Docs
CommunityJev Cookbooks
Content Audits with Jev
Official Jev cookbook that audits all 279 pages of the Django documentation in under 5 seconds for about $0.10, asking 45 score, choice, and noul questions per page and plotting quality against importance.
- Format
- Docs
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Audits 279 Django documentation pages and 584,234 words in under 5 seconds for about $0.10.
- Each request holds one page and 45 questions covering quality, importance, classification, problems, and quick wins.
- On one test page, the median request took 144 ms with 1 question and 151 ms with all 45.
- The 45 questions count as input tokens and make up roughly 40% of the $0.10 cost.
- A deep scan button asks Jev which sentence holds each problem and links findings to their line on GitHub.
Questions about this entry
Short answers drawn from the linked project or page.
Clone the Django repository with git clone --depth 1, set TYPESAFE_API_KEY, and run audit.py. The sample asks 7 of the 45 questions, sends 12 pages at a time, and lists the 20 pages with the highest priority.
About $0.10 for all 279 pages. The 45 questions per request count as input tokens and make up roughly 40% of that cost; more questions add cost but little time.
On one test page the median request took 144 ms with 1 question and 151 ms with all 45, because Jev answers every question in a request in parallel. The full audit runs in under 5 seconds.
It uses Score, Choice, and Noul questions: 8 on quality, 5 on importance, 7 classification questions such as Divio type and fix effort, 21 problem flags, and 4 quick-win flags.
One request holds one page plus site context describing docs.djangoproject.com and noting that Sphinx reStructuredText markup is source markup, not an error. An API key from the TypeSafe console is required.
There is no limit on the number of questions, only on context length. The audit asks every question that might be useful, including ones that flag only a handful of pages.
Each page has a deep scan button that asks Jev which sentence holds each problem and highlights it. Findings link to their line on GitHub, so flagged typos can be fixed in a pull request.
More Jev resources like this
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Jev Cookbooks#community#python#robotics
Community
FBddcz/embodied-jevPython
FBddcz/embodied-jevPythonA demo application that navigates a Neo4j graph one hop at a time: Jev gets the outgoing relationships as a Choice plus a goal Noul in one system_one call, and beam search follows the probabilities.
Jev Cookbooks#community#python#neo4j
Community
jexp/neo4jevJupyter Notebook
jexp/neo4jevJupyter NotebookA side-by-side T-Rex game where local Laya runs on Apple Silicon through MLX and hosted Jev uses the TypeSafe API, showing choices, latency, survival streaks, and crash replays on one course.
Jev Cookbooks#community#python#games
Community
virajbhartiya/laya-vs-jevPython
virajbhartiya/laya-vs-jevPythonA fine-grained robot control study loop for LIBERO tasks: Jev layers an intent, a contact or motion family, and one of 27 control inputs, while reversible MuJoCo previews evaluate each candidate before execution.
Jev Cookbooks#community#python#robotics
Community
Dimweaker/jev-liberoPython
Dimweaker/jev-liberoPythonA ManiSkill demo where plain-English goals drive a simulated Franka Panda: Jev picks one primitive per step from a catalog of about 30 hardcoded skills, and Python executes the move. No training or policy.
Jev Cookbooks#community#python#robotics
Community
TarunTomar122/jev-askable-armPython
TarunTomar122/jev-askable-armPythonSpanish-language prototype that uses Jev to classify event sign-ups and decide program, action, and message before sending, with a guardrail that approves, flags, or blocks outgoing text. Includes synthetic datasets, evaluation scripts, and a local engine that runs without a key.
Jev Demos & Experiments#madewithjev#demo#python
Communityblockstars-labs/30x-JEV
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.