One learning experience.
An expandable opportunity.

The project currently has a functional product specification, a design system, and interface concepts for multilingual dashboards, spaced-repetition practice, AI conversation, and review games. The source material includes desktop and mobile layouts.

This website turns that specification into an English product presentation with local, interactive examples. The full learning platform, AI integrations, account system, payments, and operational analytics are still to be built and validated.

The product is being designed for learners who want to develop more than one language without maintaining separate, competing routines. The intended experience balances time between languages and links recall directly to practical use.

Three connected building blocks

• Contextual recall: spaced repetition of useful phrases and natural expressions.
• Guided conversation: AI role-play for everyday situations, with feedback and opportunities to save phrases for review.
• Sustainable practice: short sessions, review challenges, and a consolidated view of habits and progress.

The planned differentiation is the connection between these parts. Its effectiveness and learner preference must be evaluated through product testing.

The initial specification proposes a freemium subscription model, with a limited entry tier and paid plans for more intensive, multilingual use.

All prices are proposals from the product specification, in Brazilian reais. They are not live offers. No pricing, revenue, margin, or conversion assumptions have been validated.

What must be tested

Willingness to pay, free-to-paid conversion, engagement, retention, support requirements, and the cost of AI conversation and voice features. Sustainable pricing depends on those results.

The proposed starting point is Brazilian learners studying English and Spanish. This is a go-to-market hypothesis drawn from the specification's audience and launch scope, not an established customer base.

These are product and distribution hypotheses. The sequence should follow pilot evidence and implementation capacity.

1. Deliver a connected pilot

Build onboarding for the first language pair, phrase-based review, basic progress tracking, and the text tutor prototype. Instrument the learning loop so pilot behavior can be evaluated.

2. Validate learner value

Evaluate activation, repeat usage, review completion, confidence in conversation, and the experience of alternating between languages. Define success criteria before drawing conclusions.

3. Validate commercial feasibility

Test plan preference, willingness to pay, retention, and AI operating costs. Use observed behavior to assess a viable subscription proposition.

4. Expand deliberately

Prioritize additional languages and voice features after the core loop has demonstrated value. Evaluate household and institutional demand separately.

• Content quality: ensure natural expressions, useful context, and a coherent learning progression for each language.
• AI reliability: evaluate correction quality, response consistency, and guardrails for conversational practice.
• Operating economics: understand the cost of tutor sessions, voice, infrastructure, and support before committing to unrestricted usage.
• Learner retention: determine whether a shared multilingual routine helps people return consistently.
• Delivery scope: keep the initial release focused enough to build, test, and improve before widening the catalog.
• Privacy and permissions: define account, voice-data, and institution requirements when those features are implemented.

These considerations guide product diligence and help turn a defined vision into an evidence-based launch plan.