AI transparency

How intle uses AI to generate learning content.

Intle uses AI to detect content type, plan structure, generate editable learning content, and repair malformed model output. AI is an authoring aid: creators remain responsible for review, edits, approval, and deployment.

Model registry reviewed: 2 August 2026

Current model registry

The registry is config-driven: stage-specific environment variables can route a stage to another approved model without changing page copy. The table below reflects the current defaults/active env values visible to this deployment.

Stage	Provider	Model id
Detection	OpenAI	gpt-5.6-luna
Planning	OpenAI	gpt-5.6-terra
Content	OpenAI	gpt-5.6-terra
Editing	OpenAI	gpt-5.6-terra
Vision/source image	OpenAI	gpt-5.6-terra
Fallback	Anthropic	claude-sonnet-4-6

What may be sent to AI providers

- The brief or prompt the creator writes.
- Text extracted from uploaded PDF, DOCX, PPTX, TXT, and supported source files.
- Uploaded source images (PNG, JPG, GIF, WebP), sent to the vision model to produce a text description used as source material.
- Text fetched from user-supplied web, YouTube, or Vimeo source URLs after SSRF-safe fetching.
- Generated content, edit instructions, repair prompts, and model outputs needed to complete the request.
- Generation metadata needed for routing, schema validation, retries, quality gates, and cost telemetry.

Uploaded files may contain personal data if a user includes it. Users should avoid uploading unnecessary personal, confidential, or special-category data.

What is not intentionally sent

- Card numbers or payment-method data.
- Stripe payment method details.
- Raw billing identifiers unless a user explicitly includes them in a brief or uploaded file.
- Account authentication secrets, magic-link tokens, session cookies, or participant HMAC secrets.
- Admin-only notes or internal security logs unrelated to the generation request.

Retention and training defaults

OpenAI

OpenAI states that API data is not used to train models by default unless a customer opts in. Standard API abuse-monitoring retention can be up to 30 days; modified abuse monitoring and zero-data-retention controls are available for eligible customers.

OpenAI API data controls

Anthropic

Anthropic states that commercial/API inputs and outputs are not used for model training by default. Some API features or policy reviews may require retention; zero-data-retention options are available for supported API use.

Anthropic API retention / Anthropic training policy

Workspace-specific OpenAI and Anthropic data-control settings are still being confirmed. Until that check is complete, intle describes AI inference as processed outside the UK/EU by default.

Human oversight

Generated output is editable. Creators are expected to review, correct, and approve content before publishing, hosting, or exporting a SCORM package, especially for compliance-sensitive, health and safety, legal, medical, or regulated training.

Quality and risk controls

- Schema-bound generation through the Vercel AI SDK rather than free-form output where structured content is required.
- Content-quality validators for accessibility, visual density, cognitive load, duplication, and brief alignment.
- A repair pass that fixes common structural issues before schema validation.
- Three-attempt resilience path: primary model, fallback model, then simplified primary generation.
- Creator review and editing before publishing, hosting, or SCORM export.

ICO-aligned disclosure headings

Purpose

AI assists learning-content authoring and does not make access, pricing, or legal-rights decisions about users.

Data minimisation

Only the request content needed for the generation flow is sent to AI providers; payment data and secrets are excluded.

Accountability

Model routing, quality telemetry, provider terms, and human review expectations are documented and reviewed when models or providers change.