Technology

An architecture designed for evidence and scale

ARASH separates presentation, application, AI services, business logic, data and infrastructure with strict one-way boundaries — so engines can change without touching the classroom experience.

Principles

Six engineering commitments

Six-layer architecture

Presentation, Application, AI Services, Business Logic, Data and Infrastructure with strict one-way boundaries.

Vendor-neutral AI gateway

No provider SDK exists outside the gateway, so engines can be swapped or degraded without touching product code.

Version-stamped scoring

Every score carries its rubric, prompt and model version, making results reproducible months later.

Domain-isolated data

Core, Learning, Conversation, Assessment, Analytics and Administration domains with row-level security per tenant.

Degradation ladder

If an engine is unavailable, the platform reduces depth instead of failing the learner's session.

Scale targets

Designed for 10,000 concurrent learners with 99.9% availability on the learning path.

AI services layer

Specialised engines, one gateway

Each engine has a single job and a versioned contract. No vendor SDK exists outside the gateway.

  1. 1

    Speech Recognition AI

    Transcript, word timings, confidence

  2. 2

    Conversation AI

    Scaffolded dialogue turns and hints

  3. 3

    Pronunciation AI

    Phoneme accuracy, stress, intonation

  4. 4

    Grammar AI

    Error taxonomy, severity, correction

  5. 5

    Vocabulary AI

    Range, CEFR band, target-word coverage

  6. 6

    Fluency AI

    Rate, pauses, disfluency, mean length of run

  7. 7

    Comprehension AI

    Relevance, accuracy, instruction following

  8. 8

    Pragmatic AI

    Register, politeness, turn-taking

  9. 9

    Feedback AI

    Student, teacher and parent feedback variants

  10. 10

    Adaptive Recommendation AI

    Mastery update and next-activity plan

  11. 11

    Learning Analytics AI

    Trajectories, cohorts, at-risk signals

System layers

Six layers, strict boundaries

L1

Presentation Layer

Role-aware clients, speech capture, realtime rendering

Role workspaces
Speaking client
Realtime client
Design system
L2

Application Layer

Gateway, identity, orchestration, quotas, contracts

API gateway
Middleware pipeline
Use-case orchestrators
Realtime gateway
L3

AI Services Layer

AI gateway plus specialized engines and rubric aggregation

Model registry
Analysis engines
Rubric aggregator
Safety filters
L4

Business Logic Layer

Domain invariants, pedagogy policy, workflows, events

Domain modules
Policy engine
Workflow engine
Event publisher
L5

Data Layer

OLTP, OLAP, object storage, cache, research vault

Six data domains
Object storage
Cache cluster
Governance
L6

Infrastructure Layer

Cloud, edge, queues, secrets, observability, DR

Edge & network
Worker pools
Observability
Backup & DR

Backend concerns

Ten disciplined concerns

Each concern has one owner and one place to change.

Controller

Transport handlers, DTO mapping, response envelopes

Middleware

Trace, authN, tenancy, authZ, validation, rate limit

Service Layer

Use-case orchestration and transaction boundaries

Repository Layer

Aggregate persistence, unit of work, row-level tenancy

API

Versioned public, private, AI, admin, analytics, research surfaces

Authentication

Tokens, sessions, SSO, guardian consent gating

Caching

Edge, HTTP, distributed, AI response cache

Logging

Application, audit, security, AI interaction streams

Queue

Scoring, analytics, notify, export lanes with DLQ

Storage

Private audio buckets, signed URLs, lifecycle tiers

API surfaces

Nine versioned surfaces

Separated by audience so security, quotas and deprecation stay independent.

Authentication APISessions, tokens, SSO, step-up
User APIProfiles, roles, links, consent
Learning APICurriculum, classes, assignments, paths
Conversation APIDialogue sessions, voice, transcripts
Assessment APIAttempts, rubrics, scores, feedback
Recommendation APIMastery, plans, spaced repetition
Analytics APIStudent, teacher, usage, performance
Research APIStudies, cohorts, snapshots, exports
Admin APIConfig, prompts, quotas, audit

Talk architecture with us

Happy to walk your IT team through security, retention and integration.