Dimension Labs

Use case

Customer, guest and fan experience analysis

Upload your reviews, surveys, tickets and calls. Find which experience issue is really moving your score, and which is just loud.

Start now › See pricing ›

Ask Which experience issue is actually costing us stars?

We work with enterprises such as NBA, Travelers, Mars and Concentrix.

[01] The problem

They told you what's wrong. Your dashboard ranked it by volume.

Every tool you own ranks by volume. Marriott's guests named front desk check-in constantly. It ranked #2 and moved star rating almost none.

Right now

01The loudest complaint gets fixed first
02Sentiment says people are unhappy, never what it costs you
03Comparing locations stalls on inconsistent language
04A score drops and the answer takes four weeks
05Teams act on the average instead of the real driver

Knowing what they said is easy. Knowing which part actually moves your score is the job.

[02] EnrichOne record, structured

Language in. Structured data out.

Every record is read in full and written back with dozens of typed Dimensions, the same way every run. Here is what that looks like for this use case.

enrichment · one record

Raw text

We booked a suite for our anniversary and arrived to hair in the sink and a stained carpet. When I asked to move, the manager was dismissive and made us feel like the problem. Then a $39 resort fee we were never told about. We will not be back.

Google review · 1 star · property joined

Dimensions written to the record

Facility & Cleanlinessbroadly dirty
Primary Frictioncleanliness
Staff Interaction Qualitydismissive · named role
Service Recoveryrefused
Fee & Premium Changeundisclosed fee · $39
Price–Value Perceptionpoor
Loyalty Signalwill not return

Each colour links a phrase in the raw text to the Dimensions extracted from it. Hover either side.

[03] The product

3.1 · Read everything

Every record, enriched.

Start with one file. Reviews, surveys, tickets, calls, whatever your customers, guests or fans have already told you. Every record comes back enriched with structured Dimensions: root cause, effort, sentiment, escalation risk.

Start with one CSV or connect every channel you have
Join every conversation to account, agent and outcome data
Build custom Dimensions in plain English
Have the agent build context on your business

dimension labs · blend

3.2 · Prove the cause

Ask why. Get proof.

Ask in plain English. The agent writes the queries, runs the analysis, controls for the things that would confound it, and returns the finding with an effect size and confidence interval. It checks its own work.

Rank issues by causal impact, not complaint volume
Prove which fix would actually move your rating
Put a dollar figure on a specific experience failure
See what separates your best and worst locations

dimension labs · ask

Example finding

Which experience issue is actually costing us stars?

Cleanliness moved one-star risk by 34 points. Front desk, mentioned almost three times as often, moved it by about two.

8,504 public Google reviews · Marriott-family hotels in Orlando

3.3 · Deliver

Ask for the report. Get the report.

Say what you need and the agent builds it: executive summary, causal findings, charts, recommendations. Set it to rerun weekly or monthly on fresh data and it lands in your inbox. Export as HTML, PDF or slides.

Produce the monthly readout without building it
Send a link leadership can open and interrogate
Track whether the fix you shipped moved the metric
Export to PDF, slides or your BI tool

dimension labs · report

The priority list, rearranged by cause

Exhibit from “What your CX tools can’t tell you”. Left: the standard CX-analytics ranking. Right: a DoWhy causal model on 8,504 rated public reviews, holding hotel, tier, language, review length and reviewer fixed. Every effect survives placebo, random-cause and subset tests.

[04] How the platform worksRuns daily

From raw conversations to a proven answer.

Language from every channel and your business data flow into one pipeline that enriches, governs and tests every record, then delivers wherever your team works.

Language · 37 sources

ZendeskIntercomSalesforceLiveChatDriftSlackQualtricsMedalliaSurveyMonkeyQuestionProGenesysAmazon ConnectAvaya Cloud8x8TwilioSMSAdaKore.aiYellow.aiCognigyRasaMicrosoft Bot FrameworkAmazon LexAmazon AlexaOracle Digital AssistantBotcopyCapacityFacebook MessengerKikX (Twitter)OpenAIEmailCall recordingsApp store reviewsGoogle reviewsOpen-ended surveysCommunity forums

Business + world data

SnowflakeDatabricksBigQueryAmazon S3Salesforce CRMCSV + ExcelREST APIRevenueOrdersRenewalsUsage eventsLoyaltyStore + location dataWeatherSeasonalityMarket events

Dimension Labs pipeline · Runs daily

Ingest + normalizeEvery channel and language into one schema

EnrichDozens of Dimensions written onto every record

Map + governValidated for drift, versioned, the same fields every run

Analyze + proveJoined to outcomes and tested for cause

Where it goes

Dimension Labs agentAsk, report, schedule

Your warehouseSnowflake, Databricks, BigQuery

BI toolsTableau, Power BI, Hex

Claude and ChatGPTvia MCP · coming soon

[05] ArtifactsBuilt by the agent