back_office_ops · saas · workflow
How Qualtrics built Socrates: An AI platform powered by Amazon SageMaker and Amazon Bedrock
Qualtrics needed an enterprise-level ML platform to enable its researchers, scientists, engineers, and knowledge workers to efficiently build, test, and deliver AI-powered capabilities across the XM product suite.
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 · Data sourcing and exploration
Knowledge workers source, explore, and analyze Qualtrics data using Socrates's ML workbenches and AI Data Infrastructure.
Tools used
Amazon SageMakerAmazon BedrockSageMaker InferenceJupyterLabLangGraph PlatformOpenAI GPTMeta Llama 3
Outcome
The Socrates platform enables the full ML lifecycle at Qualtrics using Amazon SageMaker and Amazon Bedrock, has reduced AI inference costs multiple folds for some use cases, and has boosted performance and accessibility of AI-driven features within the XM suite.
Results
Time savedup to 40%
Volume50%
Cost replacedreduced AI inference costs multiple folds for some of our use cases
Running sinceEarly 2020
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
agentic workflowcontent generationsentiment analysisknowledge basebuilder submittedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwarecost reductionemployee productivitythroughput increasetime savedtechnical build writeupback office opsagentic task execution