Your LLM gave you an answer. Should your application trust it?

A developer has released BOOTH, an open-source Python checkpoint layer that verifies LLM outputs against retrieved evidence before they are passed downstream. The library's check_with_evidence() function compares a model's answer to documents already retrieved by a RAG pipeline, flagging unsupported claims such as a return window stated as 90 days when the evidence says 45. BOOTH is provider-agnostic, has zero runtime dependencies, and has surpassed 2,000 PyPI downloads with 300+ tests under an MIT license.

Your LLM gave you an answer. Should your application trust it? I built BOOTH , a lightweight checkpoint layer for LLM outputs. The idea is simple: don't automatically pass every model response downstream. Check it first. For example: Evidence: Returns are allowed within 45 days. LLM: Returns are allowed within 90 days. The answer sounds confident. It's also unsupported by the evidence. BOOTH's check with evidence lets you check an LLM response against evidence your RAG pipeline has already retrieved. result = booth.check with evidence answer=llm answer, evidence=retrieved docs, compare fn=your comparison function, No need to replace your existing RAG pipeline or commit to a particular LLM provider. Zero runtime dependencies. Provider-agnostic. Small API. pip install boothpy GitHub: https://github.com/Vedantgitbot/booth https://github.com/Vedantgitbot/booth How are you currently deciding whether an LLM output is safe to pass downstream? Beta · 2K+ PyPI downloads · 300+ tests · CI passing · MIT · Python 3.9+