Agent action approval with decision models

Grok Bot preflight layer: local hard gates first, then Jev judges ambiguity and returns proceed, scope_down, ask_human or block.

Hermes Agent approvals provider where one Jev request answers six typed questions and code derives APPROVE, DENY or ESCALATE.

Decision engine that combines Jev probability distributions with loss matrices to decide when a clarifying question is worth asking.

Example of Jev as a before-tool-call risk gate in a Google ADK agent, blocking tools when P(risky) passes a threshold.

Skill and CLI that compares a shortlist of agents, MCP servers or skills against a task and permission ceiling, abstaining on weak leads.

Python guardrail with a Streamlit dashboard that sends agent tool calls to Jev and allows, blocks or asks for clarification.

Jev Router for Cursor: Jev picks a COST, BALANCED or INTELLIGENCE tier per task, with soft routing in chat and hard routing via the SDK.

Codex computer-use skill where Jev picks the next on-screen element, action, completion and risk from text candidates.

Experimental browser-only MCP server where Jev picks a code-owned action ID and a human approves before execution.

Guide and small prototype for using Jev with Herdr to route tasks to coding agents like Claude, Codex and Hermes under code-owned policy.

Autonomous PR review bot with typed Jev questions, deterministic approval gates and escalation of uncertain reviews to trusted owners.

Strict-allowlist shell harness where Jev walks a TOML decision tree to pick a bash command, flags and paths, confirming writes.

On-device Android agent that taps any app, with an allow/confirm/block safety gate optionally backed by Jev or Laya.

Rust template for multi-agent orchestration with Jev as the L0 layer for typed routing, risk and escalation decisions.

OpenCode plugin collection whose oc-auto-perms package uses Jev to check tool-call intent against natural-language permission rules.

OMP extension keeping one endless chat as a summary tree, with five Jev judge gates for rules, prefetch, compression, tools and recall.

Desktop computer-use agent for macOS and Windows where Jev chooses each concrete native action, with optional GPT-6 Astra planning.

Execution-control layer for MCP agents: deterministic policy, Jev decisions, human approval and one-use execution permits.

Buildathon entry adding failproofai policies plus Jev intent checks so an IT service-desk agent stops harmful actions.

Small one-file Pydantic AI examples where Jev guards prompts, gates shell commands, judges evals and plays Flappy Bird.

Rust governance layer that treats Jev's per-tool-call scope and destructiveness checks as evidence feeding persistent trust state.

Datadog Labs Rust library for observability control loops where Jev recommends an action and declared guards decide if it commits.

Hackathon arena where 200 people attack a support agent and a Jev allow/block/escalate gate on every tool call is hardened each round.

Proof-of-concept Claude Code plugin where Jev checks every pending tool call against the session plan, then allows, asks or blocks.

Unity Behavior action node that gets finite-outcome Jev decisions through an authenticated Node gateway with revision checks.

Educational email agent where Jev picks each message's label, reply need and family flag before drafting.

Typed judgment harness for coding agents with gates from PRD to release; runs on JSON-forced LLMs today and Jev by swapping the backend.

Language and VM for long-running agent programs that pause for approval, resume after restarts and replay, with typed decision cells.

Reliability-curve study of Jev on 240 hand-labelled agent tool calls, publishing labels, raw responses and scripts.

Minimal agent loop where Jev selects each action and approves tool calls, a chat model fills arguments, and MCP tools execute.