Use Case Intelligence RSS Search use cases Search
Databricks Software / SaaS France

Mirakl

Document Processing · IT Operations Automation

Mirakl needed a better way to support generative AI supplier catalog onboarding for ecommerce marketplaces because strict governance rules and siloed data teams slowed marketplace analytics and made supplier catalog onboarding take weeks per vendor.

Read the original story Explore all use cases
30x faster iteration and delivery across data and ai teams
<24
Cutting onboarding from 28 days to hours with genAI
From 28 days to under 24 hours: tangible AI impact and lower costs

Reported impact

Business outcome

Mirakl improved generative AI supplier catalog onboarding for ecommerce marketplaces with measurable results including Cutting onboarding from 28 days to hours with genAI, Ops overhead equal to 5 full-time engineers, and <24, while giving teams a faster path from governed data to production decisions.

  • Cost Reduction
  • Productivity Improvement
  • Speed to Market

Solution

Mirakl uses Databricks Data + AI Platform to support generative AI supplier catalog onboarding for ecommerce marketplaces. The implementation replaced a legacy state where strict governance rules and siloed data teams slowed marketplace analytics and made supplier catalog onboarding take weeks per vendor. Supplier catalogs and product attributes move through Lakeflow Jobs and land in shared lakehouse datasets, giving teams one trusted data foundation. Unity Catalog governs access, lineage, and compliance across sensitive datasets. MLflow, Model Serving, and Agent Bricks operationalize models, agents, and analytics that deliver normalized supplier catalog entries and genAI onboarding workflows.

Data flow

Supplier catalogs and product attributes land on a shared platform, pipeline services clean and standardize them, governance controls enforce trusted access, and AI, model-serving, and analytics services deliver normalized supplier catalog entries and genAI onboarding workflows.

Solution architecture

6 components · 4 layers
  1. Compute
    • Databricks Data + AI Platform Databricks Data + AI Platform unifies engineering, analytics, governance, and AI workloads for generative AI supplier catalog onboarding for ecommerce marketplaces.
    • MLflow MLflow tracks experiments, versions, and release workflows for models that support generative AI supplier catalog onboarding for ecommerce marketplaces.
  2. Serving
    • Model Serving Model Serving exposes real-time predictions and AI outputs to normalized supplier catalog entries and genAI onboarding workflows.
    • Agent Bricks Agent Bricks packages domain-specific agents that automate parts of generative AI supplier catalog onboarding for ecommerce marketplaces.
  3. Orchestration
    • Lakeflow Jobs Lakeflow Jobs schedules ingestion and transformation of supplier catalogs and product attributes into reusable datasets.
  4. Governance
    • Unity Catalog Unity Catalog applies centralized access controls, lineage, and auditability across sensitive datasets.

Architecture clues

  • Automated ingestion and transformation pipelines keep source data synchronized for downstream analytics and AI.
  • Centralized governance, lineage, and access controls are enforced through Unity Catalog.
  • Cutting onboarding from 28 days to hours with genAI
  • Operational AI workflows are deployed directly beside governed data and analytics assets.
  • Ops overhead equal to 5 full-time engineers

Evidence from the source

Databricks lets us treat models and data as first-class, governed assets,
We can experiment quickly, productionize with confidence, and still know exactly which model version and dataset powered each decision.
We can't send our customers’ data to third parties because of data governance regulations,
We need to control where the data resides and what we do with it.
Transparency Evidence & methodology 100/100 reference value · 89% 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
    6 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • 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 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. Databricks

    Mirakl customer story

    First-party
    https://www.databricks.com/customers/mirakl
    Source type
    Vendor-published customer story
    Published
    Jan 21, 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

  • Published on source page Jan 21, 2026 · Databricks · 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
Google Cloud Modified · Oct 9, 2026 Anthropic Software / SaaS San Francisco, CA, USA During large-scale training runs, traffic is highly variable—dropping to near zero during model checkpointing before bursting to millions of events per minute. Anthropic needed a serverless messaging queue that scaled… Handles peak throughput of over 1M events per second Document ProcessingIT Operations Automation BigQuery · Bigtable · Cloud Pub/Sub Google Cloud Modified · Jul 13, 2026 UJJI AI Software / SaaS United Kingdom Before the strategic partnership between UJJI AI and Google Cloud, the development of a single corporate training, especially for banks and financial entities, struggled with slow and linear production cycles, requiring… , guaranteeing 99.9% availability Document ProcessingIT Operations Automation Cloud Run · Gemini · Gemini Enterprise OpenAI May 7, 2026 Oracle Software / SaaS Global The talent acquisition team used ChatGPT Work to build a talent market intelligence tool that takes a job description, researches comparable roles, benchmarks compensation, and assesses the talent pool across relevant… "We’ve gone from zero to a hundred," says Jan Ackerman, Senior Vice President and Global Head of Talent… Document ProcessingIT Operations Automation ChatGPT Work · Codex