customer_support · saas · workflow
GoDaddy's Lighthouse platform uses LLMs to analyze 100,000+ daily customer service transcripts and surface issues in hours instead of weeks
GoDaddy processes up to 100,000 English-language customer service transcripts daily, but manual review by supervisors and analysts could not scale to extract company-wide intelligence or detect emerging issues quickly enough to influence daily operations.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Customer interactions transcribed
Recorded customer interactions are converted into transcripts that serve as the input data source.
Tools used
Lighthouselarge language models (LLMs)Claude v2GoCaaSOpenSearchAWS LambdaS3Amazon QuickSight
Outcome
Lighthouse processes the full daily volume of 100,000+ transcripts in approximately 80 minutes and surfaces emerging issues in hours instead of weeks, enabling GoDaddy to catch and resolve problems before they escalate into significant service disruptions.
What failed first
Manual review and sampling approaches failed to surface systemic issues, and early attempts at automated analysis using ad hoc prompts produced inconsistent results across similar conversations.
Results
Time savedapproximately 80 minutes
Volume100,000+
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
anomaly detectiondata extractionsentiment analysissummarizationcall recordingchat transcriptbuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwarecycle time reductionresolution time reductionthroughput increasetechnical build writeupcall center aicustomer supportquality assuranceextract classify routemonitor detect alert