PromptKB

A citation is a starting point, not a verdict

Turn documents into a reviewable brief.

Bring a question and your sources. Take a prompt to your model, bring back its answer, then inspect each claim beside the exact words it cites. Export only the claims you approve—with unresolved questions and an honest review appendix.

Local-only · no account · no model calls · no content upload · no autosave

See a real-source Python migration brief: two pinned documentation versions, an actual local runtime probe, and a rejected claim that still passes quote matching. These are agent-authored editorial judgments, not a model benchmark.

1. Set the question and collect sources

Paste text you have permission to use. The tool does not fetch URLs, parse PDFs, browse the web or establish provenance. Keep version/date/page information in each source’s locator. Compare historical versions as historical versions, not automatically current facts.

Opening asks before replacing work. No saved approval is restored. This format is separate from Test Bench projects and model answers.

Be specific about audience, versions and what evidence would answer the question.

Up to 12 sources, 60,000 characters each. IDs stay attached to their source when another source is removed; they are not silently renumbered. Source text and metadata edits clear every current claim decision. Whitespace is significant in quote matching; native textarea editing may normalize pasted line endings.

Inspect the exact prompt before sharing
The prompt includes your question, every source title/locator and full source text. It excludes the brief title, rights fields, notes and current answer. Your external model service has its own privacy and costs. The tool does not record or authenticate a model run.
2. Bring back an answer, check its citations
Answer format and check limits
{
  "claims": [{
    "id": "C1",
    "text": "One specific claim supported by these sources.",
    "citations": [{"source": "S1", "quote": "Exact contiguous text from source S1."}]
  }],
  "questions": ["What evidence is still needed?"]
}
Up to 40 claims, 8 citations per claim and 30 questions. Missing source IDs or nonmatching quotes block that claim, not the whole answer. A claim with no citations cannot be approved. A malformed response blocks preview. Duplicate JSON keys follow native parsing (last value wins); inspect the parsed preview. Matching does not judge entailment, completeness, source quality, conflicting versions or truth.
Nothing saved or sent. Add sources, then preview an answer.
3. Keep the reasoning, share a scoped brief
Notes appear in both work files and briefs. Editing notes clears current approvals so the exported interpretation is reviewed again. Use them to explain disagreements; decisions alone are not a review record.
HTML is a read-only, script-free offline document; Markdown is editable reading material. Both contain approved claims with quotes and source locators, unresolved questions, excluded claim text/status, your notes and all source metadata and rights fields. They do not include full source bodies or the raw answer. Inspect the review appendix and expandable rights before sharing. They are not re-importable work files or proof of verified facts.
Work JSON retains all source bodies, metadata, rights, the raw answer even if invalid, question, title and notes, but no claim decisions. Reopening requires a fresh preview and individual approval. Keep the reviewed brief separately to retain decisions. Files are unsigned, unencrypted and unredacted; no source authenticity or execution identity is verified. Reloading loses this tab’s work unless you download it. Clear removes tab contents, not previously shared/downloaded files or clipboard text.
How to review a claim
  1. Check the source identity and version. A perfect quote from the wrong version can still mislead.
  2. Read the cited words and their surrounding source. Multiple exact occurrences are disclosed; the line range is the first match in your pasted text.
  3. Ask whether the quotes support every part of the claim. A source saying “does not write” cannot support “can write,” even though its quote matches.
  4. Reject unsupported conclusions. Keep missing evidence and conflicts as questions rather than making the brief appear complete.
  5. Approve claims individually, then read the exported brief as a recipient. Recheck included private text and attribution before sharing.
Source Brief is a separate task workspace, not a quality score, citation crawler, formal research system or Test Bench import. Its limits and review policy are provisional product choices. Privacy details.