Vercel fx: Jev as a command safety reviewer
Guillermo Rauch's X post: Jev reviews every command in Vercel's fx tool as a safety reviewer, faster and more accurate than a chat model.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
In this X post, Vercel's CEO Guillermo Rauch describes using Jev as the safety reviewer in fx, a Vercel tool. According to the list summaries, Jev reviews every fx command and is faster and more accurate than a chat model for the job.
It is a notable example of a decision model being used as a command-safety gate in a real developer tool, though details such as the questions and thresholds are not given.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this command safe to run?(inferred) | safe · unsafe |
How it works
- A user issues an fx command.
- Jev reviews it for safety.
- The command runs or is blocked or flagged.
Strengths
- Real-world use of Jev as a command gate.
- Reported faster and more accurate than a chat model.
Caveats
- Claim from a social post; no published method.
- Implementation details unknown.
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
The safety reviewer in fx.
wh000wh000/awesome-jev-liveGuillermo Rauch: Jev reviews every fx command, faster and more accurate than a chat model.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev do in fx?
Reviews every command for safety, per the post.
Who posted it?
Guillermo Rauch of Vercel.
Are there benchmarks?
The post claims better speed and accuracy than a chat model but gives no published method.
Related projects
Auditable Zig terminal agent pairing Codex for coding with Jev typed preflight and postflight checks under deterministic policy gates.
CLIproductionZigGateway that checks agent tool calls with policy plus Jev evidence, then binds approval to a single-use permit for that exact action.
MCP serverbetaTypeScriptMCP proxy and hooks that screen agent tool calls before they run and their results before the agent reads them, using Jev judgments.
MCP serverbetaTypeScriptXano backend template where Jev judges each agent tool call as safe, needs review or dangerous, and uncertain calls wait for a human.
ProjectbetaXanoScriptOpenAI-compatible endpoint that answers an agent's command-approval call with APPROVE, DENY or ESCALATE from a Jev Choice, failing closed.
ProxybetaPythonClaude Code plugin adding Jev judgments to Bash, Write and Edit calls and their outputs; a semantic guardrail, not a sandbox.
Pluginbeta