---
title: "Builds: content, media, email, calls and reading"
type: community
source_tier: community
tags: [ideas, builds, community, content, email, media]
created: 2026-09-25
updated: 2026-09-25
confidence: medium
sources:
  - raw/community/every-to-also-true-for-humans-mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-writte.md
  - raw/x/danshipper-2099947471518474522.md
  - raw/x/kraayenJon-2101157548346794059.md
  - raw/x/jozef_gherman-2100627898436571555.md
  - raw/x/robj3d3-2100722975645598191.md
  - raw/x/aresotik-2100949805573030378.md
  - raw/x/tshmieldev-2102014401314254912.md
  - raw/x-repos/ilyamk__jev-gmail-ai-spam-filter-and-labeling.md
  - raw/x-repos/fazlerocks__jevmail.md
  - raw/x/jnnnthnn-2101399331115077760.md
  - raw/x-repos/ZeroGold__call-coach-ai.md
  - raw/x/BurhanUsman-2101641842441732297.md
  - raw/x/richard_meng_01-2101897102557425680.md
  - raw/x/fayazara-2100953838891192789.md
  - raw/x-repos/cclank__jevclip.md
  - raw/x-repos/gaborishka__jev-wrapped.md
  - raw/x-repos/dani1005__book-aurora.md
  - raw/x-repos/AustinAWay__Working-Memory-Jev.md
  - raw/x-repos/AustinAWay__Working-Memory-Jev__docs-evaluation-2026-09-21-live-benchmark.md
  - raw/community/youtube-matthewberman-8-jev-use-cases.txt
jev_version: "jev-1.13.0"
summary: "Community builds for writing checks, ads, inboxes, chats, calls, video, images and reading: what Jev decides, reported numbers, flags (chats sent to third parties, licences). Numbers attributed."
---

# Builds: content, media, email, calls and reading

> **TL;DR** 15 builds plus 12 names (split from [[ideas/builds-apps]] on 2026-09-25) where Jev checks writing, scores posts and ads, or labels mail, chats, calls, transcripts, images and reading passages, and code sorts, cuts or counts. Evidence is thin: most rows have no accuracy figures; Every's check caught 6 of 7 planted defects (Fable 7 of 7), and the best-measured reading tool (Working Memory Jev) saw answers change between identical runs and ships two samples per decision. Chat readers send other people's messages to a third party: see the warning line. Every number is one builder's own run.

**How to read.** Price checks use $0.042/Mtok input, output free (`verified`, [[reference/models-and-pricing]]). Jev is text-only (`verified`), so audio and video go through speech-to-text or subtitles first ([[concepts/state]]). Data, search and business builds: [[ideas/builds-apps]]; games and robots: [[ideas/builds-games-and-devices]]; agents: [[ideas/builds-agents]]; browser and interface: [[ideas/builds-browser-and-interface]].

## Writing, 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 | [[ideas/patterns-business]] P30 | [Every](https://every.to/also-true-for-humans/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds), [@danshipper](https://x.com/danshipper/status/2099947471518474522) |
| 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 | [[ideas/patterns-business]] P30 | [kraayenJon](https://x.com/kraayenJon/status/2101157548346794059), [jevdetector](https://x.com/jozef_gherman/status/2100627898436571555) |
| 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) | [[ideas/patterns-business]] P21 | [post](https://x.com/robj3d3/status/2100722975645598191) |
| 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 | [[ideas/patterns-business]] P21 | [post](https://x.com/aresotik/status/2100949805573030378) |

Also seen, names only (vetted 2026-09-24): [Human Compiler](https://github.com/asfarsadewa/human-compiler) (a joke linter, but a clean split: ~30 `noul`s and 3 `choice`s in one request, deterministic rules emit coded diagnostics), [jev-audio-beeper](https://github.com/santos-sanz/jev-audio-beeper) (per-word profanity check over ASR timestamps, beeped with ffmpeg; no licence; a quoted ~466 ms is in no file, `unverified`), [Jev Web Analyzer](https://github.com/replynodes/jev-web-analyzer) (ten `Choice`s over a homepage; also a demo for the vendor's scraping product), [sharp](https://github.com/tshmieldev/sharp) ([@tshmieldev](https://x.com/tshmieldev/status/2102014401314254912): Jev vs LLMs classifying an X feed; the comparison is only in a video).

