, and this asymmetry is a guarantee offered to the end user, not a limit. The separation is enforced at the level of data querying, not just the interface: the individual learning datum is not reachable by the company by construction.
The anonymisation threshold (five users minimum per aggregate) prevents the “group” datum from becoming a way to trace back to the single person. The signal the company obtains stays valuable: if a concept puts the whole group in difficulty, the material is often lacking or badly explained, and that is where it is worth intervening.
On successful completion the system generates a PDF document with the person, the course, the date, the outcome, the company logo and a sixty-four-character verification code: anyone can check it on a public page, which confirms course, date and issuer without showing the name. It counts as internal evidence and corporate documentation. It is not a certification of regulated mandatory training: it does not replace the courses delivered by accredited bodies.
Tutor installs on the phone or the computer as an app, without going through a store; without a network it shows only a “You are offline” page and no data stays on the device. On every page three buttons enlarge the text. Whoever receives the company link signs up on their own with name and email, receives the temporary password by mail and may find the courses chosen by the company already assigned. The interface speaks Italian and English: each person picks a language from the profile, the company sets the default for its users and, when no choice has been made, the browser's language applies.
The contact person uploads the company logo (PNG, JPEG or WebP), shown in the heading of the certificates. They see the per-person report and the group summary, with a threshold of five people for every aggregate number. Courses are assigned automatically to whoever signs up from the link. For every account: new temporary password, archiving and restoring, deletion for those with no history.
Campaigns with free courses: a container company, a public sign-up link with an anti-robot check that uses no external service, a daily cap on sign-ups, credential emails sent from a queue at a controlled pace, a privacy notice chosen per company. AI costs per use and per project, engine spending quotas per platform and per company checked before every generation. Up to two sponsor boxes per company in the top bar, with clicks counted without knowing who made them.
Training is born from the company's real procedures, not from generic courses. Completion tracking and certificates ready for internal audit. Respect for the person: no surveillance of individual errors, an element that eases adoption and labour relations.
Preparation focuses where one is weak and returns to wrongly-answered concepts until they stick. The explanations change form until one works. Study time goes where it is needed, not evenly spread over what one already knows.
The student uploads notes and texts and gets a structured path, with assessment and review. Explanations, questions and cards come only from what has been uploaded, and a second pass checks them against the same passages: no content extraneous to the course.
No instructional designer is needed to build the path: the system proposes it from the documents, and a person validates it. The human work shifts from writing to review, far faster.
The same platform serves companies, professionals and students. No product fragmentation, a single system to maintain and evolve, economies of scale that reflect on the price.
An honest product declares what it does not do. The limits that follow are partly technical constraints, partly deliberate design choices. Knowing them beforehand avoids disappointed expectations.
The manuals must contain extractable text. Image-scans are rejected on upload. A share of real corporate material is made of scanned documents: for those cases a text PDF must be obtained first.
They count as internal evidence, they do not replace certified mandatory training (for example that required by safety law) nor do they grant credits from professional bodies.
Anyone expecting a control dashboard on the single employee will not find it: it is a choice, not a shortcoming. To a manager used to individual measurement it may seem a limit; for the organisation it is a protection.
On disordered or incomplete material the syllabus proposal can be weak. Human validation is the safeguard for this, but it remains real review work: it is not “zero effort”.
Every question passes a verification against the sources before being administered. The residual risk exists, as in every generative system, and must be overseen by human review.
The AI functions rely on external language-model providers, under the relevant processing agreements. For companies with stringent requirements the same platform runs on a dedicated instance (see the technical part). When the AI service does not answer, the page says so in a plain sentence for each cause; the technical detail stays in the system logs.
Errors, requested explanations, choices on the cards and learning profile are accessible only to the person concerned, never to the company. The separation is enforced at the level of data querying.
Traffic encrypted at the edge, secure cookies, protection against forged requests in restrictive mode, passwords stored with Argon2, a limit on sign-in and sign-up attempts.
For employees the data controller is the company and AYXZA is the processor; for individuals AYXZA is the controller. An account with no history is deleted; the others are archived and restored, so the learning history is not lost through a management mistake.
For those who cannot accept that content transits a shared infrastructure, the platform installs on a dedicated instance: same code, a single client.
The architecture favours stability and reuse over novelty. It deliberately takes up the patterns of another AYXZA system already in service, so as to rest on tested skills and operational procedures instead of reinventing them.
| Area | Choice |
|---|---|
| Application | FastAPI with Jinja2 templates, server-side rendering, no single-page application. A light and robust interface. |
| Database | PostgreSQL, a dedicated database with separate schemas for the domain and the AI engine, migrations versioned with Alembic. |
| Authentication | Passwords stored with Argon2, session in a signed cookie holding no secrets, role re-read from the database on every request, password change on first access, limit on sign-in attempts, anti-forgery protection in restrictive mode. |
| AI engine | AYXZA Relay as an in-process dependency. All AI functions pass through the engine as versioned prompts; no direct calls to providers from the application. |
| Multi-tenancy | Logical isolation: the scope of every operation is derived from the server-side session, never from the payload sent by the client. The dedicated profile is the same codebase with a single client. |
Every intelligent function is a versioned prompt on the engine, with a validated output schema where needed. The most commercially sensitive risk, a quiz with a wrong answer, is overseen by a double pass.
| Function | How it is built |
|---|---|
| Syllabus generation | Two passes: a map of the manual's themes, then modules and topics with references to the sections, found automatically in the text. Output in structured, validated format. |
| Explanations | Written from the passages of the manual cited for that topic, in the language and length chosen for the course; a second prompt checks them against the same passages. |
| Quiz generation | Prompt with output schema (question, options, correct answer, concept, error explanation). Double pass: a critic prompt verifies every question against the sources before administration. |
| Review cards | A dedicated prompt writes three to five cards per topic from the cited passages; a second prompt verifies their correctness and drops duplicates across topics. |
| Explanation reformulation | Prompt with an approach parameter and per-user approach history, with an explicit guard against paraphrase. |
The data core records every answer with the concept, the type of error, the module, the instant and the explanation approach served. This granularity carries the assessment that insists where needed, the choice of the alternative explanation and the concept-level summary the company sees in aggregate form.
| Entity | Role |
|---|---|
| progetto_formativo | The central entity: title, status, creator, course settings and current syllabus version. |
| sillabo_versione | Immutable snapshot of the approved syllabus, with reference to the original AI proposal for traceability. |
| avanzamento | Per person and project: current module, status, final outcome and completion date. |
| evento_apprendimento | The granular log of every learning interaction. It is the basis of adaptivity and of the concept-level summary. |
| profilo_didattico | Per person: the explanation approach that proved effective, and the style statistics. |
| attestato | The document generated on completion, with a unique verification code that can be checked on a public page. |
| scheda_ripasso | The cards of a topic, written from the manual and verified. The learner's choice lives in a separate table, which the company does not query. |
The platform is offered as a multi-tenant service, with logical isolation of clients. For organisations with stringent confidentiality requirements the same codebase runs on a dedicated instance: a single client, no sharing of infrastructure with others. The choice between the two profiles does not change functionality, it changes the boundary on which the data lives. The service has been in operation at tutor.ayxza.com since 2 September 2026.