Use Case Intelligence RSS Search use cases Search
Anthropic Software / SaaS Europe

Supermetrics

Real-time Analytics

Marketers and agencies had no shortage of dashboards, but still had to manually export, reconcile, and report data from multiple ad platforms, making campaign analysis slow and too risky for AI systems that hallucinate.

Read the original story Explore all use cases
10-hour reports done in 20 minutes
250% average month-over-month growth in active users
zero hallucinations in that agency's multi-week validation of live marketing data

Reported impact

Business outcome

Supermetrics' Claude connector averaged 250 percent month-over-month growth in active users, cut one agency's reporting job from 10 hours to 20 minutes, validated zero hallucinations in multi-week testing, and gave customers faster daily optimization loops instead of monthly reporting scrambles.

  • Customer Experience
  • Productivity Improvement
  • Revenue Growth

Solution

Supermetrics built a Claude-native marketing workflow on top of its own normalized data infrastructure. Through its MCP server and Claude connector, marketers ask questions in Claude Cowork, which calls Supermetrics tools to pull live campaign data from hundreds of ad and analytics sources, attach source and timestamp details to every figure, render charts inline, and recommend next actions. With approval, the same conversation can create or edit campaigns across Google Ads, Meta, Microsoft Advertising, TikTok, LinkedIn, and Snapchat. Supermetrics accesses Claude Sonnet 5 and Opus 5 through Google Cloud's Agent Platform and keeps zero-retention agreements with its model and cloud providers. Internally, the company also uses Claude Code against its monolith and incident data, letting engineering rely on the same platform it sells to customers.

Data flow

A marketer asks Claude a question, Supermetrics fetches normalized data from connected ad and analytics platforms, Claude reasons over the live figures and inline charts, and, with human approval, the workflow can push edits back out to campaign systems in the same conversation.

Solution architecture

5 components · 3 layers
  1. Compute
    • Claude Code Supports Supermetrics engineers as they maintain the monolith and investigate incidents.
    • Sonnet 5 Handles many of the data-driven marketing tasks exposed through the connector.
    • Opus 5 Runs the more demanding reasoning tasks inside the Claude-based marketing workflow.
  2. Serving
    • Claude Cowork Hosts the conversational interface marketers use to ask questions, review charts, and approve campaign changes.
  3. Uncategorized
    • Google Cloud's Agent Platform Provides access to Claude Sonnet 5 and Opus 5 for Supermetrics' customer-facing workflow.

Architecture clues

  • Campaign creation and edits require human approval before anything goes live.
  • Supermetrics uses the same Claude stack internally for code, reporting, and incident response.
  • The connector serves normalized data from hundreds of marketing sources with a source and timestamp attached to every figure.

Evidence from the source

Grew active users of its Claude connector 250% month over month on average since its February launch
I have not found a single hallucination or incorrect data point.
Runs campaign creation and edits across Google Ads, Meta, Microsoft Advertising, TikTok, Linkedin and Snapchat with human approval before anything goes live
Turned one agency customer's 10-hour client reports into 20-minute tasks through the connector
Transparency Evidence & methodology 100/100 reference value · 79% 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
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • 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 provenance0/10
    The publication date has no documented provenance.
  • 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. Anthropic

    Supermetrics customer story

    First-party
    https://claude.com/customers/supermetrics
    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

  • First archived Sep 23, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    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 Archived · Oct 16, 2026 Alta Software / SaaS United States Alta needed a transactable Google Cloud Marketplace path for its AI and technology spend management platform without pulling its product team off core forecasting work, while also helping finance and IT leaders… Saved 125 engineering and 60 project management hours IT Operations AutomationReal-time Analytics Cloud Pub/Sub · Cloud Run · Cloud SQL 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 Snowflake Modified · Oct 9, 2026 DataHub Software / SaaS Palo Alto, California A fragmented, self-managed observability stack forced engineers to jump between tools, left monitoring on the same infrastructure it monitored, and drove high AWS cost and incident blind spots. $100K+ annual AWS savings IT Operations AutomationReal-time Analytics OPAL · Observe agent · Observe by Snowflake