## Email and inbox

| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| jevMail (ilyamk, @ILIA_AGI) | Google Apps Script in your own Gmail: one `Choice` per email over up to 12 labels you describe; metadata first, the message body only when the answer is unsure or the label would archive; preview mode, archiving only for categories you allow, a per-run budget checked before each request | No accuracy figures. Jev only through OpenRouter's alpha Decisions endpoint, billed there | [[ideas/patterns-business]] P22 | [repo](https://github.com/ilyamk/jev-gmail-ai-spam-filter-and-labeling) |
| Jevmail (fazlerocks, Syed Fazle Rahman; not ilyamk's jevMail) | Local Gmail triage, read-only by OAuth scope (`gmail.readonly`), local SQLite: one request per email via Vercel AI Gateway `typesafe-ai/jev`, three questions (tray of five: needs reply, updates, promos, sales, spam; urgency 1-5; written to you by a human?); top two probabilities shown; your corrections stored beside Jev's answer | Author: 1,000 emails in about a minute for ~3 cents; no accuracy figures. Its note that the Gateway free tier allows 5 calls per 5 minutes is Vercel's limit (`unverified` here) | [[ideas/patterns-business]] P22 | [repo](https://github.com/fazlerocks/jevmail) |
| Live-prioritised inbox (@jnnnthnn; "coming to @avec") | Inbox ordered by importance instead of arrival time. Likely one priority judgment per email, sorted in code (inferred; video only) | Berman narrates the demo as 100 emails sorted in under half a second; no accuracy figures. For ranking, mind the batching conflict on [[ideas/builds-apps]] (audits) | [[ideas/patterns-business]] P22, P20 | [post](https://x.com/jnnnthnn/status/2101399331115077760) |

## Calls and messaging

| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| Call Coach (ZeroGold) | Live sales call: browser speech-to-text; after each sentence one request (next action `Choice`, buying stage `Score`, seven signal `Noul`s) over the last 40 turns; smoothing, hysteresis and tie-breaks in code; key stays in a local Node proxy | Demo, no numbers. README warns that conversation text goes to TypeSafe (in Chrome, audio also goes to Google) and to pin a version instead of `jev-latest` (`verified` advice, [[reference/models-and-pricing]]) | [[ideas/patterns-business]] P28, [[ideas/patterns-data]] P27 | [repo](https://github.com/ZeroGold/call-coach-ai) |

**Chat readers, names only (vetted 2026-09-25):** [Crush Monitor](https://github.com/FerryCorleone/crush-monitor) (pasted chats → per-message emotion and intent; its "$5 trial credits" line predates signups closing, [[entities/typesafe-console]]), [哑巴微信](https://github.com/wuxie888/jev-yaba-wechat) (OCR of the WeChat window, an LLM drafts replies, Jev ranks them), [狗头军师 Jev Chat](https://github.com/shengjidaguai-china/goutoujunshi-jev-chat) (screen-reads chats; ships a Windows EXE), [WeChat Jev Assistant](https://github.com/yushen100/wechat-jev-assistant) (reads WeChat's local database through third-party code fetched at setup; redacts names first; no licence), the [jev-chat-jarvis](https://github.com/jev-chat/jev-chat-jarvis-ios) family (iOS keyboard with Full Access plus desktop siblings: copied message → intent, risk, reply drafts). **Warning for all of them:** the other person's messages go to a third-party API without their consent, and client hooking or screen-reading can get an account banned. Sideloaded binaries: build from source.

## Video, media and feeds

| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| clipfast (@BurhanUsman) | Type a topic, get the matching clips of a long video, one-click download. Jev must read a transcript (Matthew Berman guesses the same); timestamps and cutting stay in code (inferred) | 90+ minute video clipped "under 2 seconds" for about 2 cents (author). 2 cents buys ~476k input tokens at list price, ~26 passes over a 90-minute transcript (~18k tokens, inferred; our arithmetic): plausible, not checkable. No accuracy figures | [[ideas/patterns-data]] P27 | [post](https://x.com/BurhanUsman/status/2101641842441732297) |
| jevclip (cclank, lanshu; README in Chinese) | Subtitles cut at pauses into ~20 s segments; five questions per segment (8-way type `Choice`, 0-3 information `Score`, exaggerated-claim `Noul`, stands-alone `Noul`, up to 5 focus `Noul`s); code keeps or drops each with a stated reason, fills a ≤ 180 s highlight reel and a filler-free full cut with ffmpeg. An LLM summary may cite only segment ids, which code maps to timestamps and checks for numbers and names | Synthetic 9 min 22 s test: all 12 blocks right by the second; 12 requests, ~17k tokens, $0.0007 (arithmetic `verified`). Real 16 min 52 s talk: 45 s segments dropped the key demo (averaged with filler to 0.49); 20 s segments kept it, 32 requests, $0.0019. Default thresholds are guesses; `jevclip eval` fits them to ~50 of your labels | [[ideas/patterns-data]] P27, [[ideas/patterns-emerging]] P42 | [repo](https://github.com/cclank/jevclip) |
| Jev Wrapped (gaborishka) | Four questions per Telegram post, one request each: kind of post (one of ten), paid ad?, clickbait?, emotional pressure?; up to 1,500 posts from the last year, sampled evenly; code counts shares (an ad at ≥ 70% on the `Noul`, or ≥ 40% when the kind also said ad) | ~1,500 posts in ~85 s via TypeSafe (2 pages at a time to stay under the 1,200 requests/minute limit, `verified`) vs ~35 s via OpenRouter (4 at a time); ~$0.10 per channel at list price. **Limitation stated:** on a channel with no paid ads it marked two partner promotions as ads | [[ideas/patterns-data]] P18 | [repo](https://github.com/gaborishka/jev-wrapped) |
| Image sorter (@fayazara) | OCR text first, then Jev picks a category | ~900 images in 40 s | [[ideas/patterns-data]] P18 | [post](https://x.com/fayazara/status/2100953838891192789) |
| 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 | [[ideas/patterns-data]] P16 | [post](https://x.com/richard_meng_01/status/2101897102557425680) |

