CommunityJev Demos & Experiments
A data analyst agent with Jev as the review layer
An open-source data analyst agent that keeps Qwen for generating SQL and uses Jev as a review layer at three checkpoints: question clarity, SQL fidelity to the request, and whether the final explanation is grounded in the returned rows.
- Published by
- Community
- Author
- Sumanth
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open source
Highlights
- Qwen generates SQL and the answer; Jev reviews at three points; deterministic code controls execution.
- Jev flags ambiguous questions, like which metric best means, before the agent commits to one.
- Execution stays in code: read-only SELECT, read-only SQLite, 200-row cap, human approval for unsafe queries.
Watch out
A demonstration of the review-layer pattern rather than a hardened product; it wires Qwen through a gateway and needs the relevant API keys to run live.
Questions about this entry
Short answers drawn from the linked project or page.
An open-source natural-language data analyst agent. Qwen generates the SQL and the answer, deterministic code controls execution, and Jev acts as a review layer at three points in the loop.
Before it starts, Jev checks whether the question is clear enough to answer from the data; after SQL is generated, whether the query matches the request; and after the query runs, whether the explanation is grounded in the returned rows.
Asking who the best customer is. Best could mean highest revenue, most purchases, or highest average order value, so Jev flags the ambiguity and asks for clarification instead of letting Qwen silently pick a metric.
Execution safety. The tool accepts only a single read-only SELECT, SQLite runs read-only, results are capped at 200 rows, and queries without a WHERE clause can require human approval before running.
Because a query can be safe and still answer the wrong question. Code verifies the SQL is read-only, while Jev judges whether it represents the request, which a rule cannot reliably do.
A local SQLite sales database, Qwen through the Vercel AI Gateway, Gradio for the interface, and two database tools, inspect_schema and run_sql. It is fully open source under the author's repository.
In the author's Hands-On-AI-Engineering repository, under ai_agents/nl_data_analyst_agent, published by Sumanth as an end-to-end example of the generate, review, and act split.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: A MySQL plugin that filters rows by asking Jev whether a column matches a sentence.
maayanlevy-hn2 pointsA MySQL plugin that filters rows by meaning (built on TypeSafe Jev)Read the thread on Hacker NewsX: jev(): Postgres WHERE clauses in plain language
More Jev resources like this
97GitHub stars
A Playwright-based CodexQA skill where Jev chooses indexed controls on a page-built index while the browser executes the action.
Jev Demos & Experiments#community#browser#playwright
Community
openqa-cn/jev-browserTypeScript
openqa-cn/jev-browserTypeScript29.3kGitHub stars
The Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
trycua/cuaRust221GitHub stars
An agent skill that reproduces Jev-style single-step logits over indexed browser controls using local Qwen weights for offline browser use.
Jev Demos & Experiments#community#browser#open-models
Community
APUS-AI-Lab/fast-browser-usePython
APUS-AI-Lab/fast-browser-usePythonAn agricultural advisory demo that turns sensor readings, a forecast, and a crop stage into a next-action choice plus an urgency score, routing marginal readings to an agronomist instead of triggering an application.
Jev Demos & Experiments#community#python#agriculture
Community
A travel rebooking demo that classifies a trip disruption, checks itinerary feasibility, and ranks concrete rebooking options against a traveler's ordered preferences, returning ordered choices with probabilities.
Jev Demos & Experiments#community#typescript#travel
Community
20.5kGitHub stars
Python agent framework whose TypeSafeModel class runs Jev as a decision model inside Pydantic AI agents: Pydantic output-type fields become typed Jev questions answered together in one request, each answer carrying its own confidence, and tools can be offered as Choice options.
Jev Integrations & Adapters#community#agents#framework
Community
pydantic/pydantic-aiPython
pydantic/pydantic-aiPythonFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.