~/wiki/ideas
Builds: data, content, business, games and devices
TL;DR What people shipped with Jev outside agent loops, one row per build: what Jev decides, reported numbers, pattern ID, link. Every number is one builder's own run; re-measure on your data (Testing and evaluating a Jev workflow). Agent and browser builds: Builds: agents, coding tools, browser and interface. Price checks use $0.042/Mtok input, output free (
verified, Models, aliases, pricing, rate limits, context).
Data and search
| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| likethisgame.com recs (Mehmet Aras) | Noul per candidate "would a fan of X like Y?", 20 candidates per request; top 30 of 600 go to an LLM that writes the recs; code down-weights popular games | Batched vs one-by-one rankings Spearman 0.884; 600 candidates = 30 requests, ~2 s, $0.007; 243 pages $2.02 total, $1.59 of it Jev. Filtering after generation failed (strict cut removed 150 of 216 recs); ranking before won blind comparisons 11-9 (10 ties). Jev's effect not yet separated from better candidates (author). Via OpenRouter's decisions endpoint (unverified, not in TypeSafe docs) |
Patterns: judging, search, documents, real-time and markets P17 | dev.to |
| jevsearch (@kylemclaren) | Reranks React site-search results | none in the capture | Patterns: judging, search, documents, real-time and markets P17 | post |
| tocsin (Ateeq) | Log lines masked and templated in code; one request per new template: pageable, detail Nouls, severity Score 0-3, area Choice, against a plain-English paging policy. Code: attention = pageable × (1 − detail), verdicts cached |
22.8M lines → 11,812 templates → 13,080 calls, $0.64, 6 m 23 s (every line would be $1,120); p50 ~370 ms. BGL (tuned on) F1 0.860; Thunderbird held out F1 0.000: its dominant alert pattern scored 0.65 and went to ticket. Offline keyword fallback |
Patterns: judging, search, documents, real-time and markets P18 | repo |
| HN categoriser (@sabrinaesaquino) | 24,000 Hacker News posts into 12 categories | "about 2 minutes"; via the Venice API beta (gateway unverified) |
Patterns: judging, search, documents, real-time and markets P18 | post |
| Image sorter (@fayazara) | OCR text first, then Jev picks a category | ~900 images in 40 s | Patterns: judging, search, documents, real-time and markets P18 | post |
| Nitpicky (@richard_meng_01, roe-ai) | AI-image detector judging faces, fingers, text, poses region by region | none. Jev is text-only (verified), so a vision step must describe regions first; how is not stated |
Patterns: judging, search, documents, real-time and markets P16 | post |
| jev-reviewer (Ahmad Sofi-Mahmudi) | Systematic-review extraction: pass 1 Choice "which line answers q?" (+ none) per 2-3 pages; pass 2 Noul per candidate line, keep ≥ 0.5; code copies the verbatim quote. "Not found" is an answer | 712-line sample study: 18-question template, 27 requests, 4.6 s, $0.0101; 12,000-char chunks = same answers as 7,000 with a third fewer requests. Author: spot checks, not validation | Patterns: judging, search, documents, real-time and markets P26 | repo |
| Proq plan sets (@hari_trinay) | Sheet type per construction-plan sheet | 26 sheets in 2.9 s for $0.0052; matched GPT-4.1 and GPT-6 Astra on 100% of sheets; "17–21x cheaper and 5x faster" than their pipeline | Patterns: judging, search, documents, real-time and markets P26 | post |
| Langfuse trace judge (Annabell Schäfer, Langfuse) | One request per agent run: needs_review Noul, severity Score, failure_mode Choice; score written back to the trace. Now a built-in Langfuse evaluator |
Cites Good Start Labs: 6,003 rubric checks, 91.5% agreement with Fable 5.1 at $160 per million graded answers vs $33,000. Noul has no confidence (verified, Noul (yes/no) questions); warns Jev cannot abstain, so add an escape option |
