back_office_ops · saas · workflow
How Shortwave built an AI email executive assistant using RAG
Shortwave's attempts to turn users' email history into an actionable knowledge base using traditional search infrastructure were underwhelming, and the team wanted to unlock the full potential of LLMs to change how users interact with their inbox.
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 · User query received
When a user asks a question, the query is immediately passed to an LLM.
Tools used
GPT-4InstructorPineconeMS Marco MiniLMElasticSearch
Outcome
Shortwave's AI assistant answers almost all questions within 3-5 seconds end-to-end across multiple LLM calls, vector DB lookups, and ML model inference steps.
What failed first
Traditional search infrastructure fell short for email knowledge retrieval, and multi-stage LLM call chain architectures proved impractical because they introduced data loss and errors at each stage, leading to low-quality responses.
Results
Time saved3-5 seconds
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes.
content generationenterprise searchknowledge searchragsummarizationemailknowledge basebuilder submittedmetric backedproduction runtime claimedtools describedworkflow describedsoftwareresponse time reductiontechnical build writeupback office opsagentic task executionrag answering