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

Mirakl

Customer Service Automation · Document Processing

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.

Read the original story Explore all use cases
37% efficiency improvement in customer support while maintaining 96% customer satisfaction
70% faster creation of internal technical documentation
91% faster catalog onboarding
AI agents now operate 24/7 and in multiple languages

Reported impact

Business outcome

Mirakl sped up internal documentation by 70%, improved support efficiency by 37% while keeping satisfaction at 96%, reduced catalog onboarding time by 91%, and cut categorization errors by about half as it prepared for agent-driven commerce.

  • Customer Experience
  • Productivity Improvement
  • Revenue Growth
  • Scalability

Solution

Mirakl moved from a goal of "everyone uses AI" to "everyone builds with AI," embedding OpenAI-powered workflows into both internal operations and customer-facing commerce systems. ChatGPT Enterprise accelerates internal technical documentation and serves as a builder surface for teams redesigning workflows. Mirakl also built a support agent grounded in company documentation so customer questions can be answered instantly in multiple languages while humans focus on higher-value work. For marketplace data onboarding, its AI-native Catalog Transformer restructures and categorizes incoming catalog data far faster than manual processes, reducing errors that would otherwise hurt conversion and time-to-revenue. Looking ahead, Mirakl is extending these patterns into Mirakl Nexus, infrastructure for multi-merchant baskets, complex transaction flows, and retailer integrations so agent-native shopping and service experiences can run on top of the company's existing marketplace network.

Data flow

Internal documentation and support knowledge flow into ChatGPT Enterprise and the support agent, which answer questions or draft content for employees and customers. Seller catalog data then passes through Catalog Transformer for onboarding and categorization, while Mirakl Nexus connects retailer systems and transaction flows for future agent-native commerce experiences.

Solution architecture

4 components · 2 layers
  1. Serving
    • ChatGPT Enterprise Accelerates internal documentation and gives employees a common environment for building AI-enabled workflows.
    • support agent Answers support questions from Mirakl documentation with instant multi-language responses.
  2. Orchestration
    • Catalog Transformer Automates catalog onboarding and reduces categorization errors for marketplace data.
    • Mirakl Nexus Provides the infrastructure layer for multi-merchant, agent-driven commerce workflows.

Architecture clues

  • Catalog Transformer is the major breakthrough in onboarding speed
  • Company vision shifted from AI use to everyone building agents
  • Mirakl Nexus is being designed for multi-merchant baskets and complex transaction flows
  • Support agent is grounded in Mirakl documentation

Evidence from the source

"70% faster creation of internal technical documentation using ChatGPT Enterprise"
"In customer support, Mirakl built an agent that answers support questions using Mirakl's documentation"
"Their vision evolved to "everyone builds with AI.""
"the AI-native Catalog Transformer cut onboarding time by 91%"
Transparency Evidence & methodology 95/100 reference value · 90% confidence · 2 sources

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 value95/100
  • 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
    4 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence90%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 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 transparency9/10
    2 source references 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

    Mirakl customer story

    First-party
    https://openai.com/index/mirakl/
    Source type
    Vendor-published customer story
    Published
    Dec 1, 2025
    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
  2. LinkedIn

    Mirakl | LinkedIn

    Third-party
    https://www.linkedin.com/company/mirakl/

    The public company page includes numberOfEmployees value 892.

    Source type
    structured profile
    Supports
    • Company size

Date evidence

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

Related

Similar use cases

See all like this
OpenAI Jun 12, 2026 Preply Software / SaaS Global 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. 4.7/5 satisfaction rating Customer Service AutomationDocument Processing Brand Voice GPT · ChatGPT Enterprise · Codex 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