Skip to content
The Register

17 extractors

AI

Models, training data and RAG inputs.

17 extractors

012marketing / ai

AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini

Ask AI assistants the questions your customers ask. Track brand mentions and competitor rank per answer; Perplexity runs include provider citations, while other modes label URLs found in the answer. Bring your own API keys.

provider
model
sampleIndex
+9 more
12 fields48 runs
014ai / developer tools

Docs to Answers Pack — Citable AI-Ready Chunks

Turn a documentation site into a corpus an AI can answer FROM and CITE. Splits on headings rather than character counts, attaches a heading path and deep link to every chunk, drops boilerplate that repeats across pages, and hashes each chunk so you re-embed only what changed.

chunkId
text
headingPath
+11 more
14 fields47 runs
017developer tools / seo tools

Wayback Machine Scraper — Website History & Snapshots

Extract every Wayback Machine (archive.org) snapshot of any URL, domain or subdomain — capture date, HTTP status, MIME type, content digest, byte size and direct snapshot links. Up to 50,000 rows, many URLs per run, $0.50 per 1,000 rows. No API key.

inputUrl
timestamp
capturedAt
+6 more
9 fields46 runs
033developer tools / ai

PDF Tables Extractor — Tables Out of Any PDF

Pull real tables out of PDFs as rows you can use, with a confidence score on every table. Outputs one item per row for spreadsheets, or Markdown and CSV for docs and LLM prompts. Says plainly when a PDF is a scan with no text layer instead of returning silent nonsense.

sourceUrl
page
tableIndex
+17 more
20 fields36 runs
069ai / jobs

Jev Job Posting Taxonomy — Classify Job Listings

Normalize supplied job postings into function, seniority, and remote-policy fields with TypeSafe Jev.

index
sourceId
description
+5 more
8 fields22 runs
070ai / business

Jev Review Intelligence — Classify Customer Reviews

Classify supplied product reviews into typed topic, severity, and actionability fields using your TypeSafe Jev key.

index
sourceId
review
+5 more
8 fields22 runs
072developer tools / ai

PDF Layout-Preserved Text — Tables & Forms

Extracts PDF text with column alignment kept intact — between plain text (scrambles forms) and structured tables (not every layout has one). Verified on IRS Form 1040: plain extraction garbled two columns together; this keeps them separate. Flags scanned pages instead of nonsense.

sourceUrl
page
chunkIndex
+6 more
9 fields22 runs
077ai / marketing

Jev AI Answer Visibility Enricher — Brand Tracking

Add typed brand stance, recommendation, and citation-presence judgments to AI-answer datasets using your TypeSafe Jev key.

index
sourceId
prompt
+7 more
10 fields21 runs
078ai / ecommerce

Jev Listing Policy-Risk Monitor — Marketplace Rules

Flag unsupported or policy-risk claims in supplied listing text using a buyer-defined policy and TypeSafe Jev.

index
sourceId
listing
+5 more
8 fields21 runs
079ai / business

Jev Research Evidence Sorter — Rank Source Evidence

Rank supplied research snippets by relevance and evidence type using TypeSafe Jev while preserving source URLs.

index
sourceId
url
+5 more
8 fields21 runs
081ai / marketing

Jev Ad-to-Landing Alignment Monitor — Ad Copy Match

Review supplied ad and landing-page context for message alignment and claim risk using a TypeSafe Jev key. It never reads ad accounts or changes campaigns.

state
questions
index
+9 more
12 fields19 runs
082ai / seo tools

Jev SEO Topic-Gap Reviewer — Find Content Gaps

Review supplied SEO query, page, and content context for intent alignment and duplicate risk using a TypeSafe Jev key. It does not retrieve rankings or volume.

state
questions
index
+9 more
12 fields19 runs
086ai / developer tools

Jev AI Agent Trace Evaluator — Score LLM Traces

Evaluate supplied AI-agent traces for evidence support, tool relevance, and review need using a TypeSafe Jev key. It never executes tools.

state
questions
index
+9 more
12 fields18 runs
087ai / lead generation

Jev Lead Qualification Scorer — B2B Lead Scoring

Score supplied leads against a buyer-provided ideal-customer profile using a TypeSafe Jev key. It never writes to a CRM.

state
questions
index
+9 more
12 fields18 runs
089ai / business

Jev Support Inbox Router — Classify Support Tickets

Route supplied support tickets to a fixed queue with urgency and review signals using a buyer-provided TypeSafe Jev key.

state
questions
index
+9 more
12 fields16 runs
091ai / business

Jev Review Intelligence Pro — Advanced Classifier

Enrich supplied review records with typed themes, severity, refund intent, and actionable-detail judgments.

id
sourceUrl
capturedAt
+5 more
8 fields7 runs
093ai / marketing

Jev AEO & GEO Visibility Enricher — AI Search

Enrich supplied answer-engine responses with brand stance and recommendation judgments.

id
prompt
engine
+8 more
11 fields6 runs