back_office_ops · saas · workflow
How Amazon Bedrock Custom Model Import streamlined LLM deployment for Salesforce
Salesforce's AI platform team faced significant operational overhead deploying fine-tuned LLMs—spending months on instance selection, serving engine configuration, and GPU capacity reservations that were expensive, time-consuming, and difficult to maintain across frequent model releases.
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 · CI/CD saves model artifacts to S3
The CI/CD process saves model artifacts to an Amazon S3 model store bucket.
Tools used
Amazon Bedrock Custom Model ImportAmazon SageMaker InferenceAmazon S3AWS Identity and Access ManagementAmazon Bedrock Knowledge BasesAmazon Bedrock GuardrailsAmazon Bedrock AgentsLlamaQwenMistralvLLMTensorRT-LLMAmazon API GatewayAWS LambdaAgentforce
Outcome
Salesforce achieved a 30% reduction in model deployment time and up to 40% cost savings by adopting Amazon Bedrock Custom Model Import, while maintaining backward-compatibility with existing applications through a hybrid architecture using SageMaker proxy containers alongside Amazon Bedrock serverless inference.
Results
Time saved30%
Volume44%
Cost replacedup to 40%
Grounding & classification
Source type: technical build writeup
35 fields verified against source quotes.
agentic workflowbuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedsoftwarecost reductioncycle time reductionemployee productivitytechnical build writeupback office ops