Travel workflows and seller-intelligence scenarios test the same pipeline against different contexts.
Grounded retrieval / guardrails / release logic
RAG Pipeline with Guardrails
The vector baseline for the enterprise knowledge layer: grounded answers, safety checks, benchmark traces, and release gates connected in one production-minded system. A separate implemented GraphRAG layer now tests when relationship traversal earns its extra complexity.
Local executionCommitted corpus and 24-case evaluation
- Domains
- 2 corpora
- Eval cases
- 24
- Verdict
- PASS
- Guardrails
- 4 classes
- Decision
- Connect citations, confidence, input/output guardrails, and evaluation traces in one pipeline.
- Why
- Retrieval accuracy alone cannot support a release decision or explain a failure.
- Result
- A 24-case, dual-domain baseline with four guardrail classes and an explicit PASS verdict.
Quick readRelease discipline
Retrieval quality alone does not make a feature shippable.
A grounded answer can still be risky, misleading, or hard to defend. The useful product question is whether the system can produce grounded answers, flag unsafe behavior, and explain why a release should move forward or stop.
Prompt injection, PII, toxicity, and groundedness are checked around the answer flow.
Citations, confidence, and verdict reasons make the answer defensible.
Policy thresholds turn raw eval output into a launch-review decision.
SystemFlow
From a question to a supported answer.
Corpus
Domain content
Travel and seller workflow knowledge bases.
Retrieval
Grounding
Relevant context is selected before synthesis.
Guardrails
Risk checks
Inputs and outputs are checked before release.
Eval
Decision
Reports and gates produce PASS, WARN, or BLOCK.
Test reportsLocal execution
Try retrieval, citations, and abstention.
Ask a question of the sample travel or seller corpus. The browser ranks passages, extracts an answer, and shows its citations. An unsupported question returns an abstention. This lab runs locally without a model provider.