Dimension Labs

Use case

Multi-location performance

Compare every hotel, store, club or restaurant on the same Dimensions. Find why one location outperforms another, and which fix would move the rating.

Start now › See pricing ›

Ask Why does one location outperform another?

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

[01] The problem

Two locations, same brand, same training. A full star apart.

Location reports rank sites by score. They can't tell you what the better site does differently, because every location's comments are coded differently, or not at all.

Right now

01Sites are ranked by score, never explained
02Every region codes feedback its own way
03Best practices spread by anecdote
04Regional managers can't compare like with like
05The fix that worked in one site never gets tested in another

The difference between your best and worst location is written down, thousands of times.

[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

Waited 25 minutes in the drive-thru and they still forgot the kids' meals. The shift lead at the window was great about it, but this is the third time at this location.

Google review · 2 stars · store joined

Dimensions written to the record

Service Speed & Wait25 min · drive-thru
Transaction / Visit Typedrive-thru
Order & Service Accuracyitems missing
Staff Interaction Qualitypositive · named role
Service Recoveryattempted
First-Time vs. Repeatrepeat · 3rd incident
Location Referencedthis store

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 export of reviews, surveys and tickets from every location, or connect every channel. Every record comes back with typed Dimensions like location referenced, service speed and wait, staff interaction quality, facility and cleanliness and order accuracy, written the same way every run, then joined to location, region, format, staffing and sales data.

Read every record, not a sample
Join each record to location, region, format, staffing and sales data
Add your own Dimensions in plain English
Backfill years of history in the same run

dimension labs · blend

3.2 · Prove the cause

Ask why. Get proof.

Ask in plain English. The agent writes the queries, controls for what would confound the answer, and ranks each issue by its measured effect on rating, revisit and revenue per location, with an effect size and a confidence interval. Findings that fail the robustness checks are never reported as causal.

Why does one location outperform another
Rank each site's drivers by their effect on rating
Find the operators and practices worth copying
Track whether a fix moved one site's score

dimension labs · ask

Example finding

Why does one location outperform another?

See the Chick-fil-A customer review analysis: 24 Dimensions across public Google Maps reviews, compared location by location.

Published artifact · public reviews

3.3 · Deliver

Ask for the report. Get the report.

Ask for the readout your regional managers needs and the agent builds it: summary, ranked findings, charts and recommendations, each figure checked. Schedule it weekly or monthly on fresh data, or publish it as a live monitor.

Produce the monthly readout without building it
Publish a live monitor leadership can open and question
Track whether the fix you shipped moved the number
Export to PDF, slides or your BI tool

dimension labs · report

[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