customer_support · saas · workflow
A New Bot: Building a Vespa-Powered RAG Slackbot for Community Q&A
Vespa.ai saw Docker pulls soar from 2M to 11M in a few months in late 2023, leading to a flood of questions on their Slack channel that required an automated solution to handle at scale.
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 · Slack message ingested to Vespa
Every message posted in the Slack channel is fed into a Vespa app, with users' consent.
Tools used
VespaOpenAI · partnerSlack SDK for JavaKotlinGradleTerraformSpaceLiftGCP
Outcome
The team built and deployed a working Slackbot powered by Vespa and OpenAI that continuously indexes community messages and answers questions based on past conversations and documentation, with accuracy expected to improve as more interactions are processed.
Results
Time savedcapabilities and accuracy will improve
Volumesoaring from 2M to 11M
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
chatbotknowledge searchragsummarizationchat transcriptknowledge basenamed customerproduction runtime claimedtools describedworkflow describedsoftwarethroughput increasetechnical build writeupcustomer supportrag answering