~/talk

Dan Fergusson, Glean & John Purcell, DoiT International | Google Cloud Next 2023

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

Glean builds a permissions-aware workplace search and knowledge graph running in single-tenant Google Cloud projects, then layers Vertex AI and PaLM models to add generative answers; initial compute ran ~30–40% of product cost and optimizations plus Kubernetes bring costs down. DoiT provides cloud architecture, cost engineering and GCP marketplace enablement; a phased approach—search first, then GenAI—scales to hundreds of millions of documents and ships production GenAI features after a concentrated engineering sprint.

AI-written summary · about

  1. 0:00Introduction and Do it
  2. 2:13Glean AI workplace search
  3. 5:47Partnership and cloud strategy
  4. 8:04Scaling and AI integration
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 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
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
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.