Use Case Intelligence RSS Search use cases Search
OpenAI Education Brazil

Arco Educação

Document Processing

Arco Educação needed to reduce the time teachers spend on lesson planning and individualized education plans so they could focus more on direct instruction, especially for students with diverse learning needs.

Read the original story Explore all use cases
Arco serves over 3 million students
Over 1.7 million students are enrolled in special-needs programs in Brazil
Pilot in 50 schools with plans to scale to 600 schools and about 70,000 students by the end of the year
Teachers in Brazil spend about a third of their time on administrative tasks

Reported impact

Business outcome

Arco reduced lesson-planning effort, increased teacher confidence and autonomy, and created a scalable path to personalized instruction across thousands of schools and millions of students.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

Arco Educação built Teacher Assistant with OpenAI to help teachers generate lesson plans and adapt them to individual student needs at scale. The system encodes inclusion archetypes and teaching protocols created with pedagogical and inclusion experts, then uses OpenAI models to personalize activities and questions based on learning profiles such as autism, ADHD, hyperactivity, or dyslexia. Teachers begin from a general lesson plan and then describe a student’s inclusion needs so the assistant can generate a tailored plan, while uploaded student data remains visible only to the teacher for privacy. Arco is piloting the tool in 50 schools before scaling toward hundreds more and eventually across a customer base of over 3 million students, using phased rollout, continuous testing, and refinement to improve quality and reliability. The goal is not to replace educators, but to free hours of administrative work so they can concentrate on students.

Data flow

Teachers start from curriculum and student inclusion needs, which are combined with Arco’s encoded archetypes and expert protocols. OpenAI models then generate tailored lesson plans and activities that teachers review and use directly in the classroom.

Solution architecture

2 components · 2 layers
  1. Compute
    • OpenAI models Adapt classroom questions and activities to each student profile and teacher request.
  2. Serving
    • Teacher Assistant Generates general and individualized lesson plans for teachers based on curriculum and inclusion needs.

Architecture clues

  • Long-term plan expands to public and private K-12 schools across Brazil and Latin America
  • Only the teacher can access uploaded student data
  • Rollout is phased with continuous testing and refinement
  • System codifies inclusion archetypes and protocols with pedagogical and inclusion experts

Evidence from the source

"Arco is beginning to pilot the Teacher Assistant in 50 schools"
"Arco then uses OpenAI models to enable teachers to adapt questions and activities based on each student’s profile."
"The Teacher Assistant allowed me to optimize my time, saving me hours"
"The Teacher Assistant helps teachers create general lesson plans and then tailor them to individual students’ needs"
Transparency Evidence & methodology 75/100 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 value75/100
  • 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 impact0/25
    0 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 provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    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

    Arco Educação customer story

    First-party
    https://openai.com/index/arco-education/
    Source type
    Vendor-published customer story
    Published
    Sep 17, 2024
    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

  • Published on source page Sep 17, 2024 · OpenAI · First-party
    Open date source
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 Aug 26, 2024 Arizona State University Education North America Today, ASU is enhancing educational outcomes by integrating ChatGPT Edu into projects across teaching, research, and operations. Guided by the ASU charter, which prioritizes inclusion over exclusion, research benefiting… Document ProcessingEnterprise Knowledge Search ChatGPT Edu OpenAI Oct 16, 2026 Benefit Street Partners Financial Services North America Benefit Street Partners needed to answer investment-committee follow-up questions faster, compare lender marks across shared loans, and review 300-page credit agreements for clauses that could shift value away from… 10–12 hours total. Document ProcessingRisk Management BDC mark tracker · Codex · Credit agreement analyzer 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