What challenges did Fifth Dimension face before AI implementation?

Commercial real estate teams were spending days or weeks drafting complex investment memos. The business needed a reliable way to process large document sets and run multi-step extraction and reasoning workflows quickly.

What was the impact of the AI solution?

Investment memo drafting time was reduced from days or weeks to about 30 minutes. The company reports 99.9% reliability for long-running workflows. Engineers generate more than 300,000 lines of code per month and accept 98% of suggestions. The company expects inference spend to grow 6x in 2026 due to customer growth.

Source

GCPEvidence: Medium50/100

Fifth Dimension: multi-model CRE document workflows with Vertex AI + Gemini for 30-minute investment memos

Use case typeDocument processingUpdated Jun 13, 2026

Fifth Dimension is an AI platform for commercial real estate workflows that handles document-heavy acquisition intelligence, asset optimization, reporting, and communication tasks. The company uses Google Cloud to process massive deal datasets and long-running workflows involving hundreds or thousands of documents.

Organization: Fifth Dimension
Industry: Real Estate
Location: United Kingdom
Published: May 2026

Reported outcomes

quantified impactCost savings

30 minutestime99.9%quantified impact+98%quantified impact

Strategic outcomes

Speed & agilityReduced memo drafting to minutesScale & capacityProcessed massive document workflowsNew product / capabilityBuilt multi-model CRE workflow platformBetter decisions & insightEnabled document-based investment intelligence

Catalog median for cost savings deployments: +53.5% across 16 reported metrics. Compare benchmarks →

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Time: 30 minutes decrease

Google Cloud Customer StoryMay 13, 2026Customer storyInferred claimMedium evidence strength

Investment memo drafting time was reduced from days or weeks to about 30 minutes.

Normalized claim

Quantified impact: 99.9%

Google Cloud Customer StoryMay 13, 2026Customer storyInferred claimMedium evidence strength

The company reports 99.9% reliability for long-running workflows.

Normalized claim

Quantified impact: 98% increase

Google Cloud Customer StoryMay 13, 2026Customer storyInferred claimMedium evidence strength

Engineers generate more than 300,000 lines of code per month and accept 98% of suggestions.

Normalized claim

Quantified impact: 6 x increase

Google Cloud Customer StoryMay 13, 2026Customer storyInferred claimMedium evidence strength

The company expects inference spend to grow 6x in 2026 due to customer growth.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Fifth Dimension
Provider: GCP
Maturity: Unknown
Linked source: Google Cloud Customer Story

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

1Document processing
2Workflow orchestration
3Investment research

Commercial real estate teams were spending days or weeks drafting complex investment memos.
The business needed a reliable way to process large document sets and run multi-step extraction and reasoning workflows quickly.

Fifth Dimension built a multi-model AI platform on Google Cloud.
Vertex AI orchestrates long-running workflows and centrally runs model inference securely.
Gemini Flash and Gemini Pro are used for large-scale document grouping and ingestion with a 1-million-token context window.
Claude models are used for high-precision data extraction, reasoning, and code generation tasks such as rental income adjustments and Excel model code generation.
BigQuery is used for natural language analytics for account managers, and the platform also uses Cloud Run, Cloud SQL, Google Cloud Storage, and Model Garden on Vertex AI.

Technologies

Vertex AI Gemini BigQuery Cloud Run Cloud SQL Google Cloud Storage Model Garden on Vertex AI Claude

Investment memo drafting time was reduced from days or weeks to about 30 minutes.
The company reports 99.9% reliability for long-running workflows.
Engineers generate more than 300,000 lines of code per month and accept 98% of suggestions.
The company expects inference spend to grow 6x in 2026 due to customer growth.

Architecture

Vertex AI orchestrates a multi-model workflow using Gemini for initial large-scale document grouping and ingestion, then switches to Claude for subsequent extraction, reasoning, and code generation. The platform also uses BigQuery for analytics, Cloud Run, Cloud SQL, Google Cloud Storage, and Model Garden on Vertex AI.

Sources & evidence1

Evidence: Medium50/100Evidence strength