Scoring & Ranking

PDF question-answering demo where Jev chooses which extracted text chunk answers each question, shown with its location.

Semantic command palette demo where one Jev Choice over 77 commands per keystroke gives the ranking, beside a fuzzy-match baseline.

Next.js resume review app where Jev returns typed scores for overall fit, individual criteria and each experience bullet.

Web app that has Jev score emoji categories and candidates 0 to 3 for relevance to a short text and returns many matches.

Browser PDF search by meaning: Jev answers a yes/no per line on whether it answers your query, and matching lines light up.

Scores a page for SEO, answer engines and generative engines, using code for measurable checks and Jev rubric scores for judgment.

TypeScript CLI and REST API that asks Jev to rate an occupation's AI layoff risk, trajectory and need for human accountability.

Startup-idea evaluator where Jev scores eight indie-hacker questions and code turns the weighted average into KILL, FIX or SHIP.

Map where you ask anything in plain words and Jev gives every nearby place a probability, lighting up those likely to match.

Fingerprints a target, has Jev score every Nuclei template 0-4 for relevance, then runs all templates highest-relevance first.

Proof of concept that scores replayed support-call transcripts live against a weighted scorecard using OpenAI Decisions or Jev.

Open Jev-style 0.6B decision model plugged into BlitzRank and Reranker-Guided Search, scoring k candidates per match in one pass.

DeepSeek Harness paper-reading workbench whose PDF search reranks keyword candidates with Jev, falling back to keyword order.

Auto-clipper for talky videos: code enumerates every possible cut point and Jev judges where each standalone clip starts and ends.

CLI and MCP server giving coding agents Jev-powered semantic search, focused reads and list picking in about a second for about a cent.

Web search CLI for agents that has Jev score results and scraped chunks against the query and goal, passing only relevant ones on.

Profile matching that encodes preference criteria as Clef or Jev decision vectors, retrieves with HNSW and checks rules both ways.

Milvus bootcamp notebooks combining Gemini embeddings, Milvus retrieval and Jev judgments for reranking, filtering, routing and stopping.

Experimental Rust SEO and GEO CLI and MCP server combining page checks, DuckDuckGo queries and optional Jev scoring.

Repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.

Free web tool that checks any URL for 35 tells of AI-generated design and returns a slop score in about 250 ms.

Web demo that tests a social post against 10,000 synthetic personas before you publish it.

Test project using Jev to build chat-style search over a blog with hundreds of articles.

Sayora write-up comparing Jev with production embeddings for picking the right website page to answer caller questions.

ChemIllusion post on Jev ranking RDKit-validated structure candidates as autocomplete cards in a chemistry sketcher, about 0.2 s each.

Growth tool that asks Jev to score experiment results against a promotion bar and choose the next SEO, content or ad play.

A shared demo that scores TikTok and Instagram hooks against about 100 personas in near real time with Jev.