What it scores
Every AI engine splits your page into passages and scores each one alone. This checklist is the pre-publish version of that test, eight properties that decide whether a passage survives chunking, retrieval and reranking. Each maps to a specific failure mode: unnamed subjects and dangling pronouns cause vector drift; buried answers lose the reranker; renamed categories cause lexical mismatch.
Score a single article honestly. The lowest items are your biggest gaps.
How to use it
- Score a page against the eight pre-publish checks.
- Read the readiness score and ranked gaps.
- Fix the gaps before you publish.
Frequently asked questions
What is on the retrieval-readiness checklist?
Eight pre-publish checks for surviving chunking and reranking: self-contained answers, question headings, monosemantic passages, plain-HTML facts, schema, named sources, freshness and internal linking. It scores a page and ranks the gaps before you ship.
When should I run this checklist?
Before publishing, and again after major edits. Fixing retrieval gaps pre-publish is far cheaper than diagnosing why a live page never gets cited, most misses come from a handful of these eight items.
Is the Retrieval-Readiness Checklist free to use?
Yes. The Retrieval-Readiness Checklist is completely free, with no sign-up, no usage limits and no watermark on the output.
Is my data private?
Yes. The Retrieval-Readiness Checklist runs entirely in your browser. Nothing you paste or enter is uploaded, stored or sent to any server.
Related tools and reading
Keep going with the playbooks and tools behind this one.