customer_support · manufacturing · workflow
Impel enhances automotive dealership customer experience with fine-tuned LLMs on Amazon SageMaker
As Impel's Sales AI transaction volumes grew, their third-party LLM provider's per-token pricing became cost-prohibitive, and restrictions on fine-tuning prevented them from leveraging proprietary customer interaction data to improve model quality.
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 inquiry via email or text
Prospective customers contact automotive dealerships through email and text, initiating a customer engagement.
Tools used
Amazon SageMakerMeta LlamaSageMaker LMI containersAmazon SageMaker StudioPyTorchtorchtuneLoRAAWQawscurl
Outcome
By deploying a fine-tuned Meta Llama model on Amazon SageMaker, Impel achieved a 20% improvement in accuracy across core features, with personalized replies rising from 73% to 86%, summarization from 70% to 83%, and follow-up generation from 59% to 92%, alongside cost predictability and greater operational control.
What failed first
Impel's existing third-party LLM provider charged per-token pricing that became unaffordable at scale and did not allow sufficient fine-tuning on Impel's proprietary automotive data.
Results
Volume20%
Cost replacedCost predictability through hosted pricing, mitigating per-token charges
Grounding & classification
Source type: technical build writeup
33 fields verified against source quotes.
content generationconversational aipersonalizationsummarizationchat transcriptemailhuman review describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedautomotiveaccuracy improvementcost reductiontechnical build writeupcustomer supportsales opssales outreachautonomous resolution