Patterns: judging, search, documents, real-time and markets P15 | blog |
Content and marketing
| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| Every writing checks (Mike Taylor; Dan Shipper) | 21 yes/no AI-tell questions per article (Noul, inferred); 11 experiments (context finding, reply grading, triage) | 37 docs × 21 = 777 judgments in < 0.7 s, ~¼ cent; 1,709 judgments < 1 cent. Shipper: 4 checks × 12 passages, Jev 0.35 s median vs 8.83 s Fable 5.1, ~580x cheaper, caught 6 of 7 planted defects (Fable 7 of 7). Idea: a linter an agent runs after each paragraph | Patterns: marketing, sales, GTM, content, support and ops P30 | Every, @danshipper |
| Slop detectors (@kraayenJon; @jozef_gherman) | One question per AI-slop tell on a page or text (type not stated) | Kraayenbrink: 35 tells, 243 ms, $0.00015. Gherman: ~10,000 words in ~2 s | Patterns: marketing, sales, GTM, content, support and ops P30 | kraayenJon, jevdetector |
| SuperX post scorer (@robj3d3) | 61 questions per draft; loop: draft, score, revise until the score stops rising | ~1 s, $0.0004 per post; fitted on 9,481 posts from 207 creators; picks the viral post "2 in 3 times" (no baseline stated) | Patterns: marketing, sales, GTM, content, support and ops P21 | post |
| maxfusion ad teardown (Ori Silver, via @aresotik) | Funnel stage and creative style per ad in a brand's ad library | 1,891 ads in 19 s for $0.12 | Patterns: marketing, sales, GTM, content, support and ops P21 | post |
Business ops
| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| Fraud email cascade (Hassan, @nutlope) | Fraud vs legit; confidence < 0.95 escalates to Kimi K3 | 100 emails in 1.42 s; 31 escalated; pipeline 96/100 in 16 s for ~$0.07, of which Jev $0.003 | Patterns: agent internals, context and coding agents P06, Confidence-gated routing | post |
| Spliit Cloud expenses (Antonio Ivanovski) | Expense category from title: local dictionary, then group history, then one engine (LLM or Jev Choice); below AI_CATEGORY_MIN_CONFIDENCE (0.5) no suggestion; uncertain guesses shown as one-tap chips |
none. README: pin jev-1.13.0 once thresholds are tuned, jev-latest moves (verified, Models, aliases, pricing, rate limits, context); LLM self-reported and Jev confidence are not on one scale, recalibrate when switching |
Patterns: agent internals, context and coding agents P06, Patterns: browser, computer use, voice and product UI P34 | repo |
| Regex rules → Jev (Ilias Ism, @illyism) | Hard-coded rules (vibe-coded regex) replaced in aiseotracker, linkdr, genppt | "around 10x faster, 50% cheaper" than regular LLM calls (no method) | Patterns: agent internals, context and coding agents P01 | post |
| Backdoor job match (@sarvagya_kul) | Fit probability of one candidate for 400 companies; flags mismatches | 12 s, $0.0005. At list price that is ~12k input tokens, ~30 per company: only fits very short profiles; treat as approximate | Patterns: marketing, sales, GTM, content, support and ops P19 | post |
| Gojiberry outreach mining (@pierreeliottlal) | Labels thousands of outreach messages by intent signal; which signals booked demos (the tally is code, inferred) | 40 s, < $0.20 | Patterns: judging, search, documents, real-time and markets P18, Patterns: marketing, sales, GTM, content, support and ops P20 | post |
Games, simulation and devices
| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| Dual-arm robot (@Raptor_zip) | Middle layer of three: the decision; IK and physics in code | ~500 ms per answer, ~0.5 yen per trial | Patterns: judging, search, documents, real-time and markets P24 | post |
| RoboJEV (lyk) | Franka arm in MuJoCo, structured state not images: Choice of intent, then per-axis negative/zero/positive and gripper open/hold/close; malformed answers execute nothing |
