Documentation
ISNAD grades who handled a claim in an AI pipeline (the transmitters and the chain) and can export each verdict as an audit record you can sign and verify.
Install
Section titled “Install”pip install isnad30-second example
Section titled “30-second example”from isnad import Registry, gradefrom isnad.types import NarratorGrade
reg = Registry()reg.register("openstax", "physics", grade=NarratorGrade.RELIABLE)reg.register("pdf-scraper", "physics", grade=NarratorGrade.UNGRADED)reg.register("ingest-model", "physics", grade=NarratorGrade.ACCEPTABLE)
verdict = grade("p = mv", ["openstax", "pdf-scraper", "ingest-model"], reg, domain="physics")print(verdict.why)# claim 'p = mv' → chain DAIF (weakest: pdf-scraper, ungraded)A new pipeline starts with every narrator UNGRADED, so nothing serves; seed grades with Registry.seed().
Read next
Section titled “Read next”- Quickstart — add ISNAD to a LangChain agent in five minutes.
- Concepts — the isnād–rijāl model.
- Compliance — the evidence ISNAD produces for AI governance frameworks.
- Architecture — the module map.
- Critics — content critics and their measured recall.
- ISNAD-Bench results