back_office_ops · saas · workflow
Deedy Das (Glean) on enterprise search architecture, the employee portal evolution, and why simple LLM-drop-in fails
Employees at most companies cannot efficiently find internal documents and knowledge the way Google employees can with internal tools like MoMA — knowledge is scattered across 10–100 SaaS apps with no unified retrieval layer, a gap that worsened with remote work.
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 · SaaS data indexing via APIs
Glean uses robust SaaS APIs to index all documents and permissions from the apps employees use.
Tools used
elasticLLMs
Outcome
Glean became a unicorn with customers including Databricks, Canva, Confluent, Duolingo, and Samsara, with users reporting they cannot go back to a working life without internal search.
What failed first
Earlier enterprise search attempts were on-prem and lacked modern SaaS API integrations, and more recent startups that simply drop in LLMs and embeddings still fail to produce quality results without rigorous ranking and tuning work.
Results
Volume15%
Running since2019
Grounding & classification
Source type: generic use case
14 fields verified against source quotes, 2 dropped as unverifiable.
enterprise searchknowledge searchpersonalizationragknowledge basenamed customerproduction runtime claimedtools describedworkflow describedsoftwareemployee productivitygeneric use caseback office opsrag answering