Paste an AI response.
We cite every line.

1. 1

   Paste the response

   Drop the full AI output into the manuscript editor. Original line breaks are preserved — each line becomes its own inspection unit.

2. 2

   Extract claims

   Substantive factual lines are identified and cited. Filler and transitions are skipped. Long lines are split into individual sentences.

3. 3

   Search & verify

   Each claim is searched across Wikipedia, OpenAlex, and DuckDuckGo in parallel, then Google Custom Search — with nearby lines as context. Serper and SerpAPI run early or as fallbacks depending on your toggles. Sources are deduplicated, scored, and an AI or heuristic engine assigns a verdict.

4. 4

   Review the dossier

   Every line appears in a folio card with its verdict, confidence, sources, and stance. Filter, copy footnotes, or save for later.

• ¶

  Line-by-line inspection

  Every non-empty line is examined in original order. Nothing is reduced to a summary or digest.

• ✎

  Manuscript editor

  Ruled-paper textarea with an italic line-number gutter, live line and character counters, an optional title field, a one-click sample response, and Ctrl/Cmd+Enter to run.

• ◎

  Smart claim extraction

  Strips markdown formatting, classifies each line as fact or context, and splits long factual lines into sentences so every claim is searched independently.

• ⌕

  Multi-provider search

  Wikipedia, OpenAlex, DuckDuckGo, Google Custom Search, Google News RSS, Serper, and SerpAPI — plus inline URLs from the pasted text. Trusted domains are boosted, low-quality sources are blocked, and results are cached.

• ≡

  Context-aware search

  Nearby lines (±3) are passed as document context when searching and fact-checking, so pronouns and references resolve against the full response.

• 🔗

  Inline URL citation

  URLs already present in the pasted text are extracted and cited directly as "Cited in the original line" — no search required.

• ✓

  Dual fact-check engines

  AI verification through any OpenAI-compatible endpoint — set your own base URL and model — with a heuristic keyword matcher as automatic fallback. Only the top 4 sources are sent to the model; each verdict shows its method.

• ⊕

  Source stance detection

  Every source is labeled as supporting, contradicting, or neutral — with a relevance overlap score and provider attribution.

• ▤

  Live progress streaming

  Claims are processed in parallel with a real-time progress bar. Results stream into the dossier as each line completes.

• ⊞

  Filterable dossier

  Click a tally pill to show only Supported, Contradicted, Unverifiable, Sourced, or Unmatched lines. Copy footnotes exports exactly what is on screen, so the filter doubles as a citation picker.

• ⊟

  Analysis history

  Every inspection is saved with the original text, extracted claims, and found sources. Browse up to 80 past analyses.

• ↻

  Re-run on edited text

  Open a saved dossier, expand the AI Response panel, edit the text inline, and re-run the full pipeline — saved as a new dossier while the original stays in history.

• ⚙

  Provider status panel

  Live state for Wikipedia, OpenAlex, DuckDuckGo, Serper, SerpAPI, and the AI fact-check engine, with config hints and the active model. Recheck runs a real probe against your LLM. Serper offers before-DuckDuckGo, before-SerpAPI, and fallback toggles; SerpAPI offers before-DuckDuckGo and fallback — all persisted across sessions.

• ⊛

  Fact-check summary

  Aggregate roll-up verdict in plain English: well supported, partially supported, unsupported, contradicted, mixed results, or nothing to verify — with a per-verdict breakdown and a count of hidden filler lines.

• ⏱

  Rate limiting

  Per-IP quotas on every write endpoint — 15 analyses, 300 citations, 30 setting changes, and 6 live LLM probes per hour — with a Retry-After hint when you hit the ceiling.

• 🔒

  Hardened by default

  CSRF tokens on every POST, a strict Content-Security-Policy, HSTS on HTTPS, optional admin-token gating on the settings endpoints, and an optional token on the health check.

• Wikipedia Free encyclopedia API
• OpenAlex Scholarly works API
• DuckDuckGo Privacy-focused web search
• Google Custom Search API + News RSS
• Serper Low-cost Google SERP, three ordering toggles
• SerpAPI Early or fallback, ordered against Serper
• Inline URLs Cited from the pasted text

• POST /api/analyze.php Create an analysis and extract claims from pasted text
• POST /api/cite.php Search sources and fact-check a single claim
• GET /api/get.php?id= Fetch a saved analysis with all claims and sources
• GET /api/search_status.php Provider diagnostics with optional live LLM probe
• POST /api/serper_settings.php Persist Serper ordering: before DuckDuckGo, before SerpAPI, fallback
• POST /api/serpapi_settings.php Persist SerpAPI ordering: before DuckDuckGo, fallback
• GET /health.php Server health — PHP, database, schema, and data-directory writability

Fact-check verdicts

Source status