Use Case Intelligence RSS Search use cases Search
Google Cloud Software / SaaS United Kingdom

Fifth Dimension

Document Processing · Enterprise Knowledge Search

Fifth Dimension needed to process large commercial-real-estate deal datasets with long-context reasoning, secure centralized model access, and internal developer adoption without forcing engineers to manage separate vendor runtimes for Gemini and Claude.

Read the original story Explore all use cases
Engineers are generating more than 300,000 lines of code monthly
Processed massive deal datasets containing thousands of documents using Gemini’s 1-million-token context window
consistently accept 98% of suggestions

Reported impact

Business outcome

Fifth Dimension processed larger deal datasets securely, improved internal engineering adoption, and gained the flexibility to use the best model at each phase of a complex commercial-real-estate workflow.

  • Cost Reduction
  • Productivity Improvement
  • Scalability

Solution

Fifth Dimension expanded its Google Cloud estate into a multi-model document-processing platform that combines Gemini platform, Claude, and core data services. Gemini platform centralizes model inference securely and supports workflows that can last one to three hours while switching models at different phases. The team uses Gemini for large-scale document grouping and Claude for extraction and reasoning when working through deal datasets containing thousands of documents. Cloud SQL for PostgreSQL and Google Cloud Storage store relational and unstructured data, while BigQuery tracks analytics and usage. The same environment also improved internal engineering adoption, with engineers generating more than 300,000 lines of code monthly and accepting 98% of suggestions. This gives Fifth Dimension a governed way to route each stage of document intelligence to the best-fit model without rebuilding the platform per vendor.

Data flow

Large document sets are stored in Google Cloud Storage and Cloud SQL-backed application workflows, then orchestrated through Gemini platform. Gemini handles large-scale grouping, Claude performs extraction and reasoning, and BigQuery tracks analytics and usage across the platform.

Solution architecture

5 components · 3 layers
  1. Compute
    • Claude Performs high-performance extraction and reasoning over commercial-real-estate deal documents.
  2. Storage
    • Cloud SQL Stores relational application data that supports the document-processing platform.
    • BigQuery Acts as the central analytics and usage-tracking engine for the environment.
    • Google Cloud Storage Stores unstructured document content used in large-scale document-processing workflows.
  3. Orchestration
    • Gemini platform Centralizes secure model inference and orchestrates long-running multi-model document workflows.

Architecture clues

  • BigQuery serves as the central engine for data analysis and usage tracking
  • Claude is used for extraction and reasoning
  • Gemini is used for initial large-scale document grouping
  • Gemini platform supports workflows lasting between 1 and 3 hours

Evidence from the source

BigQuery serves as the central engine for data analysis and usage tracking.
Engineers are generating more than 300,000 lines of code monthly and consistently accept 98% of suggestions.
Every engineer at Fifth Dimension is an active Claude Code user.
Gemini platform supports long-running workflows that can sometimes last between 1 and 3 hours
we will sometimes use Gemini for initial large-scale document grouping, then switch to Claude for subsequent high-performance data extraction and reasoning.
Transparency Evidence & methodology 85/100 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 value85/100
  • 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 impact15/25
    1 metric 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

    Fifth Dimension customer story

    First-party
    https://cloud.google.com/customers/fifth-dimension-anthropic
    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. Built In

    Fifth Dimension Careers, Perks + Culture | Built In

    Independent secondary
    https://builtin.com/company/fifth-dimension

    The Organization JSON-LD lists addressLocality 'London', addressCountry 'GB', and numberOfEmployees value 26.

    Source type
    Structured company profile
    Supports
    • Company size

Date evidence

  • First archived Apr 13, 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 Oct 9, 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 · Jun 9, 2026 igot.ai Software / SaaS Vietnam igot.ai needed a governed AI operating model for audit and enterprise workflows, where teams could search and reason over complex document repositories without maintaining heavy custom infrastructure. Document ProcessingEnterprise Knowledge Search BigQuery · Gemini Enterprise Agent Platform · Gemini Pro Google Cloud Archived · Feb 14, 2026 Mosaic AI Software / SaaS Israel Mosaic AI, an Enterprise AI platform, unifies a company's fragmented knowledge and tech stack onto a single platform where companies can build AI Assistants, workflows, and analytics that boost employee output and drive… In fact, generative AI is becoming nearly ubiquitous; its market size is expected to show an annual growth rate… Document ProcessingEnterprise Knowledge Search Gemini · Vertex AI Google Cloud Archived · Sep 27, 2026 SIGNAL IDUNA Financial Services Germany SIGNAL IDUNA needed to spread AI safely across a large insurance workforce, make a century of internal policy knowledge searchable, and let teams build their own agents without creating a fragmented, insecure shadow-AI… 80% weekly active adoption rate with a +45 NPS in first five months Document ProcessingEnterprise Knowledge Search Document AI · Gemini · Gemini Enterprise Agent Platform