100 episodes, 10 seeds each, Jev vs rule baseline: pick-place, push, peg 10/10 both; stack 8/10 vs 10/10; gate obstacle 5/10 vs 8/10. Failures: repeated wrong-direction moves exhausting the budget, one inconsistent answer | Patterns: judging, search, documents, real-time and markets P24 | repo |
| JevScape (Skyvern-AI) | RuneScape via ~50 coded actions: next_action, a this_tick fix-up, and when to poll next |
Mean peak XP/min: random 235, Jev 197, Claude Opus 118; Jev total XP 2.1x random; 1,307 decisions, $0.17. Live: 13,402 polls, $2.22, median 0.22 s, ~$0.55/h. Authors: "The catalog carries the game knowledge" | Patterns: judging, search, documents, real-time and markets P24 | repo |
Markets (engineering only, not financial advice)
| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| fedjev-bench (maybern-tripp-smith) | Pairwise Choice "more hawkish about inflation" over FOMC press-conference openings, checked against rate actions and FedLock scores | Main run ≈ $0.031; gates 1, 3, 4, 6 pass, 2/5/7 reported; 7-criterion extension $1.5329. Text ranking, not a trade signal; buy/sell (Patterns: judging, search, documents, real-time and markets P25) stays poor |
Patterns: judging, search, documents, real-time and markets P17 | repo |
Audits to rerun before you build
| Audit (author) | Finding that changes a design | Pattern |
|---|---|---|
| jev-evaluation (Will Kelly; 123,805 requests, $12.69) | 60 questions on one state: 20x fewer tokens, 8x sooner, identical answers. 60 tickets in one state: 1.000 when each question names its ticket, 0.420 with "Ticket 1". Source text 0.894 vs pre-digested edge list 0.530. A polite "lead already decided" line flipped 147/200 tickets (crude injection 1/200). A 0.8 gate catches 95.5% of missing-fact states, none of fluent nonsense | Patterns: judging, search, documents, real-time and markets P15 |
| jev-orderby-bench (yodablocks) | Passes on 360 rows (inversion 0.036); fails 4 of 6 gates on hard shopping relevance. 40-row batches fail the ranking gate (0.171) that one row per request passes. Two-decimal probabilities: 53 rows tie at 0.99, so LIMIT 20 is partly arbitrary |
Patterns: judging, search, documents, real-time and markets P17 |
| jev-acento (Marcos Martinez; 19,200 calls, $0.58) | Spanish state costs 3.0-6.4 pp accuracy and doubles ECE on XNLI; Spanish instructions do not help, keep them in English; 17-38% more tokens. Direction matches docs (English primary, verified) |
Patterns: judging, search, documents, real-time and markets P18 |
| jev-capability-atlas (Zaious) | A typo in the correct option drew 0.90 confidence on a wrong answer; strong when the signal is in state, weak when outside knowledge is needed |
Patterns: judging, search, documents, real-time and markets P16 |
Conflict: Kelly finds batching safe when questions name their subject; the ORDER BY bench finds 40-row batches break ranking. For ranking products, send one item per request or test both (yodablocks' own jobbyjev does one company per request).
What these builds teach when advising
- Jev ranks, code or an LLM acts. Recs, search, fraud and robots all keep generation, arithmetic and physics outside Jev.
- Put Jev before generation, not after. Aras's post-filter failed; pre-ranking candidates worked.
- Collapse, then judge once. tocsin's templates and verdict cache turn 22.8M lines into 13k calls.
- Select, don't write. jev-reviewer picks line ids, code copies quotes: nothing to hallucinate.
- Cheap local stages first, one engine, a floor, a pinned version (Spliit), then escalate the uncertain (@nutlope).
- Tuned policies don't travel. tocsin's held-out F1 was 0; RoboJEV lost to rules on two tasks. Label your own sample.
- A good action catalog can beat a model: JevScape's random baseline outscored Jev on peak XP.
- Images, audio, scans: OCR or a vision step to text first (State: what you send Jev).
- Check the arithmetic of viral cost claims against token counts (Measurements, access routes and open replicas).