Also seen, names only (vetted 2026-09-25): [changelog.earth](https://github.com/byalex33/changelog.earth) (news as patch notes: an LLM selects and titles, Jev optionally checks eligibility and title accuracy), [RefGarden](https://github.com/AlbionaHoti/refgarden) (Jev picks search phrases over museum and NASA archives; the hosted build now refuses Jev keys with a 410), [Book of Answers](https://github.com/csskrtao/jev-to-answer) (an LLM lists options for a dilemma, Jev picks one; no licence).

## Reading and learning

| Build (builder) | Jev decides | Reported numbers | Pattern | Source |
|---|---|---|---|---|
| Book Aurora (dani1005) | Ten questions per ~90-word passage in one request: a 0-3 `Score` for each of nine emotions plus intensity; code draws the picture | Frankenstein: 601 passages, 6,010 decisions, ~22 s without the screen recorder, ~3 cents; a duplicate request fires after 1.5 s by default. Its direct-route variable is `TYPESAFE_AI_API_KEY`, the app's own name (TypeSafe's SDKs read `TYPESAFE_API_KEY`, [[reference/environment-variables]]) | [[ideas/patterns-data]] P18 | [repo](https://github.com/dani1005/book-aurora) |
| Working Memory Jev / Passage (AustinAWay) | Educator tool: where an English passage (≤ 6,000 characters) asks a reader to hold too much at once. A local parser proposes reading steps; Jev makes bounded choices on familiarity, active or background, grouping and relationships; code counts slots against a 1-5 budget | [Live benchmark](https://github.com/AustinAWay/Working-Memory-Jev/blob/cee3edb9922115d759778434878f6c56b483b390/docs/evaluation/2026-09-21-live-benchmark.md) (2026-09-21, 10 cases + 4 probes, every pass run twice): **choice changed between runs 2.9%** (6.4% at baseline), supported status flipped 5.7%, slot count changed on 3 of 43 steps; relationship accounting resolved on only 9.3% of clauses; support rate 0.717; 1,638 requests, 9.5M input tokens, ~$0.40 (arithmetic `verified`). Because answers vary it sends each batch `PASSAGE_JEV_SAMPLES` times (default 2): one sample gave 4.5% choice flips, two gave 2.4%. Author: not a measure of student memory. **Custom licence:** organisations with more than one employee, or any commercial use, must ask first | [[ideas/patterns-data]] P18, [[ideas/patterns-emerging]] P42 | [repo](https://github.com/AustinAWay/Working-Memory-Jev) |

## What these builds teach when advising

- **A linter beside the writer.** Many cheap yes/no checks per draft (Every, slop detectors, SuperX) suit Jev; in Shipper's test Jev caught 6 of 7 planted defects, Fable 5.1 all 7.
- **Private text leaves the device.** Mail, calls and chats go to TypeSafe or a gateway; Call Coach and WeChat Jev Assistant say so, the chat readers also send people who never agreed ([[reference/legal-and-data]]).
- **Read-only first.** Jevmail's `gmail.readonly` scope and jevMail's preview mode keep a wrong label from costing mail.
- **Segment size is a design choice.** jevclip's 45 s segments averaged a key demo away; 20 s kept it.
- **Sample twice when stability matters.** Working Memory Jev halved choice flips with two samples at twice the requests ([[ideas/request-mechanics]]).
- **Fit thresholds to your labels.** jevclip ships guesses and an `eval` command; tune them ([[guides/testing-and-evaluation]]).

## Related

- [[ideas/builds-apps]] — data, search and business builds; [[ideas/builds-games-and-devices]] — games, simulators, robots
- [[ideas/patterns-business]] — P20, P21, P22, P28, P30; [[ideas/patterns-data]] — P18, P27; [[ideas/patterns-emerging]] — P42
- [[ideas/failure-reports]], [[ideas/measurements]] — breakages and measured numbers

## Sources

Links are inline in each row; the raw captures (2026-09-20 to 2026-09-25) are listed in the frontmatter. Matthew Berman's [video](https://www.youtube.com/watch?v=jGD_UR4wMJc) (machine captions, raw/community/youtube-matthewberman-8-jev-use-cases.txt) narrates the clipfast and inbox demos. Names-only entries without a capture rest on our vetting at source: 2026-09-24 (docs/sweep/2026-09-24-awesome-jev/part1.md) and 2026-09-25 (docs/sweep/2026-09-25-mrjev/partb.md). The writing, content and marketing rows moved here from [[ideas/builds-apps]] unchanged.