--- title: "Patterns: judging, search, documents, real-time and markets" type: community source_tier: community tags: [ideas, patterns, search, documents, moderation] created: 2026-09-21 updated: 2026-09-21 confidence: medium sources: - raw/nate/jev-shaped-problems.md - raw/x-repos/kyotofin__tax-doc-classifier.md - raw/x/nedwize-2100973868324417852.md - raw/x/iannuttall-2100668908227162567.md - raw/x/INDEX.json - raw/x/LangChain-2101454284927959080.md - raw/x/mvanhorn-2100784142850097482.md - raw/x/jerryjliu0-2101738281046294552.md - raw/x/startupideaspod-2101029801821941933.md - raw/x-repos/INDEX.json - raw/x-repos/jerryjliu__docjev.md - raw/x-repos/ellipsis-dev__blink.md - raw/x-repos/AkashPriyadarshii__jev-curate.md - raw/x-repos/jkudish__jev-mcp.md jev_version: "jev-1.13.0" summary: "P15-P18 and P24-P27: community decision patterns for judging, moderation, search and ranking, corpus labelling, documents, transcripts, devices and markets, with fit verdicts." --- # Patterns: judging, search, documents, real-time and markets > **TL;DR** Eight decision shapes people published for evaluation and moderation, retrieval and corpus labelling, document and transcript processing, device control, and market signals. Scan the **Decision** lines, then follow **Map** into the official pages for the real contract. ## How to read this One pattern = one narrow judgment. **Fit** is our verdict against [[concepts/jaggedness-jev-1-13]] and [[concepts/system-one]]: `strong` = bounded options, semantic judgment, code owns the rest; `workable` = real, caveat named; `poor` = leans on arithmetic, dates, indirection, generation or huge state. Pattern IDs are permanent and never renumbered; the index of all patterns is [[ideas/patterns]]. Posted numbers are attributed and unverified. ## Moderation, guardrails & judging **P15 Jev-as-a-judge for agent evals** - *Decision* did this captured agent run pass, and how good was it - *State* the frozen trace: question, tool calls, evidence, final answer - *Ask* `Noul` for `does_pass`, `Score` on an ordered quality rubric - *Code* replay the same fixed runs; keep a human-labelled oracle to check the judge - *Fit* strong — @LangChain reports 0.44s, $0.00035/call and per-case variance 92–913x below three LLM judges (five-example set) - *Map* [[cookbooks/consistency-noul]] - *Seen* [@LangChain](https://x.com/LangChain/status/2101454284927959080), `danielgshea/jev-as-a-judge` **P16 Screening what goes in and what comes out** - *Decision* does this input steer the agent or break rules; does this draft follow policy - *State* one untrusted message, or the draft plus the rules or source passage - *Ask* `Noul`s where `true` means something is wrong; add an `uncertain` `Choice` option - *Code* aggregate with `max`; only failures and the uncertain band reach a person - *Fit* workable — the docs say jev-1.13 is *not* hardened against adversarial text - *Map* [[cookbooks/citation-check]] - *Seen* [@LeoTava8](https://x.com/LeoTava8/status/2100822293803143208) (110ms interception), [@shannholmberg](https://x.com/shannholmberg/status/2101050494202634537), `brainstormity/Jev-Moderation-Bot`, `jkudish/jev-mcp` (a screen tool returns injection, substance and relevance probabilities for a fetched page and recommends pass/review/block/skip — advisory only, the caller enforces) ## Search, ranking & data at scale **P17 Per-candidate relevance: rerank, SQL predicate, graph edge** - *Decision* does this candidate answer the query, match the condition, or lead somewhere - *State* the query plus one candidate, one row, or a node with its neighbour edges - *Ask* `Noul` per pair for relevance; `Choice` over neighbour ids for traversal - *Code* shortlist with ordinary search or SQL first; Jev re-ranks. Never ask for counts - *Fit* strong per pair — the shipped recipe raised top-10 from 38% to 62% on legal queries - *Map* [[cookbooks/rerank]], [[cookbooks/semantic-find]] - *Seen* [@mvanhorn](https://x.com/mvanhorn/status/2100784142850097482), `realZachi/pg-jev`, `superagents-lab/jev-search`, `ellipsis-dev/blink` (the traversal variant: Jev scores file and folder *names*, many independent walkers are allocated by those probabilities, and the answer is the share of walkers that landed on each file — no index, no embeddings), `jkudish/jev-mcp` (find = one `Choice` over up to 250 candidate ids plus a separate existence check, because a Choice always returns a winner; rerank = one relevance question per candidate so the whole ordering survives) **P18 Map-reduce labelling over a corpus or a timeline** - *Decision* every semantic label you want per record, page element or transcript span - *State* one record, or one segment with its neighbours — only the needed fields - *Ask* every independent `Noul`/`Choice`/`Score` in a single request per item - *Code* parallel workers; stitch adjacent positives into ranges, aggregate rates in code. Store answers keyed by record id so a new question later costs one pass, not a redo; let a reasoning model propose 5-8 narrow questions, approve them, run a 50-record sample first ([Nate B. Jones](https://unlock-ai.natebjones.com/guides/jev-shaped-problems), placement 2). A pattern across labels is a lead, not a cause - *Fit* strong per item — the cheapest thing free output tokens unlock; boundary maths stays in code - *Map* [[cookbooks/parallel-questions]] - *Seen* [@0xMovez](https://x.com/0xMovez/status/2101325703635435523) (100k posts × 14 questions, 20.4s, $0.67), [@iannuttall](https://x.com/iannuttall/status/2100668908227162567) (3,282 of his posts × 8 questions, 4.25M tokens, $0.1282, 8m34s, then joined to likes in code — author-reported; arithmetic `verified` against $0.042/Mtok), [@mvanhorn](https://x.com/mvanhorn/status/2100784142850097482) (777 judgments in <0.7s), `kitze/unclutter`, `AkashPriyadarshii/jev-curate` (the training-data variant: stream Parquet/JSONL rows, ask a fixed rubric per row — circular logic, step validity, sycophancy, unclosed fences — and write clean/rejected splits verbatim; author reports 1,500+ rows/sec with host-side pre-filtering and an adaptive token bucket for `429`s) ## Documents & transcripts **P26 Document classification and packet splitting** - *Decision* what is this document; does a new document start on this page - *State* normalized page text from a local parse/OCR stage, plus the category rules verbatim - *Ask* `Choice` over stable category ids with a one-line purpose `description` each (keep an `other` id); splitting is page-level, so the per-page category decision is the question and boundaries fall out of it (inferred — the repo averages page scores per segment) - *Code* OCR is a separate, fallible stage; page ranges, coverage checks and export are assembled in code. Long packets must be chunked: 64k per request, 32k for `state` plus the longest question ([[concepts/state]]), and the repo says oversized single pages fail explicitly rather than truncating - *Fit* strong — bounded id set, semantic "what is this for" judgment, no arithmetic - *Map* [[cookbooks/hierarchical-classification]], [[concepts/choice]] - *Seen* [@nedwize](https://x.com/nedwize/status/2100973868324417852), `kyotofin/tax-doc-classifier` (one request per page: a 7-option page-kind `Choice` plus a 230-option form `Choice` with `not_in_this_list`, a second small `Choice` only for five parent forms; gate at 0.95 on the minimum confidence; 0 wrong on 1,067 pages, 38 below the gate; $0.00115 vs $0.039 per page and ~0.5 s vs ~3.3 s against its Claude Sonnet predecessor — author-measured; option count `verified` under the 255 limit, [[concepts/choice]]). [@jerryjliu0](https://x.com/jerryjliu0/status/2101738281046294552), `jerryjliu/docjev` (OCR backends: local liteparse by default, LlamaParse tiers for hard scans). Its 40-document pilot: both engines classified 40/40 correctly; Jev split 7/8 packets exactly against GPT-5.6 Luna's 8/8, with Jev's one extra boundary inside a Fed statement's attachment. The author claims it is "6x faster than gpt-5.6-luna" at equivalent accuracy; the repo's own medians are 138.6ms vs 794.3ms (classify) and 209.6ms vs 1,352.3ms (split), on a small convenience sample with uncontrolled provider caching **P27 Moment finding over a transcript** - *Decision* is this span of transcript a strong, self-contained moment - *State* one chunk — a window of transcript text with a little of its neighbours; code keeps the chunk → timestamp map - *Ask* `Score` on an ordered rubric per chunk (hook, self-contained, payoff); optionally a `Noul` for "does a new moment start here?" - *Code* you chunk, you hold the times, you sort and take the top N; merge adjacent winners in code - *Fit* workable — strong per chunk (it is P18 over a timeline), poor as "read this transcript and return the timestamps of the best 17 moments": time arithmetic and counting are documented weaknesses ([[concepts/jaggedness-jev-1-13]]) - *Map* [[patterns/composite-scoring]], [[cookbooks/parallel-questions]] - *Seen* [@startupideaspod](https://x.com/startupideaspod/status/2101029801821941933) — Ryan Vogel reports a clip finder built in ~10 minutes that scored ~17 strong moments in about 3 seconds (author-reported, no accuracy check) ## Real-time, games, robotics & IoT **P24 Action selection from simulator or device state** - *Decision* which legal move this tick; does this sensor picture need action - *State* the sim or home state as compact JSON, plus the legal move list - *Ask* `Choice` over move ids; `Noul` per automation condition in plain words - *Code* fast model reacts, slow model plans; code owns the tick budget and safety cutout - *Fit* workable — text-only and network-bound, so budget 70–500ms; numeric thresholds stay in code - *Map* [[guides/smart-home-demo]] - *Seen* `fhshaik/typesafe-mario`, `RomanSlack/jev-drone`, `AboveColin/HA-Jev`, [@jpschroeder](https://x.com/jpschroeder/status/2100952337904767258) (10Hz needs ~10x lower price) ## Markets & trading Nothing here is investment advice and none of it is a recommendation to trade. jev-1.13 is documented to be unreliable at arithmetic, numeric representations and date/time comparison — most of what a market decision rests on. **P25 Per-block buy/sell decision** - *Decision* buy, sell or hold given a state your code already computed - *State* pre-computed indicators as named English buckets — never raw price arrays - *Ask* `Choice` over `buy | sell | hold` with criteria describing each regime - *Code* sizing, limits, risk caps and kill switches are code; the public repo defaults to dry-run - *Fit* poor as usually posted — the judgment is numeric, and calibration is a population property, not a per-trade guarantee - *Map* [[concepts/confidence]] - *Seen* [@oragnes](https://x.com/oragnes/status/2100400215245377895), `jarrodwatts/jev-trader` (author states profitability is unverified), [@startupideaspod](https://x.com/startupideaspod/status/2101029801821941933) — Ryan Vogel wired Jev to a per-minute Bitcoin buy/hold/sell signal and reports it "performed poorly"; he keeps Jev on routing-style decisions and away from portfolios and crypto, which matches the verdict above ## Related - [[ideas/patterns]] — the index of every Pxx, routing and anti-patterns - [[ideas/consult]] — running the "could Jev help this project?" conversation - [[ideas/patterns-agents]] — agent loops, context, coding agents; [[ideas/patterns-interface]] — browser, computer use, UI - [[ideas/patterns-business]] — marketing, sales, support and ops (P19-P23, P28-P33) - [[ideas/field-reports]] — independent measurements behind the numbers quoted here - [[ideas/community-repos]] — the repos named in *Seen* ## Sources Post and repo links are inline in each pattern's **Seen** line. The captured posts and repo READMEs behind them are listed in this page's frontmatter `sources:` (files under `raw/x/` and `raw/x-repos/` in the private repo; indexes `raw/x/INDEX.json` and `raw/x-repos/INDEX.json`).