back_office_ops · saas · workflow
Grab enables conversational data discovery with LLMs via HubbleIQ
With over 200,000 tables in their data lake, Grab's data consumers struggled to find the right datasets: Elasticsearch-based search could not handle semantic queries, documentation coverage was only 20% for critical P80 tables, and 51% of users spent multiple days hunting for data via tribal knowledge and Slack.
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 · Data consumer submits query
Data consumers ask contextual data discovery questions in Slack ask channels or on the Hubble UI.
Tools used
HubbleDatahubElasticsearchGPT-4GleanGlean AppsHubbleIQSlack · partner
Outcome
The click-through rate rose from 82% to 94%, P80 table documentation coverage increased by 70 percentage points to ~90%, and 73% of survey respondents found it easy to discover datasets—a 17 percentage point improvement over the previous survey.
What failed first
Elasticsearch in its vanilla form could not perform semantic search, causing users to abandon Hubble searches and fall back to asking colleagues on Slack for dataset help.
Results
Time saved51%
Volumeover 200,000
Grounding & classification
Source type: technical build writeup
42 fields verified against source quotes.
chatbotcontent generationconversational aienterprise searchragknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedlogisticssoftwareaccuracy improvementemployee productivitytime savedtechnical build writeupback office opsai draft human approvalextract classify routerag answering