Related
- Builds: agents, coding tools, browser and interface — agent, coding and browser builds
- Decision patterns from the community (with fit verdicts) — pattern index; domain pages Patterns: judging, search, documents, real-time and markets, Patterns: marketing, sales, GTM, content, support and ops
- Head-to-head: Jev against other models and methods, Failure reports: where Jev broke, lost, or was the wrong tool — comparisons and breakages
- Tools and integrations: MCP servers, skills, clients, gateways and libraries — SDK wrappers, gateways, eval tooling
- Jev 1.13 jaggedness: known failure modes — documented failure modes behind the fit verdicts
Sources
- raw/community/dev-to-arasovic-searching-for-better-game-recommendations-with-jev-20d9.md (https://dev.to/arasovic/searching-for-better-game-recommendations-with-jev-20d9)
- raw/x/kylemclaren-2102038326588878950.md (https://x.com/kylemclaren/status/2102038326588878950)
- raw/x-repos/TPAteeq__tocsin.md (https://github.com/TPAteeq/tocsin)
- raw/x/sabrinaesaquino-2101102660997017747.md (https://x.com/sabrinaesaquino/status/2101102660997017747)
- raw/x/fayazara-2100953838891192789.md (https://x.com/fayazara/status/2100953838891192789)
- raw/x/richard_meng_01-2101897102557425680.md (https://x.com/richard_meng_01/status/2101897102557425680)
- raw/x-repos/choxos__jev-reviewer.md (https://github.com/choxos/jev-reviewer)
- raw/x/hari_trinay-2101118529936519453.md (https://x.com/hari_trinay/status/2101118529936519453)
- raw/community/langfuse-com-blog-2026-09-18-using-typesafes-jev-for-evals.md (https://langfuse.com/blog/2026-09-18-using-typesafes-jev-for-evals)
- raw/community/every-to-also-true-for-humans-mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-writte.md (https://every.to/also-true-for-humans/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds)
- raw/x/danshipper-2099947471518474522.md (https://x.com/danshipper/status/2099947471518474522)
- raw/x/kraayenJon-2101157548346794059.md (https://x.com/kraayenJon/status/2101157548346794059)
- raw/x/jozef_gherman-2100627898436571555.md (https://x.com/jozef_gherman/status/2100627898436571555)
- raw/x/robj3d3-2100722975645598191.md (https://x.com/robj3d3/status/2100722975645598191)
- raw/x/aresotik-2100949805573030378.md (https://x.com/aresotik/status/2100949805573030378)
- raw/x/nutlope-2100614659690713543.md (https://x.com/nutlope/status/2100614659690713543)
- raw/x-repos/antonio-ivanovski__spliit-cloud.md (https://github.com/antonio-ivanovski/spliit-cloud)
- raw/x/illyism-2100489521557123265.md (https://x.com/illyism/status/2100489521557123265)
- raw/x/sarvagya_kul-2100980770206879849.md (https://x.com/sarvagya_kul/status/2100980770206879849)
- raw/x/pierreeliottlal-2100912453999587657.md (https://x.com/pierreeliottlal/status/2100912453999587657)
- raw/x/Raptor_zip-2101091398447505567.md (https://x.com/Raptor_zip/status/2101091398447505567)
- raw/x-repos/lykycy123__RoboJEV.md (https://github.com/lykycy123/RoboJEV)
- raw/x-repos/Skyvern-AI__jevscape.md (https://github.com/Skyvern-AI/jevscape)
- raw/x-repos/maybern-tripp-smith__fedjev-bench.md (https://github.com/maybern-tripp-smith/fedjev-bench)
- raw/x-repos/willkelly__jev-evaluation.md (https://github.com/willkelly/jev-evaluation)
- raw/x-repos/yodablocks__jev-orderby-bench.md (https://github.com/yodablocks/jev-orderby-bench)
- raw/x-repos/marcosmartinez__jev-acento.md (https://github.com/marcosmartinez/jev-acento)
- raw/x-repos/Zaious__jev-capability-atlas.md (https://github.com/Zaious/jev-capability-atlas)