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

Sansan

Sales Automation

Sansan needed to unify fragmented customer and sales data so teams could move from static reporting to immediate, data-driven sales actions without relying on manual aggregation or hallucination-prone AI outputs.

Read the original story Explore all use cases

Reported impact

Business outcome

Sansan eliminated manual aggregation risk, reduced hallucinations in AI-driven insights, and enabled sales teams to move directly from data interpretation to concrete, automated proposal scenarios and next actions.

  • Productivity Improvement
  • Revenue Growth
  • Speed to Market

Solution

Sansan built its Sansan BI platform on Google Cloud to connect analytics directly to sales execution. Looker sits at the center of the design, with LookML encoding complex business logic once so the company can create a reliable single source of truth for customers and internal teams. BigQuery provides the large-scale analytical store, while Gemini is grounded in the semantic layer so natural-language questions and proposal scenarios use the same governed metrics that appear in dashboards. Managed Service for Apache Airflow supports the surrounding data pipeline operations, and Git-based development lets the team review logic changes like code instead of editing dashboards ad hoc. This architecture turns sales data into a conversational system that can suggest next actions, reduce hallucinations, and move field teams from interpreting charts to acting on specific opportunities.

Data flow

Customer and sales data is modeled in BigQuery, governed through LookML inside Looker, and then exposed through dashboards and Gemini-powered conversational analytics so sales staff can ask questions in natural language and receive business-ready recommendations tied to trusted metrics.

Solution architecture

5 components · 5 layers
  1. Compute
    • Gemini Answers natural-language questions and generates actionable proposal scenarios from governed data.
  2. Storage
    • BigQuery Stores and analyzes large sales and customer datasets for rapid querying.
  3. Serving
    • Looker Provides the governed BI and conversational analytics surface used by sales teams.
  4. Orchestration
    • Managed Service for Apache Airflow Supports the managed orchestration of data workflows around Sansan BI.
  5. Governance
    • LookML Defines shared business logic as code so metrics stay consistent across dashboards and AI workflows.

Architecture clues

  • LookML is the semantic layer that grounds both dashboards and Gemini outputs.
  • Sansan BI is positioned as conversational analytics rather than traditional BI reporting.
  • The development life cycle is managed through Git integration for review and governance.
  • The platform is designed to present not only insights but specific next-step proposal scenarios.

Evidence from the source

By having the AI reference accurate metrics defined in LookML, we can suppress hallucinations and provide customers with reliable business insights.
By integrating Looker with BigQuery, Gemini and Gemini platform, Sansan has created a platform where data is not just seen but "spoken."
Created a single source of truth by defining complex business logic as code using LookML
Enabled immediate transition from data interpretation to sales action through automated, reliable proposal scenarios
Reduced "hallucinations" in AI-driven insights by grounding Gemini in accurate metrics defined within the semantic layer
Transparency Evidence & methodology 75/100 reference value · 77% 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 value75/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence77%
  • 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
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    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

    Sansan customer story

    First-party
    https://cloud.google.com/customers/sansan-ai
    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

Date evidence

  • Sitemap last modified Oct 9, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
  • Unverified extracted date Oct 9, 2026 · Google Cloud · Unknown Legacy extracted date without source-page confirmation.
    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 · Aug 26, 2026 UIB Software / SaaS Singapore UIB needed a scalable, low-latency, and localized platform for conversational commerce so clients like Transnasional could own customer data, meet Malaysian data residency requirements, and move ticket sales off… Converted more than 60% of ticket sales to WhatsApp Sales Automation Cloud Storage · Gemini · Gemma Google Cloud May 29, 2026 Google Cloud Software / SaaS United States Google Cloud's demand engine was receiving growing volumes of increasingly complex leads, but lead preparation still depended on manual, batch-based enrichment. That made it difficult to add trusted buyer, account, and… 30x faster lead processing Sales Automation BigQuery · Gemini · Vertex AI Google Cloud Modified · Oct 9, 2026 Raylu Financial Services United States Founded in 2022, Raylu is building the AI origination engine for private markets, replacing static tools and manual research with an always-on system designed for the speed of modern investing. Scaled infrastructure as Raylu grew from three to 30 employees Sales Automation Cloud SQL · Gemini platform · Google Cloud Secret Manager