~/talk

Leveraging Internal Knowledge: Building AiKA at Spotify

links:none on file
links:none on file
slides:none on file

Spotify builds AiKA, a RAG-based internal knowledge platform using embeddings, a vector database, multiple LLM providers, a custom inference and confidence-scoring model, and OpenTelemetry for observability. It ingests docs, Slack, code and org data, offers Backstage, Slack and Python clients, plus YAML-configurable Slack “goalie” bots. Adoption hits 70% tried, 1,000+ daily active users, 25% weekly; 86% of developers use it, the goalie bot runs 100+ support channels and answers ~30% of seen questions, saving thousands of hours; reranking boosts retrieval ~10–15%.

AI-written summary · about

  1. 0:00Introduction and challenges
  2. 3:10Understanding RAG
  3. 3:59Building the platform
  4. 6:12Aika core principles
  5. 7:35Meet Aika
  6. 8:15Aika capabilities
  7. 9:00Architecture and scaling
  8. 14:07Optimizing knowledge
  9. 17:53Aika Goalie Bot
  10. 20:47Learnings and future path
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.