sales_ops · saas · workflow

MSX Sales Copilot: real-time content recommendation for Microsoft sellers using bi-encoder and cross-encoder LLM architecture

Microsoft sellers needed to find and share relevant technical documentation with customers in real time during calls, but were limited to an external filter-based search on the Seismic website rather than a tool embedded directly in their CRM interface.

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 · Seller query entered
A seller asks a question to the Copilot chatbot in natural language about topics covered by the skills.
Tools used
Semantic KernelAzure Machine LearningSeismic
Outcome

The new real-time content recommendation system was deployed into the production MSX Copilot and described as a tremendous improvement by the seller community, receiving a daily task relevance score of 4 out of 5 and a document relevancy rating of 3.7 out of 5 in seller satisfaction surveys.

What failed first

The previous external Seismic filter-based search was sub-optimal and not embedded in the MSX CRM interface sellers used daily.

Results
Volume4 out of 5
Running sinceJuly 2023
Source

https://arxiv.org/html/2401.04732v1

How we source this →

Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes, 2 dropped as unverifiable.
enterprise searchknowledge searchragrecommendation systemknowledge basehuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementemployee productivityresponse time reductiontechnical build writeupsales opsrag answering