Use Case Intelligence RSS Search use cases Search
OpenAI Software / SaaS Global

Preply

Customer Service Automation · Document Processing

Preply wanted to personalize language learning more deeply and reduce repetitive tutor work without replacing the human relationship that makes one-to-one teaching effective.

Read the original story Explore all use cases
4.7/5 satisfaction rating
70% product market fit score
75% of English-language learners actively use Lesson Insights
95% ChatGPT weekly active usage among Preply employees

Reported impact

Business outcome

Preply increased internal AI adoption, helped tutors and learners keep engaging with personalized lesson follow-ups over time, and reduced the administrative burden of teaching while improving the continuity and perceived value of each learning journey.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

Preply built Lesson Insights on top of OpenAI so each live lesson could become a personalized learning loop instead of a standalone conversation. With learner consent, lessons in the Preply Classroom are recorded and transcribed, then an OpenAI-powered workflow generates structured feedback on grammar, vocabulary, pronunciation, lesson topics, and next steps just before the session ends so tutor and learner can review it together. Those outputs feed directly into Preply's self-learning exercise engine, creating personalized homework and practice that compounds lesson to lesson. Internally, Preply also deployed ChatGPT Enterprise across more than 600 employees and embedded OpenAI APIs, custom GPTs such as Brand Voice GPT, and Codex into content and engineering workflows. By pairing AI with human tutors rather than replacing them, Preply created a system where the platform handles summary, structure, and personalization while tutors focus on motivation, context, and teaching judgment.

Data flow

Lesson recordings and transcripts from the Preply Classroom are processed through the OpenAI API into summaries, corrections, recommendations, and next steps. Those insights flow into the chat thread and self-learning engine, while internal teams use ChatGPT Enterprise, Brand Voice GPT, and Codex for operational and product workflows.

Solution architecture

5 components · 3 layers
  1. Compute
    • OpenAI API Generates lesson summaries, feedback, and self-learning inputs from class transcripts.
  2. Serving
    • Lesson Insights Turns each tutoring session into structured feedback and personalized follow-up learning.
    • ChatGPT Enterprise Supports company-wide AI adoption and everyday work across more than 600 employees.
    • Brand Voice GPT Helps teams create content that stays aligned with Preply's messaging and tone.
  3. Orchestration
    • Codex Accelerates engineering work such as code generation, PR reviews, and debugging.

Architecture clues

  • Brand Voice GPT and Codex extend AI into internal content and engineering workflows
  • Insight generation is scheduled a few minutes before the end of the lesson
  • Lesson outputs feed directly into a self-learning exercise engine

Evidence from the source

"95% ChatGPT weekly active usage among Preply employees"
"Before I started using Preply's AI feature ... that time has been cut by more than half."
"Lesson Insights, an OpenAI API-powered experience that transforms every lesson into a personalized learning journey"
"Those insights feed directly into Preply’s self-learning exercise engine"
Transparency Evidence & methodology 100/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. OpenAI

    Preply customer story

    First-party
    https://openai.com/index/preply/
    Source type
    Vendor-published customer story
    Published
    Jun 12, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
OpenAI Dec 1, 2025 Mirakl Software / SaaS Global Mirakl wanted AI to become a company-wide capability that speeds internal work, improves support, and removes friction from marketplace catalog onboarding so retailers can move toward agent-driven commerce. 37% efficiency improvement in customer support while maintaining 96% customer satisfaction Customer Service AutomationDocument Processing Catalog Transformer · ChatGPT Enterprise · Mirakl Nexus OpenAI Oct 16, 2026 Itaú Financial Services Latin America Itaú needed to make financial guidance simpler and more personalized for millions of customers while also scaling document-heavy internal workflows, all under the governance, observability, and economic controls… 100% of the customer base is the goal by the end of 2026 Customer Service AutomationDocument Processing Customer DNA · IARA · OpenAI models OpenAI Sep 25, 2026 Wayfair Retail North America Wayfair needed to keep product attributes accurate across a massive catalog and handle large supplier-support volumes without relying on slow, error-prone manual review. 1,200 ChatGPT Enterprise seats deployed Customer Service AutomationDocument Processing ChatGPT Enterprise · ChatGPT Work · OpenAI API