Hybrid search for RAG
Evaluate with evidence
Measure hybrid search with denominators, slices, and gates chosen before seeing results on the technical support search assistant.
1Learn the idea
Read
Metrics
Track for hybrid search: recall@5, MRR, p95 latency, ID-slice recall, citation support. Report fractions like 36/40, not vague quality adjectives. Segment by language, plan tier, document length, or other slices that matter for the technical support search assistant.
Read
Protocol
Freeze inputs and neighboring versions while evaluating hybrid search. Change one control. Pair results case by case on the technical support search assistant. Define hard gates (severe errors, privacy, latency) before the bake-off. Use deterministic checks where possible; humans for nuance; model judges only with calibration against gold.
Numeric reminder for hybrid search: On 50 tickets, pure vector recall@5=0.72, pure BM25=0.64, RRF hybrid=0.86—report denominators.
Read
Make it operational
Resist adding a twelfth metric before the first three for hybrid search on the technical support search assistant have owners. This workload improves faster when a small scorecard is trusted than when a warehouse of unused plots exists.
Also pin one numeric memory from this hybrid search chapter: On 50 tickets, pure vector recall@5=0.72, pure BM25=0.64, RRF hybrid=0.86—report denominators. That number is not decoration; it is a template for how claims about hybrid search on the technical support search assistant should look in design docs. Scoped specifically to hybrid search / technical support search assistant / evaluation.
Read
Common mix-ups
People confuse hybrid search with neighboring buzzwords when debugging the technical support search assistant. Before changing prompts, ask whether the broken stage was evidence gathering, the hybrid search judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried hybrid search and it failed”) that blocks the next team on the technical support search assistant. Scoped specifically to hybrid search / technical support search assistant / evaluation.
Read
Rehearsal (hybrid-search-rag/evaluation)
Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.
Read
Rehearsal (hybrid-search-rag/evaluation)
Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.
Read
Rehearsal (hybrid-search-rag/evaluation)
Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.
Read
Rehearsal (hybrid-search-rag/evaluation)
Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.
Go deeper
Before you start
Why this matters
A demo of the technical support search assistant looks great on three hand-picked examples of hybrid search. What does that demo refuse to tell you?
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.