TECHNIQUE

Basic RAG

Retrieval & Grounding

5APPLICATIONS
10OBSERVED OPERATORS
01

State of Practice

CROSS-VALIDATED — 6 OPERATORS

Basic RAG is deployed as a grounded retrieval layer over enterprise/domain corpora, with operators increasingly adding query scoping, hybrid retrieval, reranking, post-processing, and evaluation around the core retrieve-then-generate pattern.

Observed Practices

Use retrieval to inject domain/source context into LLM answers or query handling, rather than relying on the model alone.

6 of 6 operators with quoted Basic RAG evidence
AgodaDropboxGrabLinkedInRipplingUber

Back RAG with embeddings, vector stores, or vector databases for semantic retrieval.

3 of 6 operators with quoted Basic RAG evidence
AgodaLinkedInUber

Connect RAG to enterprise or product-specific knowledge sources such as wikis, docs, policies, job postings, handbooks, incident records, and root-cause analyses.

5 of 6 operators with quoted Basic RAG evidence
AgodaGrabLinkedInRipplingUber

Add query understanding, query optimization, or domain/source scoping before retrieval to improve relevance.

3 of 6 operators with quoted Basic RAG evidence
LinkedInRipplingUber

Post-process, rerank, or restructure retrieved context before generation.

4 of 6 operators with quoted Basic RAG evidence
DropboxLinkedInRipplingUber

Expose grounded answers inside operational interfaces where users already work, especially Slack, chat, browser, mobile, or search experiences.

4 of 6 operators with quoted Basic RAG evidence
GrabLinkedInRipplingUber

Evaluate grounded outputs for factuality, citation support, or production quality after deployment.

3 of 6 operators with quoted Basic RAG evidence
AgodaDropboxRippling

Where Operators Converge

Across the quoted deployments, Basic RAG is used to ground LLM behavior in operator-controlled domain data or retrieved source context.

The observed deployments treat RAG as an application pipeline component, not as a standalone model: retrieval is paired with prompt construction, answer generation, search/ranking, agents, or workflow execution.

Where Operators Diverge

Retrieval stack depth differs materially across operators.

APPROACH 01

Basic vector-database or embedding-backed retrieval is the explicit RAG store/retriever.

AgodaLinkedInUber

APPROACH 02

Hybrid or filtered retrieval combines vector search with BM25 or source/document narrowing.

Uber

APPROACH 03

Rerankers or explicit ranking stages reduce or order retrieved context before downstream use.

DropboxLinkedInRippling

RAG is deployed in different product surfaces and operating workflows.

APPROACH 01

Internal no-code app builder with Knowledge Vault lookups and user-provided knowledge sources.

Grab

APPROACH 02

Search/query engine that uses RAG context and embeddings to interpret natural-language job-search intent.

LinkedIn

APPROACH 03

Operational support or security workflows that generate triage, summaries, verdicts, or Slack answers from retrieved context.

AgodaUber

APPROACH 04

Multi-agent architecture where dedicated RAG agents retrieve unstructured sources under a supervisor agent.

Rippling

Operators differ in how much explicit human or automated quality control surrounds RAG outputs.

APPROACH 01

Automated regression, staging, production sampling, judge-model, and manual spot-check evaluation around the RAG pipeline.

Dropbox

APPROACH 02

Human reviewer validates final generated incident reports before publishing, and incomplete-context cases are escalated for human review.

Agoda

APPROACH 03

Tracing, layered evals, and production monitoring are part of the production agent/RAG system.

Rippling

Watch Items

Hallucination, misinformation, and factual-support failures remain explicit concerns even when retrieval is present.

Ambiguous or underspecified queries force extra query optimization, source identification, intent classification, or human escalation.

Raw semantic retrieval is often not enough; operators report needing ranking, reranking, BM25, document narrowing, or context post-processing to improve relevance.

02

Implementation Menu

CURATED DEFAULTS
NameKindMaturity
pgvectorlibrarycommodity
Qdrantserviceestablished
LlamaIndexlibraryestablished
03

Observed in Production

5 APPS