Use Case Intelligence RSS Search use cases Search
Google Cloud Software / SaaS New York and Israel

Eon

Data Lake / Data Warehouse Modernization · Enterprise Knowledge Search

Eon needed to turn static backup archives into queryable data assets so customers could recover information faster, search historical data with natural language, and cut backup-storage cost instead of treating archives as passive cold copies.

Read the original story Explore all use cases
90% improvement in data recovery time
at least 40%

Reported impact

Business outcome

Eon turned backups into searchable data lakes, cut recovery time and storage cost, and gave customers a much more useful way to work with historical data than traditional restore-centric approaches.

  • Cost Reduction
  • Scalability
  • Speed to Market

Solution

Eon built a backup-data platform on Google Cloud that transforms archived files into live data lakes. Backup content is stored in Cloud Storage, then converted into an analytics-ready format that BigQuery can query directly without manual restores or data transfers. As new data is ingested, Eon indexes metadata and embeddings into a vector store on Vertex AI, and Gemini plus a custom Agent Development Kit workflow allow customers to ask natural-language questions over petabytes of backup history. The system then generates SQL and runs external BigQuery queries against the data in Cloud Storage. This architecture gives customers fast, granular recovery access, reduces backup infrastructure cost through global deduplication optimized for object storage, and turns backups into a searchable operational data source rather than a last-resort archive.

Data flow

Backup data is stored in Cloud Storage, indexed into a Vertex AI vector layer, and queried through BigQuery. Users ask natural-language questions with Gemini, an ADK-based agent turns them into SQL, and BigQuery executes the query directly against the backup data lake.

Solution architecture

5 components · 4 layers
  1. Compute
    • Vertex AI Hosts the vector-store indexing layer built from backup metadata and embeddings.
    • Gemini Translates natural-language backup questions into queries over the data lake.
  2. Storage
    • Cloud Storage Stores backup data in a form that Eon can transform into live, queryable data lakes.
  3. Serving
    • BigQuery Queries backup data directly and returns analytical answers without requiring restores.
  4. Orchestration
    • Agent Development Kit (ADK) Powers the custom agent that converts user questions into complex SQL over backup data.

Architecture clues

  • ADK is used to generate SQL from natural-language questions
  • BigQuery runs external queries directly on backup data
  • Global deduplication is optimized for Cloud Storage
  • Vertex AI stores metadata embeddings

Evidence from the source

As Eon backs up the data, it automatically indexes and embeds metadata into a vector store on Vertex AI.
This allows customers to search across petabytes of historical data asking natural language questions with Gemini
Using the Agent Development Kit (ADK), Eon has built a customized agent to convert these natural language queries into complex SQL queries.
improving data recovery time by up to 90%
running on Cloud Storage, Eon reduces customers’ cloud backup infrastructure costs by at least 40%
Transparency Evidence & methodology 95/100 reference value · 82% 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 depth20/25
    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
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence82%
  • 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
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • 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. Google Cloud

    Eon customer story

    First-party
    https://cloud.google.com/customers/eon
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
  2. LinkedIn

    Eon.io | LinkedIn

    Independent secondary
    https://www.linkedin.com/company/eon-io/

    The Organization JSON-LD lists addressLocality 'New York', and addressCountry 'US', and numberOfEmployees value 249.

    Source type
    Structured company profile
    Supports
    • Company size

Date evidence

  • First archived Feb 12, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Feb 10, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
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
Google Cloud Modified · Sep 22, 2026 Convert Human Digital Business Commercial and Professional Services Brazil Convert Human Digital Business is Grupo Dreamers' digital agency, specializing in connecting creativity, technology, data, and performance with one core objective: to unlock our clients' business potential through… Complex data analysis 8.4x faster Data Lake / Data Warehouse ModernizationEnterprise Knowledge Search BigQuery · Gemini Enterprise · Google Workspace Google Cloud Archived · Jul 23, 2026 TELUS Telecommunications Canada TELUS needed to unify siloed customer and network data so teams could trust the same foundation for generative AI, launch new services faster, and scale agentic platforms without each business unit building its own… 90% of AI model traffic runs through Gemini Enterprise Agent Platform Customer Service AutomationData Lake / Data Warehouse Modernization BigQuery · BigQuery Analytics Hub · Cloud SQL Google Cloud Archived · May 10, 2026 Power Retail Nordics Power needed a shared data and identity foundation across countries, stores, and SAP workloads so it could stop working from siloed data warehouses and launch AI experiments without heavy setup each time. Data Lake / Data Warehouse ModernizationEnterprise Knowledge Search BigQuery · Gemini